Avsnitt
-
Send us Fan Mail
Are pathology foundation models actually ready for labs, or are they still stronger on paper than in practice?
In this episode of DigiPath Digest #49, I unpack a timely review on pathology foundation models and ask the question that matters most to me: not just what these models can do, but what has to be true before they are genuinely useful in real pathology workflows.
I walk through how pathology AI moved from narrow, task-specific models into the era of transformer-based foundation models. That shift matters because pathology is no longer only about looking at H&E in isolation. Today, pathologists are expected to integrate morphology, immunohistochemistry, molecular assays, genomics, and clinical context. That growing complexity is one reason foundation models are getting so much attention.
In this discussion, I explain how transformers entered pathology, why image patches are treated like tokens, and how shared embeddings can support classification, regression, segmentation, and multimodal retrieval. I also go through the major pathology foundation models mentioned in the paper, including Virchow/Virchow2, Mayo Clinic Atlas, UNI, CONCH, H-Optimus, GigaPath, and TITAN, and why scale alone is not the full story.
A big part of this episode is about the gap between benchmark performance and clinical readiness. I talk about the persistent limitations in training data diversity, the overuse of TCGA, and why public benchmarks can still miss what real pathology practice looks like. I also cover where foundation models still struggle, especially in cytopathology, hematopathology, and underrepresented disease areas, along with the real-world problems of artifacts, domain shift, concept drift, infrastructure burden, regulatory complexity, and workflow disruption.
For me, one of the most important themes is this: AI in pathology should augment, not replace, pathologists. The future is not about handing diagnosis to a model. It is about building tools that support pathologists better, fit real workflows, and can be validated in ways that deserve trust.
I also spend time on what comes next: explainable AI, counterfactual explanations, conversational interfaces, retrieval-augmented systems, multimodal fusion, and the need for deployment-centric validation rather than paper-only excitement.
If you are trying to understand where pathology foundation models really stand today, this episode will help you separate the promise from the practical barriers.
Episode Highlights
00:01 – Why I chose this paper, what is changing at Digital Pathology Place, and why foundation models are worth paying attention to now.
02:15 – The core questions: what pathology foundation models are, where they are, and how difficult they are to apply in pathology.
04:50 – Why pathology is becoming more cognitively demanding, and how multimodal complexity is driving interest in scalable AI.
07:02 – From narrow AI to transformers: how pathology moved beyond single-task CNN models.
10:16 – How transformers work in pathology: image patches as tokens, self-attention, embeddings, and downstream tasks.
14:16 – Why multimodality matters, and what kinds of data foundation models may eventually integrate.
15:27 – Timeline of key model developments, from “Attention Is All You Need” to gigapixel-scale pathology foundation models.
17:13 – The leading models and what scale really looks like: Virchow, Mayo Clinic Atlas, UNI, CONCH, H-Optimus, and GigaPath.
19:51 – Why dataset diversity matters more than sheer volume, and why TCGA is not enough.
23:17 – Where foundation models still struggle: cytopathology, hematopathology, rare disease, artifacts, scanner shifts, and pen marks.
28:06 – Explainability, counterfactual explanations, and why trust in pathology AI needs more than attention maps.
30:17 – The real deployment hurdles: regulation, infrastructure, workflow fit, and economics.
36:32 – Why AI should augment pathologists, not replace them, and which tedious tasks pathologists would gladly hand over.
38:36 – Retrieval-augmented and conversational AI in pathology: where interactive systems may actually help.
40:51 – Vision-language models and multimodal fusion with histology, radiology, genomics, and clinical notes.
42:16 – The path forward: deployment-centric design, prospective multi-site validation, and human-AI collaboration.
44:08 – Closing thoughts on AI literacy, community learning, and what needs to happen next.
Resources Mentioned
Main paper discussed:
Pathology Foundation Models: Evolution, Current Landscape, Challenges and Opportunities from a Technical and Clinical Perspective
https://doi.org/10.3390/bioengineering13050577Review article / journal landing page:
https://doi.org/10.3390/bioengineering13050577Benchmarks mentioned:PathoBench — discussed in the review paper; use the review link here for context until you want to swap in a canonical project page:
https://doi.org/10.3390/bioengineering13050577PathBench — public benchmark paper:
https://arxiv.org/abs/2505.20202MEDFAIR — benchmark paper:
https://arxiv.org/abs/2210.01725MEDFAIR code repository:
https://github.com/ys-zong/MEDFAIRModels mentioned:Model overview in the review (Virchow/Virchow2, UNI, CONCH, H-Optimus, GigaPath, TITAN, Mayo Clinic Atlas):
https://doi.org/10.3390/bioengineering13050577Virchow:
https://arxiv.org/abs/2309.07778UNI:
https://arxiv.org/abs/2308.15474CONCH:
https://arxiv.org/abs/2307.12914Mayo Clinic Atlas:
https://arxiv.org/abs/2501.05409TITAN:
https://arxiv.org/abs/2411.19666Dataset mentioned:
The Cancer Genome Atlas (TCGA)
https://portal.gdc.cancer.gov/Book mentioned:
Digital Pathology 101: All You Need to Know to Start and Continue Your Digital Pathology Journey
https://digitalpathologyplace.com/Platform:
Digital Pathology Place
https://digitalpathologyplace.com/Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
How far can pathologists take visual biomarker scoring before human vision becomes the bottleneck?
In this episode, I talk with Doug Bowman. PhD, VP Precision Medicine at Indica Labs, about what happens when companion diagnostics move from traditional visual scoring into the era of AI-powered image analysis. Doug comes from a biomedical and electrical engineering background, with experience in microscopy, digital image analysis, pharma workflows, and now precision medicine at Indica Labs. That combination makes him a great person to talk to about how image analysis actually fits into real companion diagnostic development.
We start with a very practical question: what is a companion diagnostic, and why is it becoming so important in precision medicine? Doug explains that companion diagnostics are developed alongside therapeutics to help identify which patients are most likely to benefit from a specific treatment, especially in more complex therapies like antibody-drug conjugates (ADCs). We use HER2 as an example, and from there we get into the real challenge: once a biomarker cutoff matters clinically, visual estimation around that cutoff becomes much harder than many people want to admit.
That is where this conversation gets especially useful for pathologists and digital pathology trailblazers. We talk about the limits of human vision, why low or ultra-low biomarker expression is difficult to score consistently, and how AI helps at multiple levels of the workflow: slide QC, tissue classification, cell segmentation, membrane and cytoplasmic measurement, and spatial analysis. Doug makes the case that AI is not only a convenience here. In some cases, it is the only realistic way to capture the kind of quantitative information modern therapies need.
We also get into one of the more interesting examples from the episode: the Trop2 story, where a ratio of cytoplasmic to membrane expression appears to predict therapeutic efficacy better than looking at one compartment alone. That kind of compartment-level quantitation is exactly where computational pathology becomes more than a digital version of what the eye already does. It starts uncovering measurements and signatures the eye cannot reliably extract on its own.
Another important part of the discussion is workflow and regulation. Doug walks through how AI-powered companion diagnostics are developed from preclinical work, to human feasibility studies, to RUO or clinical trial assays, and eventually toward analytical and clinical validation with regulatory engagement happening early. We also talk about the Indica Labs and Leica Biosystems partnership, and why end-to-end capability matters when you are trying to build something clinically deployable rather than just analytically interesting.
