Digital Pathology Podcast

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!

Send a text
If AI can detect patterns we cannot see, how do we know when its answers are clinically trustworthy?
In this episode of DigiPath Digest #39, I explore a big-picture question in digital pathology and medical AI. Many models now match or even exceed human performance in specific diagnostic tasks. But most of that evidence comes from controlled or retrospective datasets. So what happens when we try to bring these tools into real clinical workflows?
I review four recent papers that help frame this challenge and point toward the next steps for trustworthy AI in healthcare. 
You will hear about the role of prospective validation, real-world effectiveness, transparent reporting standards, and multimodal data integration as recurring themes across these studies.
Key Highlights
00:00 – Introduction
What do we do when AI detects signals that humans cannot see? The core challenge is verifying those outputs before trusting them in clinical decision making. 
03:32 – AI Across the Healthcare Continuum
A narrative review shows AI achieving clinician-level performance in well-defined imaging tasks, including digital pathology. But most evidence comes from retrospective or controlled environments, and prospective validation remains limited. 
08:34 – Multi-Omics and AI in Gastric Biopsy Diagnostics
Morphology alone cannot fully capture molecular heterogeneity or predict disease progression. Integrating genomics, proteomics, metabolomics, and other omics with AI is shifting gastric pathology toward data-driven precision gastroenterology. 
13:38 – Hyperspectral Imaging for Real-Time Surgical Guidance
Spectral imaging can analyze tissue composition during surgery without staining, freezing, or contact with the tissue. Studies show promising sensitivity for detecting malignancy and supporting intraoperative decision making. 
17:20 – REFINE Reporting Guideline for Foundation Models and LLMs
An international consensus guideline introduces a 44-item reporting checklist to standardize how AI studies are described. The goal is transparent, reproducible, and comparable research in medical AI. 
22:35 – Big Takeaway
AI should be viewed as clinical decision support, not a replacement for clinicians. Real-world validation, ethical governance, and reproducible research standards will determine how these tools enter pathology workflows. 
References (Articles Discussed)
Artificial Intelligence in Healthcare: From Diagnosis to Rehabilitation
 https://pubmed.ncbi.nlm.nih.gov/41755929/

Transforming Gastric Biopsy Diagnostics: Integrating Omics Technologies and Artificial Intelligence
 https://pubmed.ncbi.nlm.nih.gov/41751306/

From Image-Guided Surgery to Computer-Assisted Real-Time Diagnosis with Hyperspectral and Multispectral Imaging
 https://pubmed.ncbi.nlm.nih.gov/41750768/

REFINE Reporting Guideline for Foundation and Large Language Models in Medical Research
 https://pubmed.ncbi.nlm.nih.gov/41762555/

If you enjoy staying current with digital pathology and AI research, this episode will help you connect the dots between promising algorithms and practical clinical adoption.
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!

Send a text
Clinical Artificial Intelligence in 2026. Accuracy, Education, and Guardrails
Artificial intelligence is evolving fast in medicine. But how accurate is it. And are we building it safely?
In this episode of DigiPath Digest, I review five new studies shaping digital pathology, radiology, burn diagnostics, and agent-based large language model systems. We discuss accuracy gains, hallucination filtering, education challenges, and why safeguards are essential before clinical deployment.
Clear. Practical. Evidence-based.
⏱ Topics & Timestamps
[00:02] Introduction
Weekly journal club on digital pathology and artificial intelligence.
[05:13] Hallucination Filtering in Radiology
Using Discrete Semantic Entropy to detect hallucination-prone responses in Vision Language Models.
Accuracy improved from 51.7 percent to 76.3 percent after filtering high-entropy answers.
[15:04] Artificial Intelligence in Pathology Training
Supervised use during residency.
Balancing artificial intelligence adoption with preservation of morphological analysis and critical thinking.
[20:12] Colorectal Cancer Lymph Node Detection
Two-stage classification and segmentation model in Whole Slide Imaging.
Recall 1.0. Specificity 0.935. Dice coefficient 0.818.
Artificial intelligence as a second opinion.
[25:04] Burn Depth Prediction with Artificial Intelligence
Tissue Doppler Elastography and Harmonic B-mode ultrasound combined with artificial intelligence.
90 to 95 percent accuracy in human subjects.
[31:20] Agent-Based Large Language Model Systems
OpenManus and Manus evaluated in clinical simulations.
Up to 60.3 percent accuracy. High computational cost.
89.9 percent of hallucinations filtered by safeguards.
[40:08] Patient Access to Pathology Images
Why viewing pathology slides can empower patients and improve communication.
Resources
https://pubmed.ncbi.nlm.nih.gov/41720937/
https://pubmed.ncbi.nlm.nih.gov/41720644/
https://pubmed.ncbi.nlm.nih.gov/41716065/
https://pubmed.ncbi.nlm.nih.gov/41709317/
https://pubmed.ncbi.nlm.nih.gov/41708802/
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!

