Retour

Explorez tous les épisodes du podcast Digital Pathology Podcast

Plongez dans la liste complète des épisodes de Digital Pathology Podcast. Chaque épisode est catalogué accompagné de descriptions détaillées, ce qui facilite la recherche et l'exploration de sujets spécifiques. Suivez tous les épisodes de votre podcast préféré et ne manquez aucun contenu pertinent.

Rows per page:

1–50 of 242

TitreDateDurée
170: Inside SITC 2025: How Multiplex IF Is Changing Cancer Care07 Nov 202500:22:50

Send us Fan Mail

Can spatial biology and multiplex immunofluorescence truly transform how we understand cancer?

I went live from the Society for Immunotherapy of Cancer (SITC) 2025 — the 40th Anniversary Meeting to explore how spatial biology, multiplex IF, and digital pathology are coming together to redefine cancer diagnostics, research, and precision medicine.

This session kicked off a weekend of cutting-edge discussions with leaders from Hamamatsu (Booth 415) and Biocare Medical (Booth 717) — two companies helping laboratories around the world embrace digital transformation and spatial imaging in oncology.

🧠 Episode Highlights & Key Moments

0:00 — Introduction
I set the stage live from SITC 2025, explaining the goal of this series: to connect the science of multiplex imaging and spatial analysis with the practical needs of today’s cancer pathologists and researchers.

~1:00 — What Is Multiplex Immunofluorescence (IF)?
I explain how multiplex IF enables simultaneous detection of multiple biomarkers and immune cell types within a single tumor sample — giving us an unprecedented look at the tumor microenvironment and how cells interact.

~2:30 — The Spatial Biology Revolution
We talk about spatial biology as the “next frontier” beyond traditional histopathology — visualizing not just what is on the slide, but where it happens.

~5:00 — Digital Pathology & AI Readiness
I discuss the importance of digital pathology systems for slide digitization and how AI-powered software is now helping identify biomarkers, quantify expression, and accelerate immunotherapy research.

~7:30 — Featured Booths at SITC 2025

  • Hamamatsu (Booth 415): High-end slide scanners and digital imaging solutions empowering pathology labs toward digital readiness.
  • Biocare Medical (Booth 717): Showcasing the ONCORE Pro X — an open slide stainer that automates multiplex IF, IHC, FISH, and ISH protocols, plus smart software for optimizing complex staining processes.

~9:00 — Real-World Impact
We walk through clinical case examples where multiplex IF data guides immunotherapy decisions — helping clinicians stratify patients and tailor treatments more precisely.

~12:00 — Getting Started
I share practical advice for researchers ready to adopt spatial biology or digital pathology, from workflow design to validation and staff training.

~15:00 — Audience Q&A
Live questions from the audience on implementation, data integration, and scaling multiplex workflows across research and clinical environments.

~20:00 — Future Directions
We look ahead to how machine learning and spatial data integration will shape the next decade of immuno-oncology, including new SITC workshops on AI-driven tissue profiling.

~24:00 — Wrap-Up & Takeaways
Key message: spatial biology is not just a trend — it’s the next layer of precision medicine. I invite everyone to visit Hamamatsu (Booth 415) and Biocare (Booth 717) and to stay tuned for the next livestream focused on multiplex IF in clinical settings.


Resources Mentioned

🔹 Hamamatsu Photonics (Booth 415)
High-performance digital slide scanners and imaging systems.
🌐 hamamatsu.com

🔹 Biocare Medical (Booth 717)
ONCORE Pro X — Open slide stainer automating advanced multiplex imaging workflows.
🌐 biocare.net

🔹 SITC 2025 Official Information
Conference programs, workshops, and educational resources.
🌐 sitcancer.org

My Takeaway:

Spatial biology and multiplex IF a

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

169: AI Across Organ Systems: Kidney, Liver, Colon, Bladder, and Beyond03 Nov 202500:37:50

Send us Fan Mail

Can one AI system learn from every organ — and teach us something new about all of them?

In this edition of DigiPath Digest #31, I explore how artificial intelligence is transforming pathology across multiple organ systems, revealing connections that help us diagnose faster, more consistently, and more accurately than ever before.

From glomerulonephritis to hepatocellular carcinoma, AI is no longer confined to a single specialty — it’s becoming the connective tissue between them.

What’s Inside:

1️⃣ AI for Bladder Cancer Classification
We begin with a multicenter study validating AI models for urothelial neoplasm classification using over 12,000 whole-slide images. Both CNNs and transformer models achieved high accuracy (AUC 0.983, F1 score 0.9). I discuss why the F1 score matters — and what it tells us about model balance between sensitivity and specificity.

2️⃣ AI in Colorectal Cancer Care
Next, we explore multimodal AI — integrating histopathology, radiology, genomics, and blood markers to modernize colorectal cancer workflows. AI now helps detect adenomas, infer microsatellite instability (MSI) from H&E slides, and predict treatment outcomes. I highlight the critical need for external validation, interpretability, and governance as AI enters clinical use.

3️⃣ AI for Glomerular Nephritis Diagnosis
A deep learning model trained on over 100,000 kidney biopsy images identified four nephritis types — FSGS, IgA, MN, and MCD — with over 85% accuracy. This technology could ease workloads and improve turnaround time in renal pathology. Still, I share why AI support may feel both empowering and unsettling for many pathologists.

4️⃣ AI in Liver Disease (MASLD & HCC)
AI is advancing noninvasive fibrosis staging and risk prediction in liver pathology. From large consortia like NIMBLE and LITMUS to predictive models for HCC therapy response, AI is moving us closer to precision hepatology. I also discuss the challenge of translating these tools from research to regulatory approval.

5️⃣ Lightweight AI for Domain Generalization
Finally, we look at one of pathology AI’s biggest challenges: domain shift — when a model trained on one scanner or staining style performs poorly elsewhere. The new Histolite framework shows how lightweight, self-supervised models can generalize across data sources — trading some accuracy for reliability in real-world use.

My Takeaway

Across every study, a single message stands out:
 AI isn’t replacing pathologists — it’s amplifying our vision.
By connecting kidney, colon, liver, and bladder insights, AI is teaching us that medicine works best when it learns across boundaries.

Episode Highlights

  • Bladder cancer AI validation (06:41)
  • Multimodal colorectal AI (12:38)
  • Glomerular nephritis deep learning (19:29)
  • AI in liver pathology (29:55)
  • Domain shift & Histolite framework (38:17)
  • Halloween wrap-up + SITC preview (46:18)

Join me next time for updates from the SITC 2025 Conference, where I’ll be live at Booth 415 with Hamamatsu and Biocare, discussing how AI and spatial biology are converging to drive clinical utility.

#DigitalPathology #AIinHealthcare #ComputationalPathology #CancerDiagnostics #LiverPathology #RenalPathology #FutureOfMedicine #DigiPathDigest

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

160: AI in Medicine: Neuropathology, Renal Disease, Hematology & Cytology31 Aug 202500:25:14

Send us Fan Mail

What if the way we quantify pathology is more guesswork than science? In this episode of DigiPath Digest, I take you through the latest research where AI is not just supporting but challenging traditional methods of image analysis in neuropathology, nephrology, hematology, and cytology. From Boston brain banks to Mayo Clinic kidney models, we look at how advanced AI compares to human vision—and where it already outperforms us.

Episode Highlights:

  • [00:02:49] Neuropathology image analysis (Boston VA & BU) – Why traditional semiquantitative scoring often fails, and how AI-based density quantification reveals more subtle pathology in CTE.
  • [00:13:16] Chronic kidney changes with AI (Mayo Clinic, Cambridge, Emory, Geneva) – A 20-class AI model trained on 20,500 annotations, showing how multiclass segmentation outperforms human guesswork in renal pathology.
  • [00:21:09] Digital hematology review (University of Pennsylvania) – Current hurdles in AI for blood and bone marrow evaluation: regulatory oversight, data standardization, and resistance to change.
  • [00:25:52] AI in cytology review (Journal of Cytopathology) – From BD FocalPoint to deep learning: two decades of digital cytology, stagnation, and why adoption still lags despite proven benefits.
  • [00:32:09] Neuropathology goes digital – Where digital neuropathology is already routine (Ohio State, Mayo Clinic, Leeds, Granada) and why this specialty is crucial for pushing adoption.
  • [00:34:19] Personal note – Why I believe learning, sharing, and experimenting with AI tools now will shape the way we practice pathology tomorrow.

Resources from this Episode

  • Comparison of quantitative strategies in neuropathologic image analysis – Boston VA / BU Brain Bank study.
  • Multiclass AI model for chronic kidney changes – Mayo Clinic, Cambridge, Emory, Georgia Tech, Geneva collaboration.
  • Review: Digital hematology in the AI era – International Journal of Laboratory Hematology.
  • Review: AI and machine learning in cytology – Journal of the American Society of Cytopathology.
  • Digital Pathology 101 (by me, Dr. Aleksandra Zuraw) – Free PDF & Amazon print edition.
  • Pathology AI Makeover Course – Practical training for AI in pathology workflows.



Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

70: Digital Pathology 101 Chapter 1 (Part 1) | Digital Pathology Milestones and Basic Digitalization Concepts10 Oct 202300:51:11

Send us Fan Mail

Get the PDF of "Digital Pathology 101" Book here

Get the paper copy  of "Digital Pathology 101" on AMAZON


I'm thrilled to introduce you to a long-awaited companion in your digital pathology voyage – the book, "Digital Pathology 101 - All you need to know to start and continue your digital pathology journey."

This book is the culmination of months of passion and hard work. If you've been following me on social media, you know it's been a labor of love. But why did I write this book, you might ask? Well, it's your comprehensive guide to navigating and thriving in the realm of digital pathology.

But first, let's rewind a bit. Back in 2003, Dr. Anil Parwani predicted that everyone would be digital by 2007. Well, that might have been a bit too optimistic, but guess what? The digital age in pathology is here, and it's not a distant future; it's right around the corner.

I'm convinced that now is the time, and that's why I'm so excited to share this book with you.

If you missed our webinar launch, don't worry – you can catch the replay here

In that webinar, I delved deep into why digital pathology is the future, and trust me, it's a future you don't want to miss out on.

But enough about that, let's dive into the first chapter of the audio version of "Digital Pathology 101." In this chapter, we'll explore the historical milestones that paved the way for digital pathology. So, without further ado, let's get started on this journey into the world of digital pathology.