What I liked about this conversation is that it stayed grounded. We did not talk about AI as magic. We talked about image analysis as a method, companion diagnostics as a workflow, and precision medicine as something that only works when the measurement is good enough to support real decisions.
Episode Highlights00:00 – Why AI matters in slide QC, tissue classification, and cell-level analysis before you even get to the biomarker score.
00:54 – Doug Bowman’s background in biomedical engineering, microscopy, and digital image analysis.
05:16 – What a companion diagnostic actually is, and why it is critical for targeted therapies and ADCs.
07:34 – Why visual biomarker scoring becomes unreliable around critical cutoffs, especially in low-expression cases.
10:09 – How AI expands the workflow: slide QC, tissue classification, and precise cell segmentation.
13:07 – Why pathologists remain central in AI workflows through validation, markup review, and model refinement.
16:31 – The Trop2 example: when cytoplasmic-to-membrane ratio tells you more than one compartment alone.
20:23 – The Indica Labs + Leica Biosystems partnership and why end-to-end workflow matters in companion diagnostics.
22:53 – What the development journey looks like from early algorithm work to RUO, validation, and regulatory interaction.
26:51 – Multiplexing, spatial analysis, and why more clinical value often comes with more deployment complexity.
33:29 – Why image analysis literacy matters, and how shared language between pathologists and scientists becomes essential.
40:13 – Where to learn more about Indica Labs and who to contact for collaboration.
Indica Labs Indica Labs contact – [email protected] software / HALO AI diagnostic image analysis – discussed in the context of companion diagnostic deployment and pharma services.Leica Biosystems GT450DX – referenced as an FDA-cleared slide scanner in the Indica-Leica partnership.Digital Pathology Association – mentioned as part of the broader educational ecosystem for digital pathology and image analysis.Digital Pathology Place / Digital Pathology Podcast – the platform hosting this conversation and related education around digital pathology and AI.
Resources mentionedSupport the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Saknas det avsnitt?
-
Send us Fan Mail
Can AI copilots really keep up with pathologists when the cases are new, the workflow is messy, and the benchmark is actually protected from leakage?
In this episode of DigiPath Digest #48, I focus on one paper: DALPHIN: Benchmarking Digital Pathology AI Copilots Against Pathologists on an Open Multicentric Dataset. I chose this paper because I think the field needs more of this kind of work. Less hype. More evaluation. Less “look what AI can do.” More “how do we test it in a way that actually means something?”
In this session, I look at what makes DALPHIN important for pathologists, lab leaders, and digital pathology trailblazers trying to make sense of pathology AI right now. The paper benchmarks three models against human pathologists: two general-purpose models, Gemini 2.5 Pro and GPT-5, and one pathology-specific model, PathChat+. The dataset includes 1,236 images from 300 cases, covering 130 diagnoses, 14 pathology subspecialties, and cases from six countries. Human performance is benchmarked with 31 pathologists from 10 countries.
What I like about this paper is that it does not stop at top-line performance. It deals with the benchmarking problem itself. The authors built a sequestered, indirectly accessible ground truth so the evaluation data could not simply be scraped into model training. That matters because without that protection, benchmarking can become an illusion of genius rather than a real test of generalization.
The results are interesting and more nuanced than a simple win-or-lose story. PathChat+ reached expert-level performance in four of six tasks, Gemini in two of six, and GPT in one of six. That tells us something important already: pathology-specific training matters. But it also does not mean pathology is solved. In organ recognition, expert pathologists still outperformed all the models. In rare cancers, none of the models reached expert-level performance. And in ambiguous cases, the models still struggled with something human pathologists do all the time: expressing uncertainty.
I also spend time on one of the most practical parts of the paper: model behavior. Gemini tended to overcall. GPT tended to undercall. PathChat was more balanced. That matters in practice. A pathologist using a copilot needs to know the tool’s calibration bias before they can safely interpret what it is telling them. I also talk about anchoring bias in conversational interfaces, where early hallucinations can propagate through later answers if memory is not reset between questions. That is not just a technical curiosity. That is a workflow and safety issue.
Why should you listen? Because this episode is really about a bigger question: What kind of evidence should pathologists demand before AI copilots enter real workflows? If you want to understand validation, data leakage, rare-case performance, uncertainty, and why these tools should still be treated as co-pilots rather than autopilots, this is a useful paper to know.
Episode Highlights
01:20 – Why I chose the DALPHIN preprint and why benchmarking matters right now.
05:38 – What is in the DALPHIN dataset: 300 cases, 130 diagnoses, 14 subspecialties, 6 countries.
07:57 – Top-line performance: PathChat+ reaches expert-level performance in 4 of 6 tasks.
09:41 – The benchmarking trap of data leakage and why DALPHIN’s sequestered ground truth matters.
12:19 – Why real pathology diagnosis is not text-only and why macro + micro context matters.
15:26 – Tissue recognition, neoplasm detection, ambiguity, and conversational memory: how the testing was structured.
21:29 – The diagnostic personalities of the models: overcalling, undercalling, and balanced behavior.
24:36 – Rare cancers: where AI copilots still fall short of expert human performance.
28:00 – Why binary outputs are not enough when pathology often lives in uncertainty.
31:37 – Anchoring bias and conversational memory: how early hallucinations can keep propagating.
37:11 – Why these tools should be treated as co-pilots, not autopilots.
40:29 – Resources for beginners: Digital Pathology 101 and continued AI literacy.
Resources mentioned
DALPHIN preprint: arXiv:2605.03544v1 DALPHIN evaluation platform: dalphin.grand-challenge.org PathChat+ pathology-specific AI model discussed in the benchmark. Digital Pathology 101 free eBook by Dr. Aleksandra Zuraw. Educational streams on tissue recognition and computer vision literacy mentioned in the session.Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Do you really need a scanner, whole slide images, and AI infrastructure before you can start in digital pathology?
In this episode, I argue that you do not.
I’m Dr. Aleksandra Zuraw, veterinary pathologist and digital pathology educator, and this talk is about a belief I hear all the time: I don’t have the tools yet, so there is no point learning digital pathology. I used to think that too. When I was training in Berlin, there was one Leica 6-slide scanner, and it felt like digital pathology was only for a small group of chosen people. That experience made the field feel distant, exclusive, and not really available to beginners.
What changed for me was not a new scanner. It was a small project.
I needed a more consistent way to quantify a senescence marker in archived skin samples, so I used a microscope camera, captured images, opened them in Microsoft Paint, and manually marked cells with colored dots. It was scrappy. Very low tech. But it was also digital, consistent, and verifiable. That project became my first real step into digital pathology and helped me get my first job in the field, where I worked between pathologists and image analysis scientists on biomarker quantification and patient stratification problems.
That is the core point of this episode: knowledge unlocks technology.
Scanners matter. AI tools matter. But the deeper bottleneck is whether enough people understand how to use these tools, ask good questions, and connect pathology expertise with digital workflows. That is why this episode is really about readiness. Not readiness of the hardware. Readiness of the people.
