Digital Pathology Podcast

Send us Fan Mail
How close is pathology AI to making decisions that matter in real workflows, real trials, and real patient care?
In this episode of DigiPath Digest, I review five recent papers that approach that question from very different angles. We look at multimodal survival prediction in cervical cancer, pathology-driven response assessment in neoadjuvant immunotherapy for head and neck squamous cell carcinoma, AI-assisted Ki-67 scoring in pulmonary neuroendocrine neoplasms, automation and AI in hematologic diagnostics, and AI-based qFibrosis readouts from the Phase 3 MAESTRO-NASH trial.
What I liked about this set of papers is that they do not all tell the same story. Some show clear progress. Some show where AI already works well as an adjunct. Others make it very clear that validation, governance, reproducibility, and workflow design still matter just as much as model performance.
Key topics and timestamps
00:00 Introduction, Easter edition, and community updates 
00:51 USCAP recap, signed book giveaway, and free Digital Pathology 101 PDF 
02:04 Partnerships, lab automation preview, and what’s coming in this episode 
03:25 Multimodal deep learning for cervical cancer survival prediction 
13:00 Why pathology may be a better response endpoint than radiology in neoadjuvant HNSCC immunotherapy 
23:09 Ki-67 scoring in pulmonary neuroendocrine neoplasms: pathologists vs two AI systems 
33:46 AI, digital morphology, and automation in hematologic diagnostics 
43:29 qFibrosis, digital biomarkers, and the MAESTRO-NASH Phase 3 trial 
51:57 Closing thoughts, community updates, and Easter promotion 
Resources
 Deep Learning Can Predict the Overall Survival of Cervical Cancer Based on Histopathological Image, Gene Mutation and Clinical Information
 https://pubmed.ncbi.nlm.nih.gov/41902378/

 Modern Pathology-Driven Strategies in Neoadjuvant Immunotherapy for Head and Neck Squamous Cell Carcinoma: From Residual Tumor Quantification to Spatial and AI-Based Biomarkers
 https://pubmed.ncbi.nlm.nih.gov/41899621/

 Ki-67 Proliferation Index in Pulmonary Neuroendocrine Neoplasms: Interobserver Agreement Among Pathologists and Comparison of Two Artificial Intelligence-Based Image Analysis Systems
 https://pubmed.ncbi.nlm.nih.gov/41898274/

 Molecular Pathology, Artificial Intelligence, and New Technologies in Hematologic Diagnostics: Translational Opportunities and Practical Considerations
 https://pubmed.ncbi.nlm.nih.gov/41897649/

 Quantitative regression of qFibrosis with resmetirom: Exploratory histologic endpoints from the MAESTRO-NASH phase III clinical trial
 https://pubmed.ncbi.nlm.nih.gov/41895606/
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!

Send us Fan Mail
Why do digital pathology projects get harder once the real workflow starts?
In this USCAP 2026 conversation, I talk with Robert Moody from Hamamatsu and Jake Eden from Agilent about what the conference theme, MAKING CONNECTIONS, looks like in actual digital pathology implementation. This was not just a conversation about products. It was a conversation about workflow. We talked about why consistent staining matters before scanning, why strong partnerships need a shared vision, and why labs increasingly want a simpler point of contact as they move into digital pathology.  
One point I really liked is that the value of a partnership is no longer just in combining components. It is in reducing complexity for the lab. Robert and Jake explain how vendors increasingly act as guides during digital transformation, helping customers navigate technical decisions, implementation steps, and the many stakeholders involved beyond pathology itself. That includes IT, information security, legal, finance, and lab operations. 
Another key theme is that no two deployments look the same. Some labs are centralized. Some are hub-and-spoke. Some outsource parts of the workflow. That is why future-proofing came up so strongly in this episode. Jake talks about keeping options open with open, agnostic workflows, and Robert makes the practical point that the most expensive thing you can do is the same implementation twice. 
Key highlights
[00:22] Why this episode moves from high-level partnerships to what they look like in the lab 
[02:33] Why staining consistency matters for successful digital workflows 
[03:14] Shared vision, relationships, and why partnerships start with people 
[05:29] The idea of a single point of contact to reduce complexity for labs 
[08:32] Why vendors have become digital pathology guides 
[10:03] Why every deployment is unique 
[14:22] Future-proofing and choosing open, agnostic workflows 
[15:46] Why doing the same implementation twice is the expensive mistake to avoid 
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!