Here is what we will cover in this part of chapter 1:

DIGITAL PATHOLOGY MILESTONES

  • A. Historical Milestone
  • B. Regulatory Milestone

BASIC DIGITALIZATION CONCEPTS

  • A. About Digitization, Digitalization and Digital Transformation
  • B. Digitization - The Scanner and its Components
  • C. Digitalization and its challenges - Data Generation and Management
  • D. Digital transformation: Advantages and Challenges of Digital Pathology

--------------------------------------------------------------------------------------

Get the PDF of "Digital Pathology 101" Book here

Get the paper copy  of "Digital Pathology 101" on AMAZON

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

69: How to Set Realistic Expectation in Digital Transformation w/ Anil Parwani, Ohio State University04 Oct 202300:33:46

Send us Fan Mail

 In this episode of "The Digital Pathology Podcast," we delve into the fascinating career of Dr. Anil Parwani from Ohio State University, a visionary whose ardor for technology and research paved the way for groundbreaking advancements in digital pathology.

Dr. Parwani's journey commenced with a bold move – launching a web educational series during his residency – well ahead of digital pathology's mainstream emergence. As we delve into his narrative, you'll witness how his pioneering spirit laid the groundwork for a transformative trajectory. The pivotal moment? It arrived with the debut of the first digital pathology scanners. Dr. Parwani envisioned a future where patient care and pathology research could soar to unprecedented heights through digitization. His role in implementing digital pathology solutions, including collaborations with startups, deepened his grasp of the clinical significance of this game-changing technology.

As the COVID-19 pandemic accelerated technological advancements in digital pathology, Dr. Parwani witnessed a significant 20% surge in adoption within his institution. How did they strike the ideal balance between remote and in-person interactions? Discover the insights in this episode.

Furthermore, in an era where the number of medical students pursuing pathology is dwindling, we'll examine how digital pathology is sparking renewed interest. Dr. Parwani reveals how this field, with its research prospects, educational promise, and collaborative ethos, is reshaping perceptions and attracting fresh talent.

Stay tuned for an expedition through the dynamic realm of digital pathology with Dr. Anil Parwani. It's a captivating odyssey into innovation, precision, and the future of medical science that promises not to disappoint!

Start your 7-day free trial: Digital Pathology Club Membership

EPISODES YOU WILL ALSO ENJOY:

DIGITAL PATHOLOGY RESOURCES:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

68: The Evolution of Digital Pathology: 2013 vs. 2023 w/ Dr. Matthew O. Leavitt, DDx Foundation20 Sep 202300:56:12

Send us Fan Mail

What happened to digital pathology in the last decade?

Step into a time machine with us as we explore "The Evolution OF Digital Pathology– From Improved Histology Quality to Fair Use of Pathology Data" alongside Dr. Matt Leavitt, President of the Digital Diagnostics Foundation and Founder of Lumea. In this captivating podcast episode, we'll journey through the years and witness the incredible transformation of digital pathology.

Travel back to 2013, when digital pathology was still in its infancy, and fast forward to the present day, where innovation and technology have reshaped the landscape and ethical questions about patient data use urgently need answers.

Dr. Leavitt provides unique insights into the challenges, breakthroughs, and trends that have defined this transformative decade.

Gain a front-row seat to the evolution of healthcare innovation as we compare and contrast digital pathology then and now. Whether you're a seasoned pathologist, a tech enthusiast, or simply curious about the future of medicine, this episode promises to enlighten and inspire.

Join us on this remarkable journey through time and innovation. Subscribe to the podcast now to uncover the secrets of digital pathology's evolution and chart a course for the future. Don't miss out—tune in and be a part of this fascinating exploration!

Start your 7-day free trial: Digital Pathology Club Membership

EPISODES YOU WILL ALSO ENJOY:


DIGITAL PATHOLOGY RESOURCES:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

67: What Is the Role of Digital Pathology in Clinical Trials w/ Monika Lamba Saini29 Aug 202300:29:00

Send us Fan Mail

How is digital pathology used in clinical trials? Because digital pathology as a discipline began with the aim of streamlining clinical trials, one could assume that this is currently the default.
Unfortunately, this is not the case… In today's discussion, our guest, Dr. Monika Lamba, a pathologist from Q2 Solutions, the lab division of IQVIA, sheds light on how digital pathology revolutionizes the landscape of clinical trials but also where we can still see the gaps.

In this engaging conversation, we discover how the origins of telepathology marked the inception of digital pathology and its journey to becoming an essential component of clinical trials.
Dr. Lamba walks us through the complexities of clinical trials, their organization, and patient matching across multiple sites and international boundaries.

As we unravel the role of pathology in clinical trials, we delve into how eligibility criteria, participant engagement, and informed consent are intricately woven into the process. Dr. Lamba educates us on the critical role of pathology in stratifying and randomizing patients, as well as evaluating outcome measures.
 
From disease staging to pathologic complete response assessments, pathology guides the way toward precision medicine and targeted therapies. Don't miss this captivating episode where we explore the synergy between digital pathology and clinical trials, paving the path for medical advancements and transformative healthcare solutions. Tune in now to expand your horizons on the ever-evolving intersection of digital pathology and clinical trials.

Start your 7-day free trial: Digital Pathology Club Membership


EPISODES YOU WILL ALSO ENJOY:

DIGITAL PATHOLOGY RESOURCES:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

66: What You Need to Know About Digital Pathology Trends: Takeaways from the DP & AI Global Engage Event with Giovanni Lujan02 Aug 202300:20:50

Send us Fan Mail

Welcome to a very spontaneous and exciting episode of the Digital Pathology Podcast. In this episode, I had the pleasure of sitting down with Dr. Giovanni Lujan from Ohio State University, whom you might remember from our previous crossover podcasts with Beyond the Scope.

Recently, we were at the Digital Pathology and AI Congress in New York organized by Global Engage, and guess what? We decided to record this episode right there, surrounded by the buzz of the conference. No fancy preparations, just real and raw insights for you.

Giovanni and I are sharing our impressions and discussing the latest trends in digital pathology that were highlighted at the Congress. It's fantastic to finally meet in person after collaborating on two podcasts together. Giovanni has been a devoted follower of our podcast and all things digital pathology, and I'm truly inspired by his passion for the field.

The Congress organized by Global Engage has a unique vibe. It's smaller, which allows for more meaningful interactions and networking opportunities with fellow professionals and vendors. The longer breaks and one-on-one meetings foster valuable connections, making this conference stand out from the rest.

Start your 7-day free trial: Digital Pathology Club Membership



THIS EPISODE'S RESOURCES:


DIGITAL PATHOLOGY RESOURCES:

Keywords: Digital Pathology Congress Recap, Networking, Insights, Global Engage Impact, Giovanni Lujan, Beyond the Scope, Cutting-edge Innovations, Stay Updated, Join Now

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

65: What Is Translational Research In Digital Pathology? /w Anant Madabhushi, Emory University & Georgia Tech06 Jul 202300:51:03

Send us Fan Mail


Bringing Science into the Clinic with Prof. Anant Madabhushi

Translational research - what is it actually? How do you do it? 

I can already tell you how not to do it - halfheartedly. 

If you want to translate your scientific discoveries into something that actually benefits patients, you need to do all in! 

And this is what my guest Prof. Anant Madabhushi from the Emory University and Georgia Tech has dedicated his entire professional career to. 

He offers his insights on what it really takes to "walk your scientific talk" and work as a truly translational researcher in the space of digital pathology, radiology and medical engineering. 

Listen to an in-depth discussion about conducting high-quality science and the rigorous journey of commercializing the research and actually benefiting the patients with it.

With his vast experience and profound understanding, Prof. Madabhushi gives us an insider's view of the effort and time required to successfully take a scientific discovery from the lab to a clinical trial, and then to the market. His perspective is enriched by his role as founder of several med tech companies, co-author of numerous high impact factor scientific publications, and a mentor and teacher to the next generation of brilliant computational pathology scientists.

THIS EPISODE'S RESOURCES:


DIGITAL PATHOLOGY RESOURCES:


Keywords: digital pathology, translational research, image biomarkers, clinical practice, healthcare professionals

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

64: How To Overcome Challenges In Image Analysis For Spatial Biology w/ Lorenz Rognoni, Ultivue08 Jun 202300:20:56

Send us Fan Mail


Exploring Spatial Biology and Image Analysis with Lorenz Rognoni

Get ready for a deep dive into spatial biology and image analysis with Lorenz Rognoni, the Director of Image Data Science at Ultivue. Ultivue is a company specializing in spatial biology and Lorenz brings his wealth of knowledge in multiplex immunofluorescence (mIF) and image data science to this great conversation.


Multiplex IF: Challenges and Complexities

We kick off our discussion by addressing the inherent challenges in multiplex IF. The conversation spans a range of issues including tissue preparation artifacts, unique tissue morphology, and antibody-specific staining. The vast variability of tissues, differing across body regions, species, and health conditions, is a recurring theme. We also delve into the effectiveness of expert visual evaluation for traditional stains and the need for new strategies to interpret high-dimensional data.


Brightfield Imaging in Spatial Biology: Does it Still Play a Role?

Shifting gears, we discuss the role of brightfield imaging in spatial biology. Is there still space for brightfield if we want to learn the spatial interactions of cells in the tissue? Is this method not too limiting?
Lorenz underscores its continued relevance, particularly when robustness and scalability are prerequisites. He suggests transitioning to simpler methods like singleplex IF or even brightfield imaging, once research zeroes in on specific biomarkers of relevance with multiplex IF.


Transitioning from Image Analysis to Data Interpretation: Navigating the Pitfalls

Our conversation culminates in a look at the challenges and potential missteps in moving from image analysis to interpreting the data generated. Lorenz points out the crucial process of extracting meaningful insights from millions of cells, defining appropriate phenotypes, and considering the intricacies of downstream data mining.


Key Takeaways

  • mIF is an exploratory method and the insights gained can later be transitioned ti simpler methods such as single market IF or IHC
  • The spatial biology research relies on accurate cell segmentation and identifying the correct phenotypes of cells. 
  • Correct segmentation is the first step to explore the insights and this exploration is being done through informed data mining that takes into consideration all the information about the study. This is best done by an image data science team where image analysis scientists, data mining experts and pathologists work together. 

Join us for this insightful conversation and gain a deeper understanding of the complexities and nuances of spatial biology and image data science with Lorenz Rognoni.

Keywords: Lorenz Rognoni, Ultivue, spatial biology, image analysis, multiplex immunofluorescence, tissue morphology, brightfield imaging, data mining



THIS EPISODE'S RESOURCES:

DIGITAL PATHOLOGY PLACE RESOURCES:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

63: Is this the year of AI in pathology? And what about ChtGPT? A crossover podcast with Beyond the Scope.24 May 202300:33:39

Send us Fan Mail

Welcome to the crossover podcast with David, Giovanni and myself (Aleks) again. During this episode, we explore the world of digital pathology, artificial intelligence, including Chat GPT, and their growing importance in the field.

Is 2023 the year of AI for digital pathology?

We will talk about it and about the impact of AI in digital pathology and how Chat GPT could transform the way pathology reports are written. We discuss the benefits of using AI in digital pathology and what the future holds for this field.