I also talk about Dr. Taladzer from Pakistan, whose story makes this point even more clearly. At the time, Pakistan had around 220 million people, about 500 pathologists, and zero scanners. She still started learning digital pathology during COVID using a microscope and camera, joined the Digital Pathology Association, taught herself from papers and online resources, and kept going even after multiple AI vendors rejected her because she did not have whole slide images. Eventually, she found a DIY image analysis platform, learned to annotate and train models on static images, completed projects quickly, and went on to publish more than 10 digital pathology papers without ever using WSI.
Why should you listen?
Because this episode is for pathologists and lab leaders who are interested in digital pathology but still feel stuck at the beginning. It is for people waiting for permission, perfect infrastructure, or a formal roadmap. And it is for trailblazers who came back from a meeting or conference energized, but need a practical way to turn that energy into action before it fades.
I also address an important AI question near the end: How do we know an AI model is good enough for pathology? I talk about why models are only as good as the pathologist annotations used to train them, why concordance between pathologists matters, how orthogonal labels like IHC can improve model quality, and why pathologists still need to stay in the loop as these systems develop and get deployed.
If you are trying to figure out where to start, this episode gives you a practical answer: start where you are. Start with what you have. Start learning now.
Episode Highlights
00:00 – Why the real barrier to digital pathology is usually not the hardware
00:33 – What it feels like to be at the beginning of the digital pathology journey
02:50 – My first practical digital pathology project using a microscope camera and Microsoft Paint
05:37 – How that low-tech project led to my first digital pathology job
08:52 – Why knowledge, not infrastructure, is the real unlock
09:57 – Dr. Taladzer’s story: starting digital pathology in Pakistan with zero scanners
12:03 – What happened after repeated vendor rejection and why persistence mattered
14:39 – The “forgetting loop” vs the “commitment loop” after conferences
16:48 – Practical next steps: book, PubMed alerts, journal clubs, webinars, vendor resources
18:52 – Why I believe digital pathology is the gateway to faster diagnosis
20:00 – How to think about whether an AI model is really ready for pathologyResources Mentioned
Digital Pathology 101 – free book recommended as a starting point for learning digital pathology. Digital Pathology Association – mentioned as a learning resource and professional community. PubMed alerts for AI and digital pathology. Journal clubs – mentioned as one way to keep learning consistently. Webinars and vendor resources – suggested as practical ways to keep building knowledge. A4A – the DIY image analysis platform that supported Dr. Taladzer’s early work with static image annotation and model training.Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Why are pathology vendors still speaking different image languages when radiology solved that problem decades ago?
In this episode of DigiPath Digest #46, I talk through four papers that all point to a bigger issue in digital pathology: we are not only dealing with better algorithms. We are dealing with interoperability, workflow design, explainability, and whether the field is actually ready to use these tools well.
I start with DICOM in digital pathology, because I think this is still one of the most important infrastructure questions in the field. Digital pathology has clear value for consultation, image analysis, archival, and workflow, but vendor-specific whole slide image formats still create silos. In the episode, I explain why DICOM matters, why adoption is still low, how the multi-resolution pyramid works, and why this is really about enterprise imaging and future-proofing, not just file conversion.
Then I move into kidney transplant rejection, where the paper makes a strong case for multimodal precision diagnostics. Creatinine is late. Antibody testing can miss important biology. Biopsies can miss the area that matters. So the opportunity is not to replace pathology, but to combine biomarkers, biopsy, and machine learning in a way that is more useful than any one signal alone. I also talk about explainability here, because if a model gives a risk score, we need to know what contributed to it.
The third paper focuses on perineural invasion in solid tumors, and I liked this one a lot because it shows how AI can help standardize something that is clinically important but still inconsistently detected and reported. Perineural invasion is not just a passive pathway of spread. The biology is more active than that, and the quantification can go far beyond a simple yes-or-no answer. This is a good example of where digital pathology can do something humans cannot realistically do by eye at scale.
The last paper is on gastric cancer immunohistochemistry biomarkers and advanced quantification, including HER2, PD-L1, mismatch repair, and CLDN18.2. This section is really about complexity. We are now asking pathologists to visually score biology that is getting harder and harder to summarize consistently, especially when markers, spatial context, and multiplexing all start to matter at once. I make the case that computational pathology is becoming necessary here, not because pathologists are failing, but because the biology is outgrowing purely visual workflows.
What ties these four papers together is simple: digital pathology is not only about remote reading anymore. It is about interoperability, quantification, explainable AI, and making pathology more precise in places where the old workflow is reaching its limit. If you are a pathologist, lab leader, or digital pathology trailblazer trying to figure out what actually matters right now, this episode will help you connect the dots.
Episode Highlights
07:41 – Why DICOM still matters if we want digital pathology systems to work together.
14:39 – Current adoption of SVS, MRXS, and DICOM, and why DICOM is still lagging.
16:44 – How the DICOM whole slide image pyramid works and why it matters for workflow.
24:29 – Why kidney transplant rejection is still difficult to diagnose with any single marker.
29:18 – Why perineural invasion is clinically important and still inconsistently reported.
34:44 – How AI can quantify tumor-nerve relationships more consistently than visual review alone.
46:39 – Why gastric cancer biomarker scoring is getting too complex for purely visual workflows.
54:55 – Multiplexing, spatial biology, and why explainable AI matters in biomarker interpretation.
01:04:01 – What is really blocking digital pathology adoption: cost, workflow, regulation, or mindset?Resources mentioned
DICOM / digital pathology interoperability paper
https://pubmed.ncbi.nlm.nih.gov/42093730/Kidney transplant rejection, biomarkers, and artificial intelligence
https://pubmed.ncbi.nlm.nih.gov/42073482/Perineural invasion in solid tumors with AI and machine learning applications
https://pubmed.ncbi.nlm.nih.gov/42100436/Gastric cancer IHC biomarkers, advanced detection methods, and perspectives
https://pubmed.ncbi.nlm.nih.gov/42075555/Digital Pathology Place
https://digitalpathologyplace.comDigital Pathology 101
Free PDF book mentioned at the end of the episode through Digital Pathology Place.Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
What if the most frightening part of a pathology report is not the word cancer, but the silence that follows?
In this episode of the Digital Pathology Podcast, Dr. Aleksandra Zuraw talks with Michele Mitchell—breast cancer survivor, caregiver, national patient advocate, and longtime volunteer across Michigan Medicine, ASCP, the Digital Pathology Association, and MyPathologyReport.ca—about what happened when she saw her own cancer slide years after treatment. That moment changed how she understood her disease, her risk, and her role as a patient advocate.
This is not just a patient story. It is a digital pathology implementation story.
The episode looks at how digital pathology removes practical barriers to sharing slides, why pathology clinics matter, and what becomes possible when pathologists move from being hidden in the background to becoming direct contributors to patient understanding. Michelle and Dr. Aleks talk through the communication gap around pathology reports, the emotional cost of delayed explanation, and the real-world workflow of pathology clinic visits built to help patients review their slides with the pathologist who made the diagnosis.
They also discuss what the 21st Century Cures Act changed for patients, why immediate access to reports without interpretation can still create fear, and how pathology clinics can bridge the gap between raw data and real understanding. The conversation gets practical too: how patients can request a pathology clinic visit, what virtual pathology consults can look like, how billing and workflow concerns are already being addressed, and why the infrastructure question is smaller than many people assume.