Send a text
What if one of the biggest sources of diagnostic variability in prostate cancer isn’t the pathologist—but the stain we’ve trusted for decades?
In this episode, I speak with Professor Ingid Carlbom, founder of CADESS.AI, about a different way to approach prostate cancer grading—by rethinking staining, segmentation, and AI decision support from the ground up. We explore why 30–40% interobserver variability persists in Gleason grading and how optimized stains combined with explainable AI can significantly reduce that uncertainty.
Ingrid shares her journey from applied mathematics and computer science into pathology, the skepticism she faced in 2008, and why CADESS.AI chose not to “optimize H&E,” but instead developed a Picrosirius red + hematoxylin stain designed specifically for computational pathology. We discuss how grading at the gland and cellular level improves reproducibility, why explainability matters for trust, and what it really takes to build both stain and software as a single diagnostic workflow.
This conversation challenges long-held assumptions—and asks whether improving data quality should come before building smarter algorithms.

Highlights:
[00:00–01:08] The problem: 30–40% disagreement in prostate cancer grading
[01:08–03:03] Ingrid’s path from applied math to digital pathology
[03:03–04:58] Early skepticism toward AI in pathology and fear of replacement
[04:58–08:56] Why H&E limits segmentation—and how a new stain changes that
[10:55–15:09] Clinical testing: non-inferiority, AI assistance, and NCCN risk stratification
[19:47–22:59] Explainable UI: color-coded glands and pathologist override
[26:16–27:29] Why grading glands (not whole slides) reduces variability
[38:09–41:47] Regulatory challenges of combined stain + AI devices
[45:52–48:55] The future of optimized stains in routine pathology

Resources from This Episode
CADESS.AI – Prostate cancer decision support system
NCCN prostate cancer risk stratification guidelines
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!

Send a text
Sometimes a paper comes out that’s so practical and relevant to what we do in digital pathology that I know we have to talk about it.
In this episode, I dive into “A Guide for the Deployment, Validation and Accreditation of Clinical Digital Pathology Tools” from Geneva University Hospital (HUG) — one of the most useful, real-world frameworks I’ve seen for bringing digital pathology tools safely into clinical practice.
If you’ve ever built an AI model and wondered, “Now what?”, this episode is for you.
Because building the model is often the easy part — deployment is where things get complex.
This guide breaks the process into four practical phases every lab can follow:
1️⃣ Pre-Development – Define your clinical need, project scope, and validation plan before writing a single line of code.
2️⃣ Development – Build and integrate the algorithm in a production-ready environment.
3️⃣ Validation & Hardening – Turn your research code into a reliable, secure, and compliant clinical tool.
4️⃣ Production & Monitoring – Keep the tool validated and performing consistently over time.
We also discuss what makes qualification, validation, and accreditation different — and why that order really matters.
You’ll hear about the multidisciplinary team behind these deployments, especially the deployment engineer (DE) — the technical linchpin who turns AI research into clinical reality.
I share the story of HUG’s H. pylori detection tool, which cut diagnostic time by 26% while maintaining a 0% false negative rate. The team’s secret? Careful planning, quality control, and continuous user feedback — not just great code.
Other highlights include:
Why integration often takes longer than building the AI model itself
How to avoid invalidating your validation data
What continuous performance monitoring looks like in real labs
And why every lab still needs to do local validation, even with proven tools
If you’re working on digital or computational pathology tools — or just want to understand how AI safely moves from research to routine diagnostics — this episode will give you a roadmap grounded in real experience.
🎧 Listen now to learn how to move from algorithm to accreditation, step by step.
And if you’re just getting started in digital pathology, I’d love to give you my free eBook, Digital Pathology One-on-One: All You Need to Know to Start and Continue Your Digital Pathology Journey.
You’ll find the link to download it in the show notes.
See you in the episode!
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!