As the discussion progresses, the experts explain the workflow of digital pathology and its advancements, including deep learning, and the role of AI in these advancements. They also discuss how Open AI Chat GPT is changing the landscape of artificial intelligence news.

Join Giovanni, David and myself for an engaging and insightful conversation about the latest advancements in digital pathology and the future possibilities of AI and Chat GPT in this field. 

THIS EPISODE'S RESOURCES:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

62: Changing Stereotypes of Pathology. How Pathologists Contribute to Patient Care w/ Marilyn Bui, Moffitt Cancer Center02 May 202300:36:04

Send us Fan Mail

Have you heard the stereotype of a pathologist hidden behind the microscope (or in the era of digital pathology behind the computer screen). Pathologist as the doctors' doctor? 

Today, I have a special guest who defies this stereotype! 

Dr. Marilyn Bui, a specialized cytopathologist, is patient-focused and emphasizes the patient-centricity of pathology work. She co-authored a book, "The Healing Art of Pathology", and amplifies her message by being a leader in various organizations. 

Dr. Bui is the current president of the Florida Society of Pathologists and previously held the same role in the Digital Pathology Association.

In this episode, Dr. Bui shares her background and how she became a patient-centered pathologist. She talks about her work in tissue pathology, cytopathology, and digital pathology at Moffitt Cancer Center in Tampa, Florida, where she also teaches and conducts research. 

Dr. Bui believes that pathology and laboratory medicine are essential disciplines in healthcare, and she advocates for their protection and augmentation.

Join me in this conversation with Dr. Marilyn Bui as we delve deeper into the world of pathology and learn more about her book, "The Healing Art of Pathology."


THIS EPISODE'S RESOURCES:

-----------------------------------------------------------------

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

61: The best online pathology book ever w/ Nat Pernick, PathologyOutlines.com17 Apr 202300:24:47

Send us Fan Mail

 Introduction
Are you curious about what goes into creating a cutting-edge digital online resource like PathologyOutlines.com? Then this episode is for you!

 About PathologyOutlines.com
PathologyOutlines.com is a living textbook that covers 4,800 topics and involves 300+ contributors and 60 editors. It's a comprehensive online pathology resource that provides invaluable information for anyone in the pathology space.

PathologyOutlines.com Peer Review Process
The PathologyOutlines.com team takes great pride in their accuracy and responsiveness, as evidenced by their peer review process and willingness to address typos and other errors brought to their attention by users immediately.

Contributing to PathologyOutlines.com
PathologyOutlines.com is seeking contributors who are willing to submit their own images and articles to the website. This is a fantastic opportunity for anyone in the pathology field who is looking to expand their online portfolio and make a valuable contribution to the industry.

Personal Profile on PathologyOutlines.com
PathologyOutlines.com offers the chance to create a mini personal page on their website. This is a great opportunity for anyone practicing pathology in the world to be featured in the PATHOLOGIST DIRECTORY.

 IHC Stains and CD Markers Explained
The page with all the IHC stains and CD markers explained is a favorite resource of many pathology professionals. This is an invaluable resource for anyone working in the IHC quantification space.

Digital Pathology Starter Kit
For those just starting their journey in digital pathology I have a special gift - the Digital Pathology Starter Kit. It contains valuable resources and information to help you get started on your digital pathology journey. This includes tips on how to choose a scanner, recommendations for digital pathology software, and much more.

Keywords: digital pathology, pathology professionals, PathologyOutlines.com, online pathology resource, peer review process, contributors, IHC stains, CD markers, digital pathology starter kit, personal profile.


THIS EPISODES RESOURCES:


Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

159: What If Your AI Tool Is Lying: Hidden Bias in Pathology Algorithms30 Aug 202500:27:49

Send us Fan Mail

What if the AI tools we trust for cancer diagnosis are not always correct? This episode of DigiPath Digest takes on the uncomfortable but critical question: can AI “lie” to us—and how do we verify its performance before adopting it in clinical practice?

Highlights:

  • [00:02:00] Foundation models in action: Deployment of a fine-tuned pathology foundation model for EGFR biomarker detection in lung cancer—reducing the need for rapid molecular tests by 43%.
  • [00:08:41] Bone marrow AI misclassifications: Why automated digital morphology still struggles with consistency across leukemia and lymphoma cases.
  • [00:14:45] Lossy DICOM conversion: How file format changes can subtly—but significantly—affect AI model performance.
  • [00:21:45] Federated tumor segmentation challenge: Coordinating 32 international institutions to benchmark healthcare AI fairly across diverse datasets.
  • [00:27:47] AI in gynecologic cytology: Reviewing AI-driven Pap smear screening—promise, limitations, and why rigorous validation remains essential.
  • [00:32:27] Takeaway: Trust but verify—AI tools must be validated before they can support or replace clinical decisions.

Resources from this Episode

  • Nature Medicine – Fine-tuned pathology foundation model for lung cancer EGFR biomarker detection.
  • Scientific Reports (Germany) – Study on how DICOM conversion impacts AI performance in digital pathology.
  • Federated Tumor Segmentation Challenge – Benchmarking AI across 32 global institutions.
  • Acta Cytologica – Review on AI in gynecologic cytology and Pap smear screening.

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

60: End-to-End Solution for Digital Pathology w/ Leif Honda, TriMetis Life Sciences10 Apr 202300:48:46

Send us Fan Mail

In digital pathology is it  best to start small and incrementally implement the technology or go all in to reap all the the benefits at once?

The good news is that those two approaches are not mutually exclusive, you can totally start small and scale up, and you can do it with just one vendor partner if you feel like it!

This episode's guest is Leif Honda, Chief Innovation Officer at TriMetis Life Sciences. TriMetis is a unique company that serves as an external hub for those who want to start digital pathology but do not have all the components.

In an ideal world, going all-in would be the best option, but due to the high costs, it may be better to start small and work with partnering companies to take advantage of the full infrastructure and TriMetic can help with that. 

Leif has an extraordinary background - he has a molecular biology and economic degree. This combination positions him perfectly to be the Chief Innovation Officer. 

TriMetis started as a biobank, and started leveraging digital pathology to digitize the H&E slides of their biobank samples. Later they started using image analysis to quantify the amount and type of tissue present in their biobanking samples. Then they offered this type of service to other biobanks and other research institutions. 

They are on a mission to accelerate cancer research through facilitating access to the relevant bio-specimen for everyone who needs them. Currently they also enable the image analysis algorithm creators to deliver their algorithms to cancer researchers and deploy them through the TriMetis digital platform. 

All these developments make TriMetis an End-to-End digital pathology solution for cancer researchers. 

Listen to the full episode to learn more about how you can benefit from their work. 

THIS EPISODE'S RESOURCES:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

59: Top 5 Mistakes you must AVOID in using Machine Learning for pathology w/ Heather Couture, PixelScientia Labs22 Mar 202300:32:20

Send us Fan Mail

The field of pathology has been revolutionized by the introduction of machine learning techniques, which enable more efficient and accurate diagnoses and have the potential to some day even eliminate or reduce the number of expensive molecular tests. However, the model development is a complex process and  there are certain mistakes that must be avoided when using machine learning for pathology. 

In this informative discussion with Heather Couture, an expert in machine learning for pathology, she highlights the top 5 MISTAKES THAT YOU MUSTAVOID to ensure the best possible machine learning and deep learning project outcomes.

Through her insights, you will learn about the 5 most common ML mistakes and how to avoid them:

  1.  Not understanding your data and its challenges.
  2. Diving in without researching prior work (academic research and open source code) that is similar to what you're trying to model.
  3. Starting with too complex a model.
  4. Not thinking ahead towards validation.
  5. Not fully understanding how the technology will ultimately be used.


By avoiding these common mistakes, you can maximize the benefits of machine learning for pathology and ensure accurate and timely project results and product launches. Whether you are new to machine learning or an experienced practitioner, this discussion is a valuable resource for anyone interested in using machine learning (including deep learning) for pathology.

THIS EPISODE'S RESOURCES:

📰 Heather's amazing newsletter (Computer Vision Insights)
🎧 Heather's fantastic podcast "Impact AI"
🎙️ Aleks' previous podcast with Heather (1) - Why machine learning expertise is needed for digital pathology projects
🎙️ Aleks' previous podcast with Heather - How to make machine learning models more robust

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

58: The Regulatory Aspect of Digital Pathology and Translational Medicine w/ Esther Abels15 Mar 202300:33:36

Send us Fan Mail

Today's podcast is about the regulatory aspect of digital pathology and how it fits into the space between research and clinical use called translational medicine.

The podcast guest, Esther Abels, is a regulatory expert in digital pathology and a female leader in the field. She was involved in the team effort that brought the first Phillips clearance of a whole slide scanner to the attention of the FDA.

Translational research has the potential to bridge the gap between discovery and clinical practice. Its goal is to use evidence from research to target diseases and apply the insights in the clinic. 

Digital pathology is seen as a tool to expedite the development pipeline for drugs and medical devices through the use of algorithms and AI.

There are however regulatory requirements that need to be taken into consideration when developing and using digital pathology tools. For example tissue image analysis tools used to support clinical decisions need to adhere to the FDA's guidance for software as a medical device. 

The FDA is also working to define data sets that can be validated and reused for algorithm development. 
There are ongoing efforts in Europe and the US to draft laws and frameworks related to artificial intelligence and validation techniques for AI tools.

It is a best practice to engage with the FDA early and this process for drug and medical device companies starts with a pre-submission to the FDA, seeking advice and discussing the approach. To be successful the role of a regulatory architect is crucial in overseeing the process and guiding it from point A to B to Z.

In addition to being a regulatory expert in the digital pathology field, Esther is also the immediate past president of the Digital Pathology Association (DPA).  Because digital pathology brings people together from various fields, including pathologists, toxicologists, lab personnel, regulatory experts, and clinical development personnel, during her presidency Esther focused on collaboration between those different fields. 

Esther Abels is a regulatory consultant who can be found on LinkedIn and her YouTube channel, which features helpful guidance and information videos.


THIS EPISODE'S RESOURCES:

✔️ Previous podcast with Esther: REIMBURSEMENT FOR DIGITAL PATHOLOGY IN THE CLINIC – HOW DOES THAT WORK? W/ ESTHER ABELS, VISIOPHARM
✔️ FDA GUIDANCE - CLINICAL DECISION SUPPORT SOFTWARE
✔️ FDA GUIDANCE - SOWTWARE AS A MEDICAL DEVICE
✔️ FDA GUIDANCE LIST FOR DIGITAL HEALTH
✔️ Beyond the Scope Podcast "CPT Coding and Digital Pathology Reimbursement"
✔️ ESTHER ABELS LINKEDIN
✔️ ESTHER ABELS YOUTUBE

💻 Bridging the Gap Between Pathology and Computer Science

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

57: Beyond innovation - how to embrace responsibility and leadership in digital pathology at a personal and national level w/ Inti Zlobec08 Mar 202300:34:33

Send us Fan Mail

Today is the International Women's Day and this month at the Digital Pathology Podcast I decided to invite some incredible women who are leaders in the digital pathology field.