If you work in digital pathology, pathology informatics, patient communication, or implementation, this episode is a reminder that visibility is not extra. It is part of the value proposition. And for pathologists who worry this is too far outside the traditional role, the episode offers a grounded counterpoint: the workflows, templates, billing structures, and virtual options already exist.
Highlights
00:00 – Why pathology needs to become more patient-centered
Michele frames the core problem clearly: what often scares patients is not only cancer, but the silence around the diagnosis. 00:34 – How digital pathology changes the patient experience
Digital slides make it possible for patients to see their diagnosis, compare normal and abnormal tissue, and ask better questions. 11:13 – What happened when Michele saw her cancer for the first time
More than a decade after treatment, seeing her own slide changed how she understood her grade, her risk, and her daily health decisions. 16:19 – Why visual pathology can change adherence and lifestyle
Michele explains how the image-based explanation became a practical turning point, not just an emotional one. 20:43 – The case for direct pathologist-patient communication
The episode reviews why this can improve clarity, treatment understanding, clinic efficiency, and even professional satisfaction for pathologists. 38:40 – What a pathology clinic actually looks like
From preparation and consent to slide review, plain language, empathy, and follow-up, the workflow is much more concrete than many people assume. 45:35 – ASCP’s certification workshop for pathology clinics
Michele describes the national effort to make pathology clinics reproducible, scalable, and easier to implement. 49:32 – What the 21st Century Cures Act changed
Patients now get near real-time access to reports, but that access still needs interpretation, context, and support. 01:03:23 – Pushback, logistics, and why the barriers are not where people think
Time, reimbursement, scheduling, and virtual setup are addressed directly with examples already in practice. 01:16:57 – The future: patient-friendly reports, AI, and pathology as part of the care team
The episode closes on a practical vision: not hype, but tools and workflows that already exist and can be connected now.Resources mentioned
Digital Pathology Place – website and educational platform referenced by Dr. Aleks as the home for her work and resources. Digital Pathology 101 – Dr. Aleks’s book, referenced in the broader discussion of patient and pathologist education. Michigan Medicine breast pathology clinic – launched in 2023 as a patient-facing breast pathology clinic model. ASCP pathology clinic certification workshop – national workshop co-developed to help institutions build pathology clinics. 21st Century Cures Act – legal framework behind near real-time patient access to pathology reports and related health data. MyPathologyReport.ca – patient-friendly pathology education resource reviewed with patient advocate involvement. American Cancer Society Reach to Recovery – support resource mentioned for breast cancer patients. Scanslated – patient-friendly report interface discussed as part of a future-facing model for pathology communication. Virtual pathology consults/telehealth setup – discussed as a scalable way to lower implementation friction.Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
DigiPath Digest #45 asks a practical question: can AI in pathology move from correlation to real clinical use? In this episode, I review four papers that push on that question from different angles: computational pathology moving toward morphology-driven molecular inference, the current state of digital cytopathology and AI, multi-omics and precision oncology in hepatocellular carcinoma, and AI literacy in veterinary education. What ties them together is not model performance alone. It is the harder question of validation, workflow fit, quantitative use, ethics, and human oversight.
In the first paper, I talk about computational pathology as more than pattern recognition. The focus is on morphology-driven molecular inference, digital biomarkers, and why spatial omics matters as biological ground truth. I also discuss why continuous quantitative scoring is more useful than forcing biology into rough scoring buckets.
The second paper focuses on digital cytopathology. Cytology was early for FDA-cleared AI in cervical screening, but non-gynecologic cytology is still much harder to digitize because of specimen variability and workflow complexity. I also cover telecytology, rapid onsite evaluation, automation, and quality control.
The third paper looks at hepatocellular carcinoma and AI-driven precision oncology. This part is about using AI and machine learning to integrate genomics, transcriptomics, proteomics, metabolomics, radiomics, and pathology to support biomarker discovery, tumor microenvironment analysis, and treatment stratification.
The fourth paper may be the most broadly useful. It proposes an AI literacy curriculum for veterinary education that covers AI fundamentals, machine learning evaluation, LLMs, ethics, liability, and academic integrity. I think that matters far beyond veterinary medicine, because if clinicians are expected to use AI tools responsibly, AI literacy cannot stay optional.
Highlights
00:01 Welcome and overview of the four papers
03:02 Computational pathology and morphology-driven molecular inference
11:01 Digital cytopathology, telecytology, and QC
20:47 AI/ML in hepatocellular carcinoma precision oncology
31:04 AI literacy in veterinary education
47:42 Final takeaways and Digital Pathology 101 updateResources
Computational Pathology as a Mechanistic Discipline: From Morphology to Molecular Data
https://pubmed.ncbi.nlm.nih.gov/42052846/
Advances in Digital Cytopathology and Artificial Intelligence Applications
https://pubmed.ncbi.nlm.nih.gov/42046894/
Navigating the Labyrinth of Hepatocellular Carcinoma: Leveraging AI/ML for Precision Oncology
https://pubmed.ncbi.nlm.nih.gov/42065059/
Curriculum Framework for Artificial Intelligence Literacy in Veterinary Education
Front Vet Sci. 2026;13:1801756Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Where is AI in pathology actually becoming useful right now? In this episode of DigiPath Digest, I review 4 new PubMed papers across digital pathology, whole slide imaging (WSI), computational pathology, medical education, forensic pathology, and breast cancer AI. We look at a deep learning tool for coronary artery stenosis measurement in forensic autopsies, an AI-powered digital pathology model for renal pathology education, an open-source quality control tool for prostate biopsy whole slide images, and a breast cancer stage prediction model built for resource-constrained settings using low-magnification H&E slides. I also share updates on the upcoming second edition of Digital Pathology 101 and the decision to make AI paper summaries public on the podcast feed to help busy pathology professionals stay current.
Highlights
[01:28] Update on the upcoming second edition of Digital Pathology 101 and the release of public AI paper summaries for faster literature review.[05:22] Paper 1: Deep learning for coronary artery stenosis evaluation in forensic autopsies using whole slide imaging. Why objective stenosis measurement matters, how the model outperformed visual estimates, and why this could affect adoption in forensic pathology.
[15:18] Paper 2: AI-powered digital pathology with case-based teaching in renal education. A practical discussion on annotated digital slides, flipped classroom learning, and how digital pathology can improve pathology education and diagnostic reasoning.
[21:34] Paper 3: Open-source AI for quantitative quality control in prostate biopsy whole slide images. Why WSI quality control matters, what PathProfiler measures, and how automated QC can support remote pathology workflows.
[32:38] Paper 4: Breast cancer stage prediction from H&E whole slide images in resource-constrained settings. A look at low-magnification AI, vision transformers, and what moderate performance can still mean when access to advanced testing is limited.
[45:06] Closing thoughts, invitation to vote for future AI paper summaries, and a final reminder to download Digital Pathology 101.