Send us Fan Mail
 Why does digital pathology adoption move faster in some places than others? 
In this USCAP 2026 conversation, I sat down with Robert Moody and Fumiya Fuji from Hamamatsu to talk about what the conference theme, MAKING CONNECTIONS, really looks like in practice. This was not just a scanner conversation. It was a workflow conversation. 
We talked about why digital pathology has shifted from a scanner-first mindset to a solution-first one, and why that matters for labs trying to build workflows that actually work. Robert explained why partnerships now need to happen earlier, with software, hardware, and execution teams involved from the start. Fumiya added a global perspective, comparing adoption drivers across the US, Japan, Europe, and Canada, and explaining why local support systems, ROI, geography, and government backing can all change the pace of adoption.  
One point I especially liked was this: digital pathology is not one product. It is an ecosystem. And if one component fails, the whole workflow can break down. That is why connected thinking matters so much right now. This episode is really about how companies, labs, and partners are learning to work more like a team.  
Key highlights 
[00:00] Why MAKING CONNECTIONS fits digital pathology so well 
[01:37] Why partnerships matter beyond the scanner 
[04:29] The shift from scanner-first to solution-first
[04:58] How adoption differs across the US, Japan, Europe, and Canada 
[09:01] Why global collaboration inside Hamamatsu matters 
[10:50] How partnerships move from paper to real-world execution 
[12:55] Why does the USCAP show floor show a more connected industry 
[14:37] Why the next phase of digital pathology depends on interoperability and connected workflows
 
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!

Send us Fan Mail
What makes digital pathology feel so hard to enter, even for smart people already working around it?
In this special USCAP conversation, Stephanie Fullerton from Hamamatsu turns the tables and interviews me about Digital Pathology 101 — the book I wrote for people who are starting or continuing their digital pathology journey.
We talk about why the book is not meant to be an exhaustive manual, but a practical framework. A way to help people see the full picture, ask better questions, and understand how the pieces of digital pathology fit together. 
One of the biggest themes in this conversation is that digital pathology is a team effort. It is not just pathology. It involves scanners, software, image analysis, engineers, vendors, and people who often do not speak the same professional language. 
That matters because sometimes getting the right answer starts with asking the right question.  
We also talk about the challenge of translating expert knowledge into beginner-friendly language, why vendors often become guides as labs go through digital transformation, and why I think a shared vocabulary can make implementations smoother and more collaborative. Toward the end, we shift into the fun side of USCAP: signed book giveaways, stickers, pins, and ways to make connections at the conference.  
Topics discussed
[00:03] Why Stephanie interviewed me this time, and the idea behind Digital Pathology 101
[01:07] What the book is actually for: a framework, not a one-size-fits-all manual 
[04:07] The hardest part of writing for beginners without talking down to them 
[06:26] Why digital pathology implementation feels like a mountain, and how to lower the barrier 
[08:15] Why a shared vocabulary matters in digital pathology teams 
[09:44] Translating between pathologists, engineers, vendors, and marketing 
[11:26] Why vendors and partners often become guides during digital transformation 
[12:33] Who the book is for, including students and early-career professionals 
[13:33] Book signing, giveaways, and where to find me at USCAP 
[19:05] Stickers, pins, and why small things can help start real conversations at conferences  
Resources mentioned
Digital Pathology 101
Hamamatsu Booth 312 at #USCAP2026 in San Antonio, Texas 
 My histology and microscopy videos on YouTube 
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!

Send us Fan Mail
What happens when AI looks strong in a paper, but the workflow still isn’t ready?
In DigiPath Digest #40, I reviewed five recent papers across kidney pathology, oral and maxillofacial pathology, glioma biomarker prediction, digital twins in neuro-oncology, and a major European colorectal cancer cohort. A common theme kept coming back: good performance is not the same thing as real-world readiness.
We started with kidney biopsies and the challenge of assessing interstitial fibrosis and tubular atrophy, where AI shows promise but still does not fully agree with humans. That led into a bigger point I keep seeing in digital pathology: our “ground truth” is often based on human interpretation, and human interpretation has variability too.
From there, I looked at AI in oral and maxillofacial pathology, where the field is still early and one major bottleneck is the lack of strong public datasets. Then I discussed a systematic review on adult-type gliomas showing that multimodal models performed better than unimodal ones, which makes sense when you think about how pathologists actually work: we do not diagnose from one input alone.
I also covered a systematic review on digital twins in neuro-oncology. The idea is exciting, but the paper makes it clear that reproducibility, public code, multimodal integration, and external validation are still limiting factors.
And finally, I talked about a paper I really liked: a large European colorectal cancer cohort built across 26 biobanks in 12 countries. That kind of harmonized, quality-checked dataset matters. A lot. Because better AI starts with better data.
In this episode, I discuss:
 Why AI vs human comparisons are harder than they first look 
 the “gold standard paradox” in pathology 
 Why multimodal AI keeps outperforming unimodal models 
 What is holding digital twins back from broader use 
 Why curated multicenter datasets are so important for digital pathology research 
Resources mentioned:
 Digital Pathology 101 pdf copy
 Pathology AI Makeover Course 
 DigiPath Digest AI-powered paper summaries 
Papers discussed:   
https://pubmed.ncbi.nlm.nih.gov/41830415/
https://pubmed.ncbi.nlm.nih.gov/41826004/
https://pubmed.ncbi.nlm.nih.gov/41824546/
https://pubmed.ncbi.nlm.nih.gov/41823607/
https://pubmed.ncbi.nlm.nih.gov/41820399/

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