Today's guest, Inti Zlobec is a professor of Digital Pathology at the University of Bern. Inti is now leading the digital pathology branch of the Institute for Tissue Medicine and Pathology, where she bridges the gap between pathologists, computer scientists, and data scientists. She also serves as the president of the Swiss Digital Pathology Consortium. The institute's name was changed to emphasize the dynamism in pathology and its links to various other domains.

Her background is in statistics and computational research combined with a PhD in experimental pathology at the University of McGill in Canada. Combining and hybridizing those two fields has been a blessing for her in bringing people with different backgrounds together. Bothe her background and personality make here a natural connector of all digital pathology links.
 
A crucial part of this linkage is removal of the intimidation factor associated with pathologists.  Instead the focus should be on acquiring the necessary level of knowledge for collaboration. It's important to involve pathologists in the projects early and give them them a sense of contribution to foster a productive collaboration. 

Pathologists should not just be used for annotations and quick checks, but should be included in projects as equal contributors.

In addition to Inti's University appointment she also is the president of the Swiss Digital Pathology Consortium (SDPath).
 
In 2018, a group of three professionals (Inti included:) in Switzerland founded the Swiss Digital Pathology Initiative (SDPI) to promote digital pathology and exchange knowledge. The initiative grew to over 140 members, and in 2021, SDPI collaborated with the Swiss Personalized Health Network to build a digital pathology network across Switzerland.

The goal of SDPI is to harmonize and structure data by scanning cases, attaching a minimum set of variables to images, and using standardized hardware and formats. This network will allow researchers and industry partners to access virtual cohorts of patients for clinical trials, and the harmonized data sets can also help boost pharmaceutical development.

This would be the first initiative of this kind at a national level which will create a fantastic model for others to tweak and follow.

As a female in science in general and in the digital pathology field specifically, she has been fortunate to be surrounded by people who value her ideas and ideas of others, regardless of their gender. The gender gap in this field is still noticeable, particularly in more senior positions, which affects the number of female role models. Often insecurity can prevent some women from advancing,  but exposure,  experience and dedicated work on overcoming your own limitations will help. And so will involvement in initiatives such as SDPI. 

THIS EPISODE'S RESOURCES:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

56: The beginnings of computational pathology w/ Jeroen van der Laak, Radboud UMC21 Feb 202300:25:40

Send us Fan Mail

Computational pathology – how did this field even start?

In today’s episode my guest is Jeroen van der Laak, computational pathology professor at Radboud University Medical Center, who was recently listed on "The Pathologist Power List" in the category “Strange New worlds”

Jeroen has been in the field of computational pathology for over 30 years and has seen it being created and evolve. 

He witnessed how advancements in whole-slide imaging and deep learning have allowed for the practical application of AI in pathology.

Throughout the evolution of the field of computational pathology the focus has shifted from research-oriented work to direct collaboration with clinicians to test AI in diagnostic practice.

During his tenure Jeroen has seen what it takes to be successful in the field of computational and digital pathology. 

To be a successful researcher in this field you need to understand the importance of high quality data and understand how the field of pathology works and what you see in the tissue you are analyzing. 

This is a very collaborative field and a responsibility of an AI researcher is making AI accessible and breaking down technical aspects for pathologists.

Jeroen co-leads the Computational Pathology Group at Radboud with two other researchers – Francesco Ciompi and Geert Litjens. Their criteria for choosing successful candidates for a digital pathology group include good team spirit, collaboration, willingness to learn, and understanding of the field.

It is just a matter of (not too much) time when AI will become mainstream in pathology labs and will improve the accuracy and speed of patient diagnosis. Just like whole slide scanning is becoming part of the routine pathology workflow, so will AI based image analysis. 


THIS EPISODES RESOURCES

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

55: Merging hardware and software to deliver 2nd generation digital pathology w/ Prasanth Perugupalli, Pramana31 Jan 202300:36:08

Send us Fan Mail

Although digital pathology was supposed to be faster and more seamless than classical pathology on glass there are still many manual steps in the workflow. 

  • Cleaning slides before scanning
  • Loading the scanner
  • Controlling the quality after scanning...


What if all this could be automated and all the manual work could be significantly reduced or even eliminated?

Well it can! With the 2nd generation of whole slide scanners powered with AI software, that can perform the tasks automatically during the scanning process.

And you don't even need to buy them to gain this benefit for your lab, because you can now buy digitization of your slides as a service from Pramana.

This episode's guest - Prasanth Perugupalli, the Chief Product Officer of Pramanaexplains exactly how it can be done and what was the journey to making it possible.

To learn more how it works and book a demo, visit:
https://pramana.ai/

THIS EPISODE'S RESOURCES:
Pramana's website

WOULD YOU LIKE TO LISTEN TO EXCLUSIVE, NON-CENSORED AND NON-POLISHED CONTENT?
Subscribe here

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

54: Cytomine - a free the tissue image analysis tool for all: pathologists, developers and the lab w/ Gregoire Vincke, Cytomine22 Jan 202300:50:55

Send us Fan Mail

Do you want to do tissue image analysis for FREE? 

Cytomine is your tool. But so are QuPath, Cell Profiler, ImageJ, and several … 

So how is Cytomine different? Cytomine focuses on collaboration (which is crucial in tissue image analysis projects!) and in addition to the free open-source version it also has a paid enterprise version.

In this broadcast my guest Gregoire Vicky, the co-founder of Cytomine will tell you what Cytomine is best for, what are the differences between the paid and free versions, and how it differs from QuPath and any other open-source tissue image analysis software.

THIS EPISODE'S RESPOURCES:
Cytomine (open source) website
Cytomine (commercial) website

OTHER EPISODES YOU MIGH LIKE:
QuPath - Open-Source quantitative pathology not only for pathologists w/ Pete Bankhead, University of Edinburgh

--------------------------------
Join us for the HistoSuite webinar with Andrew Janowczyk
REGISTER HERE TODAY

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

53: Why digital pathology will be mainstream soon w/ Aleksandra Zuraw, Digital Pathology Place29 Dec 202200:08:29

Send us Fan Mail

I started working in the digital pathology space, because it sounded cool.

When I started my digital pathology journey in 2016 as the first full time pathologist supporting the image analysis team, I thought it was the coolest job to get straight out of my veterinary pathology residency!
 
I was regarded as an expert (such a different feeling from what you experience during your training, when you are constantly being reminded how little you know and how much there still is to learn), which increased my confidence and motivated me to learn more. After all I needed to explain pathology to computer scientists.

Working together with the image analysis team and the software development team was exciting and I got to play and test software to view and annotate images.

Yes...
⛌ The images were shipped on hard drives
⛌ It took forever to open an image (over 30 sec...sometimes several minutes)
⛌ The annotation tool would regularly crash

FAST FORWARD 6 years

✔️No more hard drive shipping
✔️The speed of working with digital slides matches my speed at the microscope
✔️I didn't have to reboot my computer a single time today
✔️I work entirely remotely and can attend all recitals and events my kids take part in

VERY SELFISHLY I WOULDN'T WANT TO HAVE IT ANY OTHER WAY

I know I'm part of a minority of privileged pathologists. But it very much reminds me of the time when smartphones came to the market, when I could not afford one yet and they did not have so many functionalities

I was dreaming of having one that could always connect to the Internet, so that I could use Google Maps whenever I wanted (both on vacation and during my commute as a Polish PhD student studying in Germany - knowing the fastest way home on the weekend and avoiding traffic would be priceless!)

NOW EVERYONE HAS A SMARTPHONE

And would you want to have a different phone? The old one?
I know some would, but THEY ARE A MINORITY NOW.

How far are you in your digital pathology journey?
How do you feel about it? Is it already a reality or still a science fiction for you?
Let me know in the comments on LinkedIn


THIS EPISODE'S RESOURCES:
Digital Pathology Starter Kit + Digital Pathology Newsletter
"I started because it was cool..." - LinkedIn post

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

52: What does the FDA say about non-clinical digital pathology for GLP?20 Dec 202200:26:55

Send us Fan Mail

Several scanners have been cleared by the FDA for clinical pathology work, but what about FDAs stand on all the nonclinical pathology work done in a regulatory environment? Specifically the work done in the Good Laboratory Practice (GLP) compliant environment?

  • Can we use the slides without restrictions in lieu of glass slides?
  • What part of the digital pathology system do we need to validate?
  • How do wemaintain and archive the whole slide images used for the pathology portion of the nonclinical toxicologic studies?

Good news!

There is an official FDA draft guidance for the industry that asks all those and a few more questions and answers them at the same time.

In this episode I will go through the guidance for you, so that you don't have to spend time reading this document. But if you feel like doing it anyway, it's available for you to download below in this episode's resources.

And in case you want to skip the whole episode (which I sincerely hope you don't! Believe me, it's pretty fun for and FDA guidance episode:), the answer to most questions is YES.

Talk to you inside the episode!

This episode's resources:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

51: What should we fix in digital pathology with Puneet Pantane, Crosscope30 Nov 202200:26:27

Send us Fan Mail

As much as I love Digital Pathology - things that are not always perfect, and the integrations of systems are not always seamless. We don't need to sugar coat it.

And the sooner we start talking about the things that are not so cool, the sooner we will be able to change them.

In this podcast episode I discuss the things that need to be improved with Puneet Pantane, the Co-Founder and Chief Marketing Officer of Crosscope, where he leverages the power of new technologies such as AI, machine learning, and image processing to improve the research, diagnosis and treatment of cancer.

In this episode we cover:

  • What is Crosscope? Where is this company and what are they actually doing?
  •  What is digital transformation? 
  • Who are Crosscope's customers?
  •  What is not working in digital pathology?
  •  If we had a magic wand that can solve any digital pathology problem, what would NUMBER 1 PROBLEM to solve be?
    • Spoiler alert: Puneet - interoperability of systems
    • Aleks - reinventing the wheel in image analysis
  • What digital pathology problems can be fixed immediately (the low hanging fruits)?
  • How to  standardize digital pathology in small pieces?

If you want to learn more about Crosscope, click here



Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

158: Multimodal Magic AI’s Role in Lung & Prostate Cancer Predictions29 Aug 202500:28:50

Send us Fan Mail

What if AI could predict cancer outcomes better than traditional methods—and at a fraction of the cost? In this episode, I explore how multimodal AI is reshaping lung and prostate cancer predictions and why integration challenges still stand in the way.