Resources
Paper 1: Development of a deep learning-based tool for coronary artery stenosis evaluation in forensic autopsies using whole slide imaging
PubMed: https://pubmed.ncbi.nlm.nih.gov/41998396/Paper 2: Integrating AI-Powered Digital Pathology With Case-Based Teaching: A Novel Paradigm for Renal Education in Medical School
PubMed: https://pubmed.ncbi.nlm.nih.gov/41995002/Paper 3: Application of an open-source AI tool for quantitative quality control in whole slide images of prostate needle core biopsies - a retrospective study
PubMed: https://pubmed.ncbi.nlm.nih.gov/41994924/Paper 4: Deep-learning-based breast cancer stage prediction from H&E-stained whole-slide images in resource-constrained settings
PubMed: https://pubmed.ncbi.nlm.nih.gov/41993946/Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Paper Discussed in this Episode:
Deep-learning-based breast cancer stage prediction from H&E-stained whole-slide images in resource-constrained settings. Bedőházi Z, Biricz A, Kilim O, et al. Journal of Pathology Informatics 21 (2026) 100644.
Episode Summary:
Welcome back, Trailblazers! In this Journal Club deep dive of the Digital Pathology Podcast, we flip the core assumption of microscopic precision on its head. Can an AI accurately predict pathological breast cancer stages (pTNM I-III) from a blurry, high-altitude 2.5x magnification snapshot? We explore a 2026 study that strips away standard high-resolution data to build a highly efficient, resource-aware AI diagnostic tool for clinics lacking supercomputers. We unpack the math, the models, and a haunting revelation about what primary tumors can tell us about distant metastasis.
In This Episode, We Cover:
• The Compute Bottleneck: Why the digital pathology AI revolution is leaving resource-constrained clinics behind, and how dropping from the standard 40x to 2.5x magnification slashes image patch extraction by 256 times, bypassing massive hardware and server requirements.
• The "Airplane View": How the AI compensates for the loss of microscopic cellular details (like mitosis or cellular atypia) by relying on macroscopic features, identifying disease through overall tumor growth patterns and broad architectural disruption.
• Vision Transformers & "Puzzle Bags": Why the UNI foundation model—a vision transformer fine-tuned on the BRACS dataset—outperforms older convolutional networks (like ResNet-50) by mapping long-range spatial dependencies across the entire image patch simultaneously. Plus, how Multiple Instance Learning (MIL) acts as a targeted "puzzle bag," mathematically weighting critical cancer data and ignoring irrelevant background noise.
• The Real-World Stress Test: The model's solid performance on the internal Semmelweis dataset versus the massive external Nightingale cohort, where unsupervised data cleaning with t-SNE and DBSCAN clustering automatically deleted garbage data. We also discuss the AI's struggle with the TCGA-BRCA dataset due to severe domain shift from heterogeneous tissue preparation, specifically the structural tissue damage caused by frozen sections.
• The "Messy Middle" and Clinical Triage: The model's tendency to struggle with Stage II breast cancer and the critical clinical danger of under-staging advanced Stage III cancers. We discuss why this WSI-only baseline isn't replacing human pathologists, but rather serves as an automated "sorting hat" for incomplete medical records or a highly tunable "smoke detector" to route suspicious slides for immediate manual review.
Key Takeaway:
The AI successfully predicted overall cancer stage—which inherently includes distant lymph node metastasis—by looking only at the primary tumor's architectural disruption, without ever evaluating a single lymph node slide. This proves that vital systemic biological secrets are hiding in plain sight in the macroscopic view of standard H&E slides, offering a phenomenal proof-of-concept for global health equity in resource-constrained settings
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Paper Discussed in this Episode:
Integrating AI-Powered Digital Pathology With Case-Based Teaching: A Novel Paradigm for Renal Education in Medical School. Zhou H, Cui L. Clin Teach 2026; 23(3):e70421. doi: 10.1111/tct.70421.
Episode Summary: In this journal club episode tailored for healthcare trailblazers, we explore a massive paradigm shift in medical education. We examine a 2026 perspective article that uses the notoriously complex field of renal pathology as a stress test for a brand-new teaching model. Moving away from dark lecture halls and static, perfect images, we discuss what happens when artificial intelligence is actively combined with flipped classrooms, fundamentally redefining what it means to be a competent physician in the digital age.
In This Episode, We Cover:
• The "Bottleneck" of Renal Pathology: Why the kidney is the ultimate teaching hurdle. Students must translate the dense, flattened 2D reality of an H&E stain into an understanding of a patient's complex systemic autoimmune response.
• The Danger of the "Curated Reality": Why traditional teaching methods that rely on textbook-perfect, heavily curated slides create "brittle" mental models. When students finally encounter messy, real-world biopsies with overlapping, ambiguous pathologies, the traditional educational foundation falls apart.
• The "Spell Checker" for Histopathology: How collaborative AI elevates Whole Slide Imaging (WSI) beyond just high-resolution screens. The AI acts as a concurrent guide, using pixel-level pattern recognition to highlight regions of interest simultaneously and simulate the complex reasoning process of an expert pathologist.
• The Case-Based Flipped Classroom (CBFC): The pedagogical engine that anchors these AI tools in clinical reality. Instead of passive lectures, students are handed the "detective's case file" beforehand to actively interrogate annotated slides, synthesizing diverse data streams to defend diagnoses in collaborative groups.
• Redefining Medical Competence (The "Clinical Editor"): Why the new bottleneck in medical education isn't memorization—it's critical appraisal. We discuss the necessity of teaching "digital literacy," training students to skeptically manage AI, recognize its blind spots (like confusing a physical tissue fold for an abnormality), and actively audit the algorithm against the messy human reality of the patient.
• The Impending Culture Collision: A look at the fascinating future where freshly minted, AI-native residents enter a legacy clinical workforce still transitioning away from physical glass slides, potentially reversing traditional medical hierarchies in the hospital.
Key Takeaway: The goal of modern medical education is no longer just memorizing histological patterns, as that heavy lifting is being outsourced to algorithms. By fusing AI-powered digital pathology with the necessary friction of case-based learning, we are training a new generation of diagnosticians to view AI not as a crutch, but as a powerful collaborative tool that must be thoughtfully scrutinized and audited for safe patient care
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Paper Discussed in this Episode:
Spatial omics and AI for clinically actionable cancer biomarkers. Reitsam NG. PLoS Med 2026; 23(4): e1005049.
Episode Summary: In this deep dive, we explore how artificial intelligence and spatial omics are fundamentally rewriting the rules of cancer diagnostics. We break down a 2026 editorial that challenges a deceptively simple question driving modern oncology: Is a tumor "positive" or "negative" for a biomarker? As targeted cancer therapies evolve, this binary thinking is failing us. We discuss why mapping where and how much of a therapeutic target exists is crucial, and how AI is stepping in to solve the reproducibility issues human pathologists face when making borderline diagnostic calls.
In This Episode, We Cover:
• The Illusion of "Positive" vs. "Negative": Why the basic premise of modern cancer therapies—like antibody-drug conjugates (ADCs)—often falls apart in reality when we ignore the spatial heterogeneity of a tumor.
• The Power of Computational Pathology: How AI is transforming subjective, qualitative estimates into continuous, reproducible data, scaling the quantification of complex biomarkers like PD-L1 and TROP2.
• "Virtual" Proteomics: The fascinating concept of using AI models to infer high-dimensional spatial information and immune maps directly from standard, routine H&E stained slides.
• The HER2 Bottleneck: A real-world look at the breast cancer drug T-DXd, which now demands pathologists distinguish between "HER2-low" and "HER2-ultralow". While human agreement drops below 70% at these fuzzy decision boundaries, AI steps up with a staggering ~97% sensitivity.
• Three Shifts for the Future: Why clinical trials and routines must adopt continuous measures (like percentage of expressing cells), demand longitudinal repeat testing at disease progression, and utilize adaptive trial platforms.
• Bridging the Gap to Reality: The massive hurdles preventing widespread adoption—such as equipment costs exceeding $250,000 and massive data storage needs. We discuss why a hybrid workflow that bolsters routine pathology with deployable AI is the best path forward to prevent widening global health disparities.
Key Takeaway: The future of precision oncology isn't just about finding new drug targets; it’s about fundamentally changing how we measure them. By moving away from rigid binary thresholds and using AI to map the continuous, spatial reality of tumors, we can unlock the true potential of targeted therapies. However, achieving this diagnostic ecosystem requires overcoming significant financial and systemic hurdles—such as updating reimbursement pathways and proficiency testing—to ensure these life-saving insights are accessible across all healthcare settings.
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Paper Discussed in this Episode: Artificial intelligence in clinical oncology: Multimodal integration and translational development. Ruichong Lin, Zhenhui Zhao, Zhonghai Liu, Jin Kang, Kang Zhang, Xiaoying Huang, Yunfang Yu. Cancer Letters 2026; Volume 649, 218493.
Episode Summary: In this journal club deep dive, we explore how cutting-edge AI is fundamentally rewriting the rules of cancer diagnostics. We examine a comprehensive 2026 review on clinical oncology that highlights the shift from narrow, single-modality algorithms to highly sophisticated multimodal AI. We discuss how machines are learning to cross-reference patient charts, genomic data, and medical imaging simultaneously to achieve unprecedented feats—like accurately predicting tumor mutations without ever performing a physical biopsy. Plus, we explore the controversial but necessary world of "computational hallucinations" or synthetic data, which is currently being used to solve diagnostic blind spots.
In This Episode, We Cover:
• The Fragmentation Bottleneck: Why keeping radiology, pathology, genomics, and clinical history in isolated silos limits our ability to treat the whole patient, and why single-modality AI suffers from severe diagnostic "tunnel vision".
• Cross-Modal Attention & Non-Invasive Biopsies: How models like LUCID essentially mimic the deductive reasoning of a multidisciplinary tumor board. By utilizing cross-modal attention mechanisms, LUCID dynamically shifts focus between CT scans, routine labs, and text-based clinical charts to predict EGFR gene mutations in lung cancer entirely non-invasively.
• Graph Neural Networks (GNNs) & Tumor Social Networks: A look at the NePSTA framework, which uses GNNs and spatial transcriptomics to treat the tumor microenvironment like a mathematical topology. By mapping the "social network" of cells, it can rapidly molecularly subtype notoriously ambiguous central nervous system (CNS) tumors in minutes.
• Computational Hallucinations: Introducing MINIM, a generative AI foundation model that creates statistically valid, photorealistic synthetic medical images (like optical CT or chest X-rays) for rare diseases based on textual descriptions. We discuss how intentionally generating these synthesized images solves the critical "data scarcity" problem and directly improves real-world diagnostic accuracy.
• The Reality Check - Distribution Shifts: The dangerous logistical reason why an AI model boasting near-perfect accuracy at a massive urban academic center might fail completely in a rural clinic due to differing scanner calibrations and population demographics. We emphasize why the field must transition away from retrospective "vanity metrics" and toward clinically trustworthy prospective validation.
• The Virtual Cell Paradigm: A staggering look into the near future where AI constructs completely accurate, computationally interactive digital twins of a patient's cancer. This framework allows doctors to test different drug regimens and simulate cellular responses mathematically in silico before ever administering medicine to the actual patient.
Key Takeaway: Multimodal AI proves that cancer diagnostics must go beyond isolated data points. By dynamically synthesizing highly fragmented clinical information and utilizing synthetic imaging to overcome rare disease data scarcity, AI is pushing oncology into an era of robust, individualized molecular phenotyping. Ultimately, these innovations are replacing risky, invasive testing with precision computational predictions
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Paper Discussed in this Episode: Advancements in bone marrow biopsy: the role of omics and artificial intelligence in hematologic diagnostics. Maryam Alwahaibi and Nasar Alwahaibi. Front. Med. 2026; 13:1772478.
Episode Summary: In this journal club deep dive, we explore a paradigm shift in hematopathology, moving from 19th-century visual assessments to the cutting edge of precision medicine. We examine a 2026 review that unpacks how combining artificial intelligence with multi-omics technologies is transforming the traditional bone marrow biopsy from a static, subjective snapshot into a live, interactive, predictive 3D map. We ask: What happens when deep learning can predict underlying genetic mutations just by analyzing the visual shape and texture of a cell?.
In This Episode, We Cover:
The Breaking Point of Traditional Diagnostics: Why the 150-year-old gold standard of H&E staining and human visual assessment is hitting a biological and operational wall, plagued by subjectivity, high variability, and observer fatigue.
The Multi-Omics Multiverse: Moving beyond standard genomics to unpack the complex biological machinery of the marrow, including:
Epigenomics: The biological "switches," like DNA methylation, that control cell fate and can kick off malignant transformation without altering the underlying DNA sequence.
Lipidomics: How cellular fats form specialized signaling rafts that actively remodel the marrow's communication network.
Microbiomics (The Gut-Marrow Axis): How systemic inflammation driven by gut dysbiosis acts like a massive "traffic jam" that indirectly disrupts local bone marrow homeostasis and blood cell production.AI as the Ultimate Analytical Partner: How artificial intelligence serves as a bridge between physical tissue morphology and high-dimensional molecular data. We discuss AI tools like MarrowQuant for objective cellularity mapping and the Continuous Index of Fibrosis (CIF) that replaces clunky human guesswork with a granular, predictive metric.
Predicting Genotype from Phenotype: The revolutionary capability of deep learning models to predict underlying genetic mutations (like TET2 or del 5q MDS) purely from the subvisual, spatial arrangement and shape of cells on a standard slide.
Roadblocks and Solutions: Why this technology isn't universally adopted yet. We break down the "black box" problem of AI, the brittleness of algorithms in different clinical settings, and how innovations like Federated Learning and Explainable AI (using heat maps) are overcoming these hurdles.
Key Takeaway: The integration of AI and multi-omics is redefining our understanding of bone marrow diseases. By uncovering invisible molecular machinery and objectively translating it through transparent algorithms, we are moving away from subjective human bottlenecks toward a highly personalized, predictive model of hematologic care.
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
I did something I've never done before for this episode — I went live from the middle of a national park. This is DigiPath Digest #42, broadcasting from the Great Sand Dunes National Park in Colorado via Starlink from my family road trip. Yes, it actually worked. And so did the papers.
This episode covers four papers that all ask the same uncomfortable question from different angles: how close is AI to being genuinely useful in real pathology practice — and what's still standing in the way? From LLMs interpreting cervical Pap smears, to AI guiding breast cancer treatment decisions from a simple H&E slide, to a practical roadmap for bringing generative AI into oncology workflows — this one covers a lot of ground.