Episode Highlights with Timestamps:

  • [00:02:57] Agentic AI in toxicologic pathology – what it is and how it could orchestrate workflows.
  • [00:05:40] Grandium desktop scanners – making histology studies more accessible and efficient.
  • [00:08:03] Clover framework – a cost-effective multimodal model combining vision + language for pathology.
  • [00:13:40] NSCLC study (Beijing Chest Hospital) – AI predicts progression-free and overall survival with high accuracy.
  • [00:17:58] Prostate cancer prognostic model (Cleveland Clinic & US partners) – validating AI-enabled Pathomic PRA test.
  • [00:23:35] Thyroid neoplasm classification – challenges for AI in distinguishing overlapping histopathological features.
  • [00:34:49] Real-world Belgium case study – AI integration into prostate biopsy workflow reduced IHC testing and turnaround time.
  • [00:41:03] Lessons learned – adoption hurdles, system integration, and why change management is essential for successful digital transformation.

Resources from this Episode

  • World Tumor Registry – A global open-access repository for histopathology images: World Tumor Registry
  • Beijing Chest Hospital NSCLC AI Prognostic Study – Prognosis prediction using multimodal models.
  • Cleveland Clinic Pathomic PRA Study – Independent validation of AI-enabled prostate cancer risk assessment.
  • Grandium Scanners – Compact desktop scanners for histology slides: Grandium.ai

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

50: How to approach colon cancer with supervised deep learning image analysis w/ Rish Pai, Mayo Clinic21 Nov 202200:34:16

Send us Fan Mail

This episode is brought to you by Aiforia. Thank you Aiforia :)

Today you will learn how Raish Pai, MD, a busy, practicing pathologist from Mayo Clinic developed a complex supervised deep learning tissue image analysis model to quantify visual diagnostic features of colon cancer and in the process developed a model that can predict clinical outcome.

He used the deep learning-based tissue image analysis platform - Aiforia. 

The quantified features included:

  • Stromal immune cell Infiltrates
  • Immature stroma
  • Tumor-Infiltrating Lymphocytes
  • Mucin
  • Different growth patterns 
  • & many others


THIS EPISODE'S RESOURCES:

THIS EPISODE'S SPECIAL OFFER  "THE BETA COHORT"

Join and be part of the co-creation of the only online course like this in the digital pathology world "PATHOLOGY 101 FOR TISSUE IMAGE ANALYSIS".

Learn more about the AMAZING OFFER that awaits you when you join the BETA COHORT today!

!!! Limited time offer!!! The discount expires on November 27th 2022

Learn more HERE

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

49: Scaling up your digital pathology operations with Mark Zarella, Mayo Clinic08 Nov 202200:29:43

Send us Fan Mail

This episode is brought to you by Hamamatsu. Thank you Hamamatsu :)

So...you are already doing digital pathology in your institution but would like to scale it, take it to the next level? How do you do it, where do you start?

In this episode my guest, Mark Zarella, PhD (previously Johns Hopkins University, currently Mayo Clinic) explains how he did exactly that at Johns Hopkins University. 

He talks about:

  •  What is important when evaluating whole slide scanners and how to choose the best whole slide scanner for you
  • How he organized and managed the whole slide images at Johns Hopkins University
  • How he scaled the operations from ca. 10K slides to ca. 750K slides a year
  • How he ensured interoperability of systems
  • How he approached automated slide quality control 


AND MUCH MUCH MORE!

If you are serious about taking your digital pathology operations to the next level, THIS IS THE EPISODE TO LISTEN TO!

THIS EPISODE'S RESOURCES

Mark's Paper: "High-throughput whole-slide scanning to enable large-scale data repository building"

Blog post: HOW TO CHOOSE A WHOLE SLIDE IMAGING SCANNER FOR DIGITAL PATHOLOGY – THE ULTIMATE GUIDE

Podcast episode: HOW TO CHOOSE A WHOLE SLIDE IMAGING SCANNER FOR DIGITAL PATHOLOGY W/ DOUG STAPLETON, HAMAMATSU 


Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

48: What the heck is DICOM in Pathology? w/ David Clunie, PixelMed Publishing28 Oct 202200:42:54

Send us Fan Mail

As the digital pathology community is embarking on the journey of DICOM implementations questions we haven't asked ourselves arise...

  • Is DICOM and image format or is it a standard? What is the difference?
  • Are all the DICOM images the same or do they differ?
  • how do the differences influence the technology developments and workflows?
  • Is there a single best way of implementing DICOM or do we need to keep iterating?
  • And who can help us on this journey?

Who would be a better guest to talk about it than the DICOM standard editor himself, Dr. David Clunie?

This podcast episode is a recording of a live broadcast we had together recently where he answers all the abovementioned questions and some more!

If you are thinking of using or implementing DICOM for your digital pathology journey, be sure to listen to this episode!

THIS EPISODE'S RESOURCES:

OTHER EPISODES YOU MIGHT LIKE:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

47: Artificial Intelligence in Digital Pathology (a conference talk recording) w/ Aleksandra Zuraw22 Oct 202200:28:52

Send us Fan Mail

Join me for the FREE Independent Digital Pathology Event "Bridging the Gap Between Pathology and Computer Science" 👇
REGISTER HERE


Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

46: Leveraging the power of static telecytology for veterinary diagnostics w/ Kate Baker10 Oct 202200:51:03

Send us Fan Mail

Did you know that pathology diagnostics through a smartphone is a thing?
Really and officially! It is called static telecytology and a lot has already been published on it (see RESOURCES BELOW).

This episode's guest, Dr. Kate Baker, a veterinary clinical pathologist, developed a smartphone app for veterinary telecytology! This digital pathology smartphone app is called pocket pathologist and let's you get access to a veterinary pathologist opinion remotely.

This app was developed for practicing veterinarians who want or need to consult telecytology cases with a board certified pathologist.

This technology can be used for other areas of static telepathology including rapid on site evaluation (ROSE) and Dr. Kate is giving us a sneak peek into the app development and how it was for a veterinarian to work with an app development team (and NO, it does not cost a million dollars  ).

This great little tool for remote pathology diagnostics is a proof that anyone, regardless of their budget can leverage the power of digital pathology to offer or access better care for their patients. You only need a microscope, a smartphone and smartphone adapter (to save time and take better pictures).

So don't hesitate to check it out: https://www.pocketpathologist.com/
THIS EPISODE'S RESOURCES:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

45: What's up in Digital Pathology - a crossover podcast with Beyond the Scope16 Sep 202200:34:54

Send us Fan Mail

 This is a joint podcast episode where the hosts of "Beyond the Scope" - the official Digital Pathology Association podcast and the host of the "Digital Pathology Podcast" meet to talk about what is going on in our discipline. 

Together David Tulman, Giovanni Lujan, and Aleksandra Zuraw cover the current digital pathology topics such as digital pathology guidelines for clinical and non-clinical pathology, digital pathology adoption in clinical pathology settings and pharmaceutical pathology as well as how the pandemic influenced the adoption of digital pathology. 

This episode is different than most of our episodes and it is really fun to listen to so stay till the end! 

THIS EPISODE'S RESOURCES

YouTube Version of THIS episode is here.


Digital Pathology Podcast episode with David Tulman, Instapath: 

AUDIO: https://digitalpathologyplace.com/pod...

VIDEO: https://www.youtube.com/watch?v=wECId...


Podcasts with Chen Sagiv, DeePathology:

Digital pathology Podcast: https://youtu.be/DrEUnkYkN28

Beyond the Scope: https://podcasts.apple.com/no/podcast...


Podcasts with David Clunie, Pixelmed Publishing:

Digital Pathology Podcast: https://digitalpathologyplace.com/pod...

Beyond the Scope: https://podcasts.apple.com/us/podcast...


Pathology Visions 2022 registration page: https://digitalpathologyassociation.o...


Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

44: Weakly supervised AI for pathology w/ Geert Litjens, RadboudUMC28 Jul 202200:53:19

Send us Fan Mail

Have you ever wondered what semi-supervised, weekly, and unsupervised artificial intelligence digital pathology models can do to help pathologists?

Can we finally stop annotating???

This episode's guest Geert Litjens - a member of the computational pathology group at Radboud University Medical Center explains how semi-supervised and weekly supervised artificial intelligence-based image analysis can help pathologists do better, more time-efficient, and data-efficient digital pathology.

The supervised deep learning image analysis methods are used often and are well accepted in the digital pathology scientific community, however, they rely heavily on whole slide image annotations. This is very time-consuming and is subjected to annotator to annotator variability.

There has been a lot of research going on in the computational pathology community on the semi and weakly supervised approaches. It turns out that those approaches are starting to match the results delivered by the supervised approaches.

Are we there yet? Can we stop annotating pathology slides altogether and rely on the slide-level labels?

Listen to the full episode to learn more + share with friends!

This episodes resources:

  1. Aiosyn website
  2. StreamingCNN
  3. Pathology streaming pipeline
  4. Streaming  CNNs for Multi-Megapixel Images (article)
  5. DALL-E-2 network that generates artworks from descriptions in natural language 

Other podcast episodes you'll enjoy:

  1. Bigpicture - the largest whole slide repository for AI model development in pathology. Where do we stand at month 15/72?
  2. 5 Ways to make histopathology image models more robust to domain shift w/ Heather Couture, Pixel Scientia Labs



Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

43: Never miss a piece of digital pathology knowledge ever again! Digital Pathology Place and Pathology News partnership w/ Jonathon Tunstall05 Jul 202200:21:36

Send us Fan Mail

There are a few websites online other than the Digital Pathology Place that talk about different aspects of digital pathology. An important one being Pathology News.

Pathology News is an online place bringing together the digital pathology vendors and purchasers. It is meant to be a single community for everyone working in the digital pathology space. A community working together on advancing the digital pathology science. 

A unique (and my favorite!) feature of the website, NOT AVAILABLE ANYWHERE ELSE ONLINE, is a special page where digital pathology users have access to detailed information about available digital pathology solutions provided by the digital pathology vendors.

It is like a 24/7 online digital pathology conference where the users can visit vendor space any time they need a specific piece of information, and they can visit multiple vendor spaces and compare their solutions. 

All from the comfort of their home without having to call or interact with a single vendor representative before they are ready.

This space is called the Technology Buyers guide.

In addition to this unique vendor-purchaser interactive tool Pathology News has other elements:

- scientific articles
- latest digital pathology news
- list of upcoming digital pathology events
- digital pathology career section with the latest vacancies

and now also...[drum roll please]......

A PODCAST SECTION with the DIGITAL PATHOLOGY PODCAST

We partnered to serve the largest audience possible

Digital Pathology Place and Pathology News are both on a mission to advance digital pathology in the scientific community and we want to serve the largest audience possible. We are doing it in a very complementary way that builds bridges within the multidisciplinary environment of digital pathology.

This is why we partnered to make the Digital Pathology Podcast available to the Pathology News readers straight from the Pathology News website and from their mailbox for those who are subscribed to the monthly newsletter.

Listen to the full episode to meet Jonathon Tunstall, the CEO of Pathology News and learn what else you can find on the website.

This episode's resources:





Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

42: BigPicture - the largest whole slide repository for AI model development in pathology. Where do we stand at month 15/72?17 Jun 202200:37:23

Send us Fan Mail

Deep learning artificial intelligence has entered the field of digital pathology and is here to stay because it consistently outperforms the classical image analysis methods on pathology slides.

The only caveat is that to train good deep learning image analysis models we need a lot of whole slide images.

Where do we get them? Is there a central repository that can be used for this purpose?

Good news, there is one in the making!

There is an ongoing  project to create a very large repository of several million whole slide images accessible for the digital pathology  community. It is called BIGPICTURE and in this podcast you will learn about it from the experts.

This episode's guests, two of the project leaders - Julie Boisclair from Novartis and Jeroen van der Laak from the computational pathology group at  RadboudUMC are explaining the 

Listen to the full episode to learn all about it.

This episode's resources:

Episodes you might also like:


Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

41: Digital Pathology for Dermatologists. How Pathology Watch managed to incorporate digital pathology in dermatology practices across the US w/ Dan Lambert, Pathology Watch25 Apr 202200:23:13

Send us Fan Mail

Digital pathology is supposed to help pathologists provide better patient care and make their lives easier, but what about other doctors, do they even care? Maybe radiologists? Oncologists? Nope…Dermatologists! They do care!

And they are the clients of Pathology Watch – a CLIA lab specializing in dermatopathology, that is currently servicing samples from over 65 dermatology clinics in the USA. 

Pathology Watch provides an end-to-end digital pathology solution for dermatologists. From processing the samples sent by the dermatologists, through the dermatopathology report to the whole slide image of the diagnosed sample, and all this browser-based and integrated with the dermatology clinic’s electronic medical record (EMR) systems. This provides a completely non-disruptive workflow. 

Pathology Watch is providing a true end-to-end solution built around dermatologists. 

The EMR integration saves the dermatologists time (25h/ month!!! Who would not want to have that?!?) and whole slide images build the bridge between and improve the communication on the “patient-dermatologist-pathologist” line. 

Dermatologists can show the images of the cases to the patients, and they can see the highlighted areas used by the pathologist when diagnosing the case.  

Once the digitization and intersystem integration take care of the time savings it’s time to step up the game!  The next step is using artificial intelligence for better dermatopathology diagnostics and to gain even more time savings. Pathology Watch designed its AI pipeline specifically to bypass the known industry problem of generalizability of AI models. 

It is extremely difficult to train generalizable models on samples from different institutions, but if the samples are processed in just one lab in a very controlled environment, using automated equipment and performing rigorous quality control, the pre-analytical variability causing a lack of generalizability is taken care of. 

As in any digital pathology operation, troubleshooting is part of the business. What do you do when your scanner breaks down? How do you store the digital pathology images effectively in a cost-efficient way? And how do you deliver the slides in the browser FAST? 

It took the Pathology Watch team a few years to solve those and other challenges and come up with good mitigation strategies. 

Do you want to know how they did it? Listen to the full episode to learn more from Dan Lambert, the CEO of Pathology Watch

 

This Episodes resources

Pathology Watch website  

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

157: How Academic Pathology Programs Can Prepare for AI | UPMC Podcast22 Aug 202500:38:52

Send us Fan Mail

“AI in Pathology Isn’t Coming — It’s Already Here. Are You Ready?”

From confusion to clarity — that’s what this episode is all about. I sat down with Drs. Liron Pantanowitz, Hooman Rashidi, and Matthew Hanna to dissect one of the most important and comprehensive AI-in-pathology resources ever created: the 7-part Modern Pathology series from UPMC’s Computational Pathology & AI Center of Excellence (CPAiCE). This isn’t just another opinion piece — it's your complete guide to understanding, implementing, and navigating AI in pathology with real-world insights and a global lens.

Together, we discuss:

  • Why pathologists and computer scientists are often lost in translation

  • How AI bias, regulation, and ethics are being addressed — globally

  • What it really takes to operationalize AI in patient care today

If you’ve ever asked, “Where do I even start with AI in pathology?” — this is your answer.


🔍 Highlights & Timestamps
00:00 – The importance of earned trust in AI
01:00 – Education gaps in AI for both pathologists & developers
03:00 – Why CPAiCE was built & the three missions it serves
07:00 – The seven-part series: a blueprint for AI literacy
10:00 – Making AI education accessible without losing technical integrity
13:00 – How this series is being used for global teaching (including by me!)
17:00 – Generative AI in creating figures vs. human-authored content
21:00 – Eye-opening global AI regulations that pathologists MUST know
24:00 – Ethics, bias & strategies to mitigate real clinical risks
30:00 – What’s next: CPAiCE’s mission to reshape pathology education & practice
34:00 – A teaser: the first CPAiCE textbook is on the way!


📚 Resources from This Episode

📰 Read the full series (open access!):
 Modern Pathology 7-Part AI Series: https://www.modernpathology.org/article/S0893-3952(25)00001-8/fulltext

👨‍⚕️ UPMC’s Computational Pathology & AI Center of Excellence (CPAiCE)
 🌍 Creative Commons licensing means YOU can reuse, remix & teach from these resources — just cite the source.



Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

40: A simple microscope camera, whole slide scanner and everything in between. The different tiers of digital pathology w/ Mike Miller, I. Miller Microscopes14 Apr 202200:33:55

Send us Fan Mail

A common misconception about digital pathology is that it is synonymous with whole slide imaging and has a high price point. This is not the case, as one can enter the digital pathology world and benefit from what it has to offer with a simple microscope camera. If we would like a more sophisticated solution, but don't want to get a whole slide scanner or don't have the use case or business case to justify it, no worries, there is enough to choose from!

In this episode, Mike Miller from I.Miller Microscopes is taking us through all the different levels and price points of digital pathology solutions from a simple microscope camera to a whole slide scanner explaining everything in between. 

The digital pathology solutions discussed in this episode include:

  1. Simple microscope camera + imaging software for image capture
    • For teaching and learning
    • For capturing static images
      • presentations
      • publications
      • tumor boards
    • For screen sharing on communication platforms (e.g. zoom, teams, etc.)
  2. Microscope camera with a network port allowing for live streaming
    • For intraoperative evaluation by an on-site or off-site pathologist
      • fine-needle aspirates
      • frozen sections
  3.  Live remote control telepathology system
    1. Live remote control telepathology system with low throughput screening capabilities (aka hybrid system)
      • For use in remote areas without access to pathologists
  4. Whole slide scanners
    • For high throughput digital pathology workflows on formalin-fixed paraffin-embedded (FFPE) material

Listen to the full episode to learn the details and the price points of each solution!

This episode resources:

Episodes you might also like:



Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

39: How image analysis and artificial intelligence support digital pathology-enabled precision medicine today and what to expect in the future w/ Michael Grunkin, Visiopharm15 Mar 202200:20:08

Send us Fan Mail

This episode is brought to you by Visiopharm

With the regulatory approvals of whole slide imaging systems, digital pathology became the modality for routine diagnostics. Digitalization of pathology is aiming at increasing precision and productivity in the pathology lab, but the adoption of this field is slower than expected. 

One of the causes of the slow adoption is that going digital in a pathology lab means a much bigger investment than just the cost of the whole slide scanners for slide digitization. Additional costs include digital storage and infrastructure, slide and workflow management, and connectivity to lab information systems. 

Because the improvements in precision and productivity gained by going digital are modest at best, a higher value is expected from image analysis and artificial intelligence. 

The research and diagnostic applications of image analysis have been explored for decades already and many have found great use in the research-diagnostics continuum. However, a large need for the standardization of tissue diagnostic assays remains unmet. 

Standardization of the staining and of the diagnostic interpretation of tests would tremendously benefit pathology and patient care. So far, the standardization efforts focused on the interpretation part of the puzzle. Several quantification algorithms have been developed, many of which received regulatory clearance. At the same time, the IHC assays on which the algorithms are based often lack standardization, and this is where more effort should be put. 

Currently, only pathology institutions that go fully digital reap the digital pathology benefits. There is not an efficient way to start slowly, rather it seems to be “all or nothing”. Enabling institutions to embark on the digital pathology journey in an incremental fashion would change the digital pathology landscape and significantly increase the adoption of this technology. 

The more value on different fronts digital pathology can provide to institutions and patients, the more the adoption will increase. And we have not yet explored all the ways in which value can be provided. 

Listen to the full episode to learn about it in more detail and visit Visiopharm’s website, to learn how they are contributing to the digital transformation in pathology. 

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

38: From digital microscopy to digital pathology through image analysis. How far have we come in 20 years? w/ Michael Grunkin, Visiopharm08 Mar 202200:18:49

Send us Fan Mail

Visiopharm is a company offering image analysis software used on pathology images. The software has been on the market for over 20 years and has evolved through the transition of digital microscopy to digital pathology. Digital microscopy provided static tissue images captured through the microscope camera and only branched out into digital pathology with the wider availability and adoption of whole slide scanners. Image analysis spans digital microscopy and digital pathology, and image analysis methods had to evolve in parallel with the imaging technologies to address the hypercomplex pathology problems. 

The complexity of digital pathology problems and research questions increases with every additional stain and scientific discovery. Visiopharm’s team challenged themselves by providing an image analysis solution capable of addressing this hypercomplexity and enabling researchers to advance scientifically with their tool. 

Artificial Intelligence (AI) capabilities applied to computer vision problems took tissue image analysis to a whole new level and incorporating AI into the Visiopharm software tremendously increased the accessibility of this method. 

In addition to the two well-known technologies that enabled digital pathology breakthroughs (whole slide imaging and AI), two other important advancements happened during the last two decades

·       emphasis on interoperability between different digital pathology systems 

·       advances in the field of data visualization. 

Together these four components are driving the progress of digital pathology both on the diagnostic and research front. 

During the last 20 years Visiopharm grew significantly, both organically and through funding and they continue creating value and powerful image analysis tools for the tissue image analysis community. 

Listen to the full episode with Visiopharm’s CEO Michael Grunkin to learn more about this 20-year perspective on what happened in the field of digital microscopy and digital pathology. 

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

37: How tissue clearing - based 3D immunofluorescence allows for seeing more biology in the tissue w/ Sharla White, ClearLight Biotechnologies07 Feb 202201:02:17

Send us Fan Mail

Even though tissues are tridimensional structures, most tissue research is done on two-dimensional tissue slides. This leaves a tremendous amount of biological information on the table. This episodes' guest - Sharla White, Ph.D., the vice president of research and development at ClearLight Biotechnologies explains how tissue clearing and 3D immunofluorescence can take your tissue research to a whole new level. 

With the rise of immuno-oncology, the importance of immune cell interactions with the tumor cells is now routinely interrogated with immunofluorescent markers the spatial relationships of different immune cell populations are investigated. But how can we investigate something happening in a 3D space on a flat, two-dimensional tissue section? The truth is - in a very restricted manner. This is where tissue clearing and 3D immunofluorescence come into play. 