I also introduced something new: my AI-powered paper summary podcast subscription. For $7 a month, AI hosts summarize digital pathology literature in a journal-club style so you can stay current without spending hours reading abstracts. I walk through how it works and why I built it.
What we cover:
[00:00] Going live from the wilderness — Starlink, sand dunes, and a very cold morning[02:01] How I use AI-generated audio summaries to prep for each DigiPath Digest[03:19] Paper 1: Can LLMs like ChatGPT and Gemini interpret cervical cytology? Spoiler: ~47–48% exact concordance — promising, but not there yet[10:23] Bonus: My new AI-powered paper summary subscription — $7/month, journal-club style[14:05] Paper 2: AI in oral oncology — CNNs for early lesion detection, multimodal prognostics, and the real barriers still blocking clinical adoption[20:28] Paper 3: Generative AI in oncology — from chat tools to agentic EHR-integrated assistants, and why augmentation is the goal, not automation[25:35] Paper 4: Computational pathology in breast cancer — predicting BRCA1/2, HER2, Oncotype DX, and treatment response from standard H&E slides[31:39] Final thought: the floor just got raised for all of us — how I think about new technology in pathologyResources & Links:
Paper 1 – LLMs & Cervical Cytology (PubMed): https://pubmed.ncbi.nlm.nih.gov/41931983/Paper 2 – AI in Oral Oncology (PubMed): https://pubmed.ncbi.nlm.nih.gov/41930554/Paper 3 – Generative AI in Oncology Practice (PubMed): https://pubmed.ncbi.nlm.nih.gov/41930309/Paper 4 – AI & Digital Pathology in Breast Cancer (PubMed): https://pubmed.ncbi.nlm.nih.gov/41930306/Watch on YouTube: https://www.youtube.com/live/O2hOU4gM0Bk?si=oH8iJ8HiBb29USG3Digital Pathology Place: https://www.digitalpathologyplace.comSupport the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Paper Discussed in this Episode: How artificial intelligence applied to digital pathology could guide treatment personalization in breast cancer. T. Ruelle, T. Grinda, L. Del Mastro, M. Lacroix-Triki, B. Pistilli & G. Gessain. ESMO Real World Data and Digital Oncology 2026.
Episode Summary: In this journal club episode, we step into the reality of computational pathology and explore how artificial intelligence is fundamentally transforming breast cancer diagnostics. We examine a comprehensive review detailing how AI not only assists overburdened healthcare systems but also unlocks invisible genomic data straight from a standard $5 hematoxylin-eosin (H&E) glass slide. What happens when a machine can predict complex DNA mutations just by evaluating the structural architecture of cells?
In This Episode, We Cover:
• The Diagnostic Bottleneck: Understanding the critical worldwide shortage of pathologists colliding with a projected 3.2 million global breast cancer diagnoses by 2050, and why the system is under unprecedented strain.
• The Biomarker Battle: Why the human visual cortex struggles to quantify faint immunohistochemistry stains, and how AI acts as a perfect "digital colorimeter". We discuss its near-perfect concordance in assessing crucial biomarkers like Ki-67, ER, PR, PD-L1, and the newly established HER2-low status.
• Seeing the Invisible (Predictive AI): How deep learning transcends visual diagnostics to predict treatment outcomes, such as a patient's response to neoadjuvant chemotherapy. We also discuss AI's ability to infer Homologous Recombination Deficiency (HRD) and BRCA1/2 mutations by identifying macroscopic footprints like laminated fibrosis.
• Decoding Genomic Assays: The potential to replace expensive, tissue-consuming genomic tests like Oncotype DX with AI models (such as Orpheus) that predict recurrence risk straight from digitized slides, achieving accuracy that rivals the tests themselves.
• Roadblocks to Reality: The major clinical friction preventing global rollout. We discuss the steep infrastructure costs of whole-slide scanners, the danger of AI bias across diverse hospital datasets, and the ethical "black box" problem requiring the evolution of transparent, agent-based AI.
Key Takeaway: Computational pathology is moving far beyond basic diagnostic assistance. By successfully reading the structural language of biology, AI proves it can extract costly, invisible molecular data from standard biopsies, fundamentally changing the economics and accessibility of global personalized healthcare
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Paper Discussed in this Episode: Artificial intelligence in oral oncology: Current advances and future potential in diagnosis, prognosis, and therapeutic decision-making. Annamalai A, Dhanes V, Jayalakshmi L, Shanmugam R, Ravi S. Cancer Treatment and Research Communications 47 (2026) 101193.
Episode Summary: In this journal club deep dive, we explore how AI is fundamentally reshaping the clinical management of Oral Squamous Cell Carcinoma (OSCC). We examine a comprehensive March 2026 study that confronts a frustrating paradox: despite the oral cavity being visible to the naked eye, OSCC survival rates have stagnated due to late-stage diagnosis and complex tumor biology. This episode breaks down how algorithms are moving oncology from a reactive discipline to a highly predictive, personalized science.
In This Episode, We Cover:
• The OSCC Paradox: Why relying on traditional visual inspection and standard TNM staging ignores biological heterogeneity, and how AI steps in where the naked eye and basic anatomy fall short.
• Pocket Pathologists: The revolutionary use of Convolutional Neural Networks (CNNs) in smartphone apps and portable devices, achieving up to 82% to 92% sensitivity for point-of-care screening in resource-constrained settings.
• The Committee of Algorithms: How AI acts as a "multimodal synthesizer," fusing radiomics (tumor texture), histopathology (tumor-infiltrating lymphocytes), genomics, and Natural Language Processing (NLP) of unstructured clinical notes to predict individualized risk.
• Real-Time Margin Guidance: How AI combined with fluorescent imaging provides surgical margin feedback to surgeons in the operating room in under five minutes with over 85% concordance with expert histopathologists.
• Digital Twins: The sci-fi reality of running virtual clinical trials. We discuss how AI uses reinforcement learning to build simulated patient copies, allowing tumor boards to predict radiotherapy outcomes and drug toxicities before treating the physical person.
• The Black Box, Bias, and the Fix: The major roadblocks preventing immediate clinical rollout. We discuss opaque decision-making and training data bias (which can drop accuracy by over 15% in underrepresented groups). We also explore the solutions: Explainable AI (Grad-CAM heat maps) to visualize decision logic, and Federated Learning (privacy-preserving decentralized training) to eliminate data sharing hurdles.
Key Takeaway: The true value of AI in oral oncology isn't in replacing human clinicians, but in digesting massive multi-omics data that no single human could synthesize alone. By acting as a transparent, explainable support tool, AI is setting the stage for a future where tomorrow's healthcare professional might spend as much time treating a virtual patient as the physical one sitting in the chair
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Paper Discussed in this Episode: Can large language models like ChatGPT and Gemini interpret cervical cytology accurately? Saroja Devi Geetha. Annals of Diagnostic Pathology 2026; Volume 83, 152641.
Episode Summary: In this journal club deep dive, we explore what happens when advanced artificial intelligence is thrown into the visually chaotic realm of human biology. We examine a 2026 study evaluating whether two massive multimodal models—GPT-5 and Gemini 2.5 Pro—can accurately read digital cervical Pap smears without any prior fine-tuning,,. We unpack how these general-purpose models perform on highly specialized visual tasks, revealing that while they aren't ready to fly solo, they exhibit fascinating and distinct diagnostic "personalities" that will undoubtedly reshape the future of the pathology lab,.
In This Episode, We Cover:
• The "Textbook" Test Setup: How researchers tested the baseline visual reasoning of GPT-5 and Gemini 2.5 Pro by feeding them 100 curated, gold-standard digital Pap test images from the Hologic Education Site to classify using the Bethesda System,,.
• The Clinical Reality Check: While the models only achieved a coin-toss exact diagnostic match rate (47% for GPT-5 and 48% for Gemini), their accuracy jumped to 66% when evaluating clinical management protocols—proving they are beginning to grasp the underlying severity and medical consequences of cellular abnormalities,,.
• The Over-Anxious Resident (Gemini 2.5 Pro): Gemini acted like a highly sensitive but unrefined trainee, hitting 84% sensitivity and expertly spotting infectious organisms (71%),,. However, its tendency to confuse dense, overlapping cellular clumps with high-grade squamous intraepithelial lesions (HSIL) led to massive overcalling, dragging its specificity down to 71% and creating a risk of false alarms,.
• The Big-Picture Academic (GPT-5): GPT-5 proved to be much more measured, demonstrating better overall specificity (74%) and excelling at identifying subtle structural shifts like low-grade squamous intraepithelial lesions (LSIL) (75%) and glandular changes,. Yet, in its focus on the big picture, it completely missed obvious infectious organisms, scoring a dismal 20%,.
• The Future of the Lab - Prompt Engineering & The Algorithmic Auditor: Why the next era of cytopathology requires rigorous AI fine-tuning on proprietary datasets and cytology-specific prompt optimization. We discuss a major paradigm shift where human pathologists may transition from actively hunting for disease to acting as "algorithmic auditors" whose primary job is to filter out the hyper-vigilant machine's noise,.
Key Takeaway: Current multimodal LLMs are not yet reliable for independent Pap test interpretation due to critical blind spots and tendencies to overcall lesions,. However, their out-of-the-box performance establishes a staggering baseline. By understanding their unique mechanical flaws, pathologists can prepare to use these systems as highly effective co-pilots, seamlessly combining the algorithm's computational brute force with the indispensable filter of human medical reasoning
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
Paper Discussed in this Episode:
How to bring generative AI to oncology practice. D. Truhn & J. N. Kather. ESMO Real World Data and Digital Oncology 2026.
Episode Summary:
In this journal club deep dive, we step out of the theoretical sci-fi hype of artificial intelligence and look at a practical, real-world roadmap for bringing Generative AI into oncology. We examine a 2026 paper that maps out the trajectory for deploying Large Language Models (LLMs) to combat the overwhelming cognitive load of modern cancer care. Rather than replacing clinicians, this episode explores how AI can synthesize massive amounts of unstructured data—like dense pathology narratives and shifting molecular reports—so doctors can get back to practicing medicine instead of acting as data entry clerks.
In This Episode, We Cover:
• The Data Avalanche in Oncology: Why the shifting landscape of decades of patient histories, clinical trial registries, and handwritten notes creates an information load that human cognition simply wasn't evolved to process all at once.
• How LLMs Actually "Think": Why predicting the "next word" based on massive training data allows AI to mimic medical reasoning and organize complex clinical concepts—like linking a BRAF mutation directly to a specific inhibitor without looking up a rulebook.
• The Three Evolutionary Steps of AI Complexity: ◦ Step 1: Stand-alone Models: The "closed-book exam." These models (like early ChatGPT) are frozen in time with their original training data and have zero access to new clinical trials or FDA updates. ◦ Step 2: Retrieval-Augmented Generation (RAG): The "open-book exam." The AI searches continually updated external databases and guidelines before answering, significantly reducing fabricated answers, or "hallucinations". ◦ Step 3: Agentic AI: The ultimate goal. Fully functioning "research assistants" that can iteratively reason, plan steps, and invoke external software tools (like lab APIs and medical calculators) to complete complex tasks like proposing tumor board summaries.
• The Deployment Roadblocks: Why you can't just drop an autonomous agent into a fragmented hospital IT network built in 2005. We unpack strict security silos, audit logs, and the dangerous reality of "domain shift"—where an AI trained perfectly at Johns Hopkins might silently fail at a community clinic simply due to different doctor shorthand or microscopic slide scanner colors.
• The Human Element & Automation Bias: The hidden dangers of junior doctors losing their clinical intuition (deskilling) and why system design must force the AI to "show its work" with intentional friction to prevent doctors from blindly clicking accept on a hallucinated treatment plan.
• Your Edits Are the Future: A fascinating look at how a clinician's daily administrative annoyances—every strike-through and manual correction of an AI draft—serve as the ultimate, high-value ground-truth data to train the next generation of oncology AI.
Key Takeaway:
The destination we are driving toward is augmentation, not automation. By handling massive information synthesis, uncovering patterns, and explicitly showing its work, AI can act as a tireless assistant that improves routine care, while leaving the final, nuanced clinical judgment exactly where it belongs: with the human physician.Support the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
Send us Fan Mail
You don't need a fancy scanner, a huge budget, or a computational background to get started in digital pathology. That's what I told the ACVP podcast — and I meant it. In this episode, I share my full digital pathology journey: from being completely intimidated by scanners during residency, to building a career that combines toxicologic pathology, image analysis, and remote work at a global CRO.
If you're a resident, a trainee, or even a seasoned pathologist who hasn't fully stepped into the digital space yet — this one's for you.
We talked about practical ways to get started, what foundation models actually mean for our daily work, how to build a team when implementing digital pathology at your institution, and why change management might be the most underestimated skill in this whole process.
What we cover:
[00:00] My background — from veterinary school in Poland to digital pathology[03:22] Why I chose industry over academia, and what that transition looked like[05:02] How a simple IHC side project became my entry point into digital pathology[07:11] How digital slides helped me pass my boards — and fall back in love with histopathology[10:24] My first job at a digital pathology image analysis company[12:00] What my current role at Charles River Laboratories looks like day-to-day[13:53] The best free resources for trainees to start exploring digital slides RIGHT NOW[15:26] Why pathologists need to understand image analysis principles — segmentation, classification, object detection[19:31] Foundation models, transformer architecture, and why annotation bottlenecks may soon be a thing of the past[24:13] Practical advice for institutions implementing digital pathology — equipment, teams, and managing resistance to change[27:30] How I unplug: trail running, weight training, and pathology-themed earringsResources & Links:
Joint Pathology Center (JPC) digital slides: https://www.jpc.orgDavis Thompson Foundation — Noah Slidebox: https://www.davisthomasonfoundation.orgQuPath (free, open-source image analysis): https://qupath.github.ioDigital Pathology Place: https://www.digitalpathologyplace.comWatch the full conversation on YouTube: https://youtu.be/wTDdlxJzq-A?si=xkz5YNljrUX5SnhdSupport the show
Get the "Digital Pathology 101" FREE E-book and join us!
-
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 promotionResources
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!
- Visa fler