The tissue clearing technology -CLARITY, developed by ClearLight Biosciences allows for maintaining the integrity of tissue and visualizing cells in their original place and shape at the same time by using 3D immunofluorescence.
 
In order to image deeper (beyond 100 micrometers), the light-scattering lipids of the tissue need to be removed and the refractive indexes of collagen, bone, and other tissue components need to be aligned. This is done after fixing the tissue and embedding it in a hydrogel. It ensures that the tissue structure is maintained before the detergent is applied to wash out the light-scattering lipids. 

Once tissue clearing is done, antibodies with properties and in amounts compatible with the process are used for 3D immunofluorescence. 
 
This powerful technology does not come without challenges such as:

  • the necessity of tissue bleaching for melanoma samples,
  • selection of appropriate immunofluorescence markers,
  • size of the 3D image files generated for visualization (often as big as 500 gigabytes reaching terabytes of data!)
  • meaningful interpretation of the results 

 Listen to the full episode to learn how Dr. White's team is approaching all the challenges, leveraging CLARITY potential and how this technology changes the way we do tissue research. 

This episode's resources:

Episodes you might also like:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

36: DICOM standard for pathology annotations. Why do we need it? w/ David Clunie, PixelMed Publishing25 Jan 202200:36:27

Send us Fan Mail

The Digital Imaging and Communications in Medicine (DICOM) standard for digital medical imaging has been around since the 1980s. First adopted in radiology it is slowly spreading in pathology as well. Now with image analysis being an integral part of medical imaging workflows, the question arose if the annotations made on the images should have a standard format as well? And can the same DICOM format be used?

With deep learning taking over the medical image analysis field, the answer is a definitive yes! Deep learning requires a large number of annotations to train robust image analysis models. Making them requires a lot of time and work and having them in a format that can grant interoperability between different digital pathology and image analysis systems is becoming a requirement. 

In this episode my guest Dr. David Clunie, the DICOM standard author is explaining what annotations are, why do we need to standardize the format in which they are created, and why the interoperability of digital pathology systems is actually the responsibility of the users of the system and how to be proactive with system vendors to grant it. 

If you are working in the medical image analysis field or are looking into different image analysis systems that require annotations, this episode is for you!

And if you want to learn more about the DICOM standard for images, listen to:

Or visit the following resources:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

35: Digital veterinary cytology and social media teaching w/ Kate Baker, Veterinary Cytology Schoolhouse11 Jan 202200:41:42

Send us Fan Mail

In the world of anatomic digital pathology, the mention of digital cytology usually causes thoughts of all the challenges associated with it. We are often not aware that digital pathology and image analysis applications started with digital hematology and cytology (e.g. image analysis-based pap smear evaluation) and that in veterinary medicine digital cytology is a booming discipline. 

Today’s episode’s guest, Dr. Kate Baker, is a board-certified veterinary clinical pathologist who has embraced the digital cytology journey even before she was doing diagnostic work on whole slide images. 

Her digital pathology journey started with a Facebook group – Veterinary Cytology Coffee House where she started teaching veterinary cytology with static images. The group kept growing and reached sixty-two thousand members in January 2022. Group members kept asking for more digital cytology resources, so she created two RACE-approved courses for veterinary professionals and a monthly membership site – The Cytology Clubhouse. Currently, she does digital cytology on whole slide images in collaboration with a veterinary laboratory – Scopio. 

Now confident with digital cytology images she remembers that there was a transition period when she needed her glass slides alongside the digital image to feel confident that she is not missing anything. As she experienced how the glass slides and the digital images consistently carry the same diagnostic information, she needed to consult the glass less and less until it was not necessary anymore. 

The glass vs digital slide comparison is usually part of the digital pathology system validation and giving pathologists some time to adjust to the new modality with access to both digital images and glass slides during the adjustment period helps them gain confidence and be sure that they are still doing the best job possible. 

Listen to the full episode to learn about Dr. Kate Baker’s digital cytology journey and explore her digital cytology educational resources:

And check her brilliant educational content on Instagram @clinpathkate

And to gain more insights into the world of digital cytology listen to the podcast episodes below:

Other resources:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

34: 5 ways to make histopathology image models more robust to domain shift w/ Heather Couture, Pixel Scientia Labs29 Dec 202100:16:32

Send us Fan Mail

In this episode, we talk with Heather Couture about how to make deep learning models for tissue image analysis more robust to domain shift.

Supervised deep learning has made a strong mark in the histopathology image analysis space, however, this is a data-centric approach. We train the image analysis solution on whole slide images and want them to perform on other whole slide images - images we did not train on.

The assumption is that the new images will be similar to the ones we train the image analysis solution on, but how similar do they need to be? And what is domain and domain shift?

Domain: a group of similar whole slide images (WSI). E.g., WSIs coming from the same scanner or coming from the same lab. We train our deep learning model on these WSIs, so we call it our source domain. We later want to use this model and target a different group of images, e.g. images from a different scanner or a different lab - our target domain.

When applying a model trained on a source domain to a target domain we shift the domain and the domain shift can have consequences for the model performance. Because of the differences in the images the model usually performs worse...

How can we prevent it or minimize the damage?

Listen to Heather explain the following 5 ways to handle the domain shift:

  1. Standardize the appearance of your images with stain normalization techniques
  2. Color augmentation during training to take advantage of variations in staining
  3. Domain adversarial training to learn domain-invariant features
  4. Adapt the model at test time to handle the new image distribution
  5. Finetune the model on the target domain


Click here to read Heather's full article on making histopathology image analysis models more robust to domain shift.

Visit Pixel Scientia Labs here.

And listen to our previous episode titled "Why machine learning expertise is needed for digital pathology projects" here to learn more about the subjects and learn how Heather and her company can help.



Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

33: Smart in Media - the virtual microscopy hub w/ Martin Weihrauch MD, Smart in Media14 Dec 202100:38:46

Send us Fan Mail

Advanced computer science expertise with the ability to code and a medical degree with over 20 years of clinical experience is a rare combination. This episode’s guest, Martin Weihrauch MD, the co-founder of Smart in Media incorporates this rare combination. 

His digital pathology platform originated when he was asked by a pharmaceutical company to provide some interactive entertainment for the participants of a medical congress, something beyond just coffee, and the only thing really attracting participants to a company exhibition booth. He decided to host diagnostic quizzes with virtual microscopy. Since then, supported by the close collaboration of a pathologist, Dr. Alberto Peréz Bouza, the platform evolved from the initial virtual microscopy application, through a full pathology educational platform to a fully capable digital pathology diagnostic platform with an open API and the capability for AI algorithm integration. 

Smart in Media is a digital pathology platform designed by physicians for physicians. The software is optimized for pathology workflow and IT infrastructure. Through the open API, it can communicate with any LIS or LIMS system, has the capability of image analysis algorithm integration, and is extremely user-friendly. Smart in Media users can give real-time feedback to the platform developers about any bugs or difficulties in a user WhatsApp group.  

Smart in Media is already a leading digital pathology solution provider in Europe with its presence established in Germany, Austria, Switzerland, Italy, the UK, and the Czech Republic, and is the official digital pathology provider of the European Society of Pathology. With its presence expanding to the US the company is striving to bring digital pathology to every pathologist and to improve and speed up their workflow.

To learn more about Smart in Media visit their website here

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

32: Why machine learning expertise is needed for digital pathology projects w/ Heather Couture, Pixel Scientia Labs28 Nov 202100:35:35

Send us Fan Mail

What do cancer and climate change have in common? Both are very serious problems and in both, machine learning (ML) and artificial intelligence (AI) can be used to support potential solutions. Even though these AI applications may seem very different the ML methods used to support work on both problems are very similar. 

Today’s episode’s guest, Heather Couture from Pixel Scientia Labs does exactly that – fights cancer and climate change with AI. She is a computer scientist specializing in computer vision machine learning and deep learning. She started her company during her Ph.D. when she was doing contract work and expanded her work after receiving her degree. She assists companies with accelerating their machine learning projects by distilling and adapting cutting-edge research and applying her over 16 years of experience in the field for analyzing images. 

Not only does she stay on top of the current research herself, but she also posts about it on LinkedIn several times a week, extracting the most important and actionable information out of the most recent publications on machine learning applications in pathology. 

Her consulting company gives her the opportunity to optimize her work for impact and get engaged with companies and projects that can really make a difference. 

Teamwork is important in every area of life, but in the medical domain and especially in pathology it acquires a whole new dimension. No longer is it possible for a single observer to analyze the data in conjunction with the pathology images. The use of computer vision algorithms is often a must and to come up with medically and diagnostically relevant solutions the domain experts from pathology and computer vision need to work together. 

In clinical settings and in medically focused companies machine learning expertise is necessary to leverage the power of artificial intelligence and apply it to their problems and challenges. 

Heather supports her clients with such tasks as nuclear detection and classification, mitosis detection, segmentation of different tissue types in pathology images, stain normalization, and other techniques to enable a deep learning model to generalize images from a different scanner. All these things come into a lot of different projects, even if the project endpoints vary. Another important aspect of every deep learning project is data collection and data labeling. 

Are you working with deep learning for pathology image analysis? If so, visit https://pixelscientia.com/ to learn more about the machine learning expertise you can leverage for your projects.

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

31: AI-powered digital diagnostic tools for medical, veterinary and environmental laboratories. How Techcyte uses AI for digital cytology and smears w/ Ben Cahoon, Techcyte03 Nov 202100:41:38

Send us Fan Mail

AI-powered algorithms for digital pathology and tissue image analysis are not new, also digital cytology and hematology already have their share of AI algorithms helping pathologists with faster and more accurate diagnoses. But what about parasitology or microbiology? Techcyte has a tool for that as well.
 
Today my podcast guest is Ben Cahoon, the CEO of Techcyte, a software start-up that provides AI-powered diagnostic tools for everything smearable: fecal, blood, cytology, and microbiology smears. 
 
Imaging specimen smears has all the challenges of digital cytology such as correct focusing, and then some more. This is why Techcyte's pipeline starts with optimizing the sample preparation for imaging through close collaboration with sample prep vendors, who then work with scanner manufacturers to ensure optimal image quality.  Only then can data for model development be annotated. 
 
Techcyte deep learning models specialize in the detection and classification of different structures such as blood cells, parasite eggs, and bacteria. The annotation process consists of placing bounding boxes around structures of interest to train the initial model followed by accepting or rejecting structures suggested by the preliminary model. This helps the model improve future predictions and in computer vision terminology is known as reinforcement learning. The images of the diagnostic samples are sent for analysis via a web browser and the results can be accessed there as well. 
 
Techcyte's mission is to digitize and automate diagnostics through AI in order to minimize the cost of healthcare and the number of diagnostic mistakes. In the process of following their mission, Techcyte perfected the technique of fecal float imaging, which allowed them to penetrate and serve the production and companion animal market. In turn, this served as proof of concept and provides a revenue stream that enables the funding of further developments. 
 
 Their vision for medical diagnostics consists of five phases: 

  •  phase 1 is to automate an existing test such as a peripheral blood smear or fecal smear evaluation, to increase efficiency and recall; 
  • phase 2 focuses on eliminating/ reducing the need for evaluation of the negative samples, which e.g.,  can constitute over 95% of fecal smears; 
  •  phase 3 would function as a diagnostic support tool presenting a diagnosis to the expert for confirmation;
  • phase 4 would enable the replacement of expensive tests such as flow cytometry with inexpensive image analysis tests 
  • ·       and in phase 5 results of expensive and slow tests, for which microscopy is not the gold standard, such as PCR and sequencing could be derived from the image properties. This would eliminate costs and tremendously decrease the diagnostic turn-around time. 

Reaching phase one will improve patient care significantly. Reaching phase five will revolutionize it.
 
 This episode’s resources:



Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

156: Digital Pathology and AI in Cancer Grading, T-Cell Imaging & Biomarkers21 Aug 202500:34:35

Send us Fan Mail

Can AI Grade Cancer Better Than Us? The Truth About T-Cell Imaging, Biomarkers & Digital Pathology Disruption


You think Saturday mornings are for coffee? Try diving into bone marrow morphology, organ donor kidney biopsies, and AI-driven metastasis detection at sunrise. That’s how I do it—and you’re invited to join.

Welcome to another data-packed episode of DigiPath Digest, where we explore the latest frontier in digital pathology and AI. This time, I reviewed some of the most exciting recent abstracts spanning cancer grading, T-cell quantification, and AI agents in oncology decision-making.

These studies aren’t just fascinating—they’re redefining what’s possible in diagnostics, especially in under-resourced areas where digital pathology can create game-changing access and efficiency.

🔬 Highlights with Timestamps

[00:04:00] Detecting Metastases with Vision Transformers
A team from Leeds Teaching Hospital developed a model for identifying lymph node and omental metastases in ovarian and peritoneal cancers with 99.8% AUROC and 100% balanced accuracy—this isn’t hype; it’s real AI pre-screening that could reduce diagnostic strain on pathologists.

[00:08:00] DeepHeme: Bone Marrow Smears Meet AI
UCSF and Memorial Sloan Kettering collaborated on DeepHeme, an ensemble deep learning model that classifies bone marrow aspirate cells with expert-level accuracy. With over 30K training images and strong external validation, it outperforms humans in both speed and detail.

[00:16:00] Multimodal AI for Head & Neck Cancer
This review showcases how integrating radiology, histopathology, and genomics with AI enhances personalized treatment and prognosis. Spoiler alert: Multimodal > unimodal.

[00:24:00] Real-Time Kidney Biopsy Evaluation via AI
Shoutout to our Digital Pathology Place sponsor, Techcyte, for their AI-powered tool improving accuracy and halving the time it takes to evaluate frozen kidney biopsies. This is the kind of innovation we need in organ transplantation.

[00:32:00] GPT-4 as an Oncology Agent?
Heidelberg researchers created an autonomous AI agent using GPT-4 plus vision models and OncoKB to handle oncology case decisions with 91% accuracy. This isn’t ChatGPT guessing—it’s a hybrid system citing guidelines and performing complex reasoning.

🧠 Resources From This Episode

  • 📰 Multiple Instance Learning for Metastases Detection in Ovarian Cancer – Cancers journal
  • 🧬 DeepHeme: Generalizable Bone Marrow Cell Classifier – Science Translational Medicine
  • 📚 AI in Head and Neck Cancer: A Multimodal Review – Cancers journal
  • 🧪 AI-Assisted Review of Donor Kidney Pathology – Techcyte & Digital Pathology Place demo
  • 🤖 Autonomous AI Agent for Oncology Decisions – Heidelberg Group
  • 🎙️ Podcast on GPT-4 agents with Dr. Nina Kolker
  • 🧵 Earrings mentioned in the livestream? Find them in the DPP Store


I’d love to hear your feedback, your projects, and what digital pathology means to you. You can always reach out through comments, LinkedIn, or email.

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

30: Microscope phone adapter that can bring digital pathology to everyone w/ Cade Wilson, Skoped Micro18 Oct 202100:36:19

Send us Fan Mail

This episode contains affiliate links. Learn what that means here

Have you ever tried to take a picture through your microscope with your smartphone? If you have, you know how much hassle it is to consistently take good, sharp microscope pictures. So maybe, annoyed with how cumbersome it is and how much time it takes, you have already looked for a microscope phone adapter? I know I have, and the one I got from Amazon quickly ended up in my drawer and never saw the light of day again. The pictures were no better than with the handheld phone and it took forever to mount that thing.

Disappointed with my Amazon experience I gave up on finding a microscope phone adapter, thinking a proper microscope camera was the only way to go. Then I saw a comment by Skoped Micro on one of my Instagram posts. This microscope phone adapter looked different, and it even featured a dedicated app to take pictures.

This is how I met Cade Wilson, a practicing veterinary surgeon from Oklahoma, who developed this unique microscope phone adapter together with the outdoor company Phone Scope, originally modifying it from a phone adapter designed for a hunting spotting scope. 

Fast forward 5 years and this microscope phone adapter kit consisting of a Custom Phone Case and Microscope Eyepiece Adapter is ready for purchase and anyone who wishes to do digital pathology can do it through their phone with ease, without having to disrupt their workflow or having to spend thousands of dollars for a slide scanner. 

Listen to the full episode to learn more about how Skoped Micro brings digital pathology to everyone, including veterinary practices, universities, and all other microscope users. 

So if you need to start doing digital pathology, telepathology, teleteaching, or just want to take beautiful pictures through your microscope for your Instagram or other social media feed, without breaking the bank, look no more!

Digital Pathology Place is a proud affiliate of Skoped Micro and you can purchase the digital pathology kit for your phone (consisting of Custom Phone Case and Microscope Eyepiece Adapter) through our affiliate link: 

Buy the digital pathology kit for your phone here

Thank you!

 

This episode’s resources:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

29: An easy AI tool for pathology image analysis. How Aiforia empowers pathologists and scientists with supervised deep learning w/ Tuomas Ropponen, Aiforia05 Oct 202100:39:52

Send us Fan Mail

How many times did you get annoyed when using non-intuitive digital pathology software? Have you already given up on digital pathology and image analysis or are you still looking for something powerful but easy to use? 

Today’s guest, Tuomas Ropponen, the chief technology officer at Aiforia, is talking about the creation of a pathology image analysis platform whose core principles are “easy to use” and “accessible” - Aiforia

Aiforia stands for artificial intelligence (AI) for image analysis (IA) and it combines cloud-based access with supervised deep learning for pathology image analysis. This is where pathologists and computer scientists collaborate closely to create tools that empower pathologists and give them access to the state-of-the-art image analysis methods.  

Aiforia began as a teaching and telepathology platform for sharing whole slide images. But as soon as deep learning passed the reality check and started outperforming classical computer vision methods, Aiforia’s team knew that they had to incorporate this method into their platform. It would change the way pathology was done.  

The decision about using supervised deep learning as the method of choice was based on the desire to supervise the teaching of the AI in a similar way as we supervise the teaching of students. Only by supervising and curating the inputs can we be sure that we get quality output. Teaching AI in a supervised manner happens through annotations, and annotations are a natural way that pathologists communicate. 

Pathologists have always marked areas of interest on the glass and later digital slides. It has always been the way to show others what is important on the tissue. Adapting annotations for supervised deep learning as a way of showing AI what is important was a natural progression of how pathologists work.  

Another core value at Aiforia is the close collaboration between pathologists and computer scientists. Those two groups currently work very closely together but fostering this open relationship and honest communication required a few iterations and a deeper understanding of each other’s ways of working.  

For computer scientists, it was surprising that the pathology scoring and grading system often could not be directly reproduced by image analysis algorithms. For pathologists it was surprising that the algorithm results did not match their visual estimates from glass slides. The two groups had to sit together and start dissecting the pathology problems into smaller components as well as translating them into quantifiable tasks.  

Suddenly it became clear to everyone that the Ki67 quantification in the tumor consists of first detecting the tumor epithelium and later identifying and counting the Ki67 positive and Ki67 negative cells within the epithelium. 

When pathologists’ fatty liver scores of 70 or 80% were nowhere close to the absolute pixel area of fatty vacuoles in the liver tissue of max 20% it became evident that pathologists were subconsciously normalizing their scores and spreading them on a 0-100% scale. Coming together and analyzing the discrepancies as a team revealed that pathologists’ scores or estimates are often an imprecise and inconsistent benchmark to measure against. Everyone went back to the drawing board (or drawing tablet) and provided a more objective ground truth – annotations.  

This close collaboration of pathologists and computer scientists as well as involvement of user experience designers helps drive innovation at Aiforia while maintaining accessibility and ease of use. 

To learn more about AI for image analysis visit Aiforia’s website or even better, let the team show you what this whole thing is about - book a demo.  

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

28: QuPath - open source quantitative pathology not only for pathologists w/ Pete Bankhead, University of Edinburgh24 Sep 202100:56:05

Send us Fan Mail

With more than 170K total downloads and over 700 citations in scientific literature, QuPath is arguably the most popular open-source software for quantitative pathology and bioimage analysis. Today’s podcast guest, Pete Bankhead, the author of QuPath, is taking us behind the scenes of his software creation.

Even though Pete is now a senior lecturer in digital pathology at the University of Edinburgh, his digital pathology career actually started by accident. With an undergraduate degree in theology and a master’s in computer science, he started working on bioimage analysis during his PhD in biomedical sciences. He began using open-source software for image analysis, which was an excellent and very efficient way to work with static bioimages. So, during his post doc work he tried to apply open-source software to pathology whole slide images (WSI), unfortunately without success…The pathology WSI were just too big - it was not even possible to efficiently open them with any openly available software. 

So he started his own software development – first by creating his own plugins for already available open-source programs, such as ImageJ. It sort of worked but not really… There was no way to coordinate the development and bring all his plugins together, so he started developing his own pathology WSI viewer. 

That worked, and in the process, he realized that building software tools himself gave him a lot more freedom to solve problems in a way tailored to the specific challenges of digital pathology. He dove deeper into the project and created what we now know as QuPath – the open-source software for digital pathology image analysis

During its development, the software evolved from a Ki67 quantification tool to a machine learning-powered, versatile image analysis software.

Listen to the full episode to learn 

  • Who and what influenced Pete, 
  • why is QuPath open-source,
  • why Pete fought for QuPath to stay open-source, 
  • and what are the most important features of QuPath. 

This episode’s resources:

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!

© My Podcast Data