Digital Pathology Podcast

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 Ingied 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.
Ingred 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!

Send a text
Is AI in pathology actually improving diagnosis — or just adding complexity?
In DigiPath Digest #37, we reviewed four recent publications covering AI-based biomarker quantification in glioblastoma, real-world digital workflow integration in prostate cancer, multimodal AI combining histopathology and genomics, and patient perspectives on AI in cancer diagnostics.
This episode connects technical performance with something equally important: trust.
Episode Highlights
[00:02] Community & updates
Digital Pathology 101 free PDF, upcoming patient-focused book, and global attendance.
[04:07] AI-based image analysis in glioblastoma
AI showed strong consistency with pathologists when quantifying Ki-67, P53, and PHH3.
Significant biological correlations (Ki-67 ↔ PHH3, PHH3 ↔ P53) were detected by AI — not by manual assessment.
Takeaway: computational quantification improves precision.
[09:28] Real-world digital workflow + AI in prostate cancer (France)
AI-pathologist concordance:
• 93.2% (high probability cancer detection)
• 99.0% (low probability slides)
Gleason concordance: 76.6%
10% failure rate due to pre-analytical artifacts.
Takeaway: infrastructure and sample quality still matter.
[15:58] Multimodal AI (MARBIX framework)
Combines whole slide images + immunogenomic data in a shared latent space using binary “monograms.”
Performance in lung cancer: 85–89% vs 69–76% unimodal models.
Takeaway: integrated data improves case retrieval and similarity reasoning.
[22:13] AI-powered paper summary subscription introduced
Structured summaries for busy professionals who want more than abstracts.
[26:17] Patient roundtable on AI in pathology (Belgium)
Patients expect:
• Better accuracy
• Faster turnaround
• Stronger collaboration
Trust is high when:
 • Algorithms use diverse datasets
 • Pathologists retain final responsibility
Clinical validity mattered more than full algorithm transparency.
 Privacy concerns focused more on insurer misuse than cloud transfer.
Key Takeaways
AI improves biomarker precision in glioblastoma.
Digital pathology implementation works — but pre-analytics can limit AI performance.
Multimodal AI represents the next meaningful step in precision diagnostics.
Patients are not afraid of AI — they want validation, oversight, and governance.
Human–AI collaboration remains central.
If you’re working in digital pathology, computational pathology, or precision oncology, this episode connects evidence, implementation, and patient perspective.
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!

Send a text
What actually needs to be in place before digital pathology can replace the microscope?
In this episode of DigiPath Digest, I walk through the 2026 Polish Society of Pathologists guidelines and translate them into practical steps for real pathology labs. This isn’t theory. It’s about hardware fidelity, data integrity, validation, and AI integration — and what each of these actually requires in daily workflow.
We talk about scanner resolution standards (≤0.26 μm per pixel), 4K monitor calibration, visually lossless compression (20:1), scalable storage, pathologist-driven validation, and what “non-inferiority” truly means.
Digital pathology is not just a change of medium. It’s an operational shift.
Episode Highlights
[00:02] Community & growth
1,600+ new newsletter subscribers, 10,000+ Facebook members, and free Digital Pathology 101 book access.
[07:20] The 4 pillars of adoption
Hardware fidelity · Data integrity · Clinical validation · Future integration.
[08:30] Hardware requirements
40x equivalent scanning (≤0.26 μm/px), 4K monitors, >300 cd/m² luminance, 10-bit color depth.
[12:00] Workflow & throughput
200–300 slides/day per scanner, automated focus control, urgent case prioritization.
[17:25] Storage & archiving
~1 GB per slide. Active archive (6–24 months). Long-term retention (10–20 years). GDPR compliance & TLS encryption.
[23:09] Validation philosophy
Pathologist-centered validation.
Two phases:
• Familiarization (~20 retrospective cases)
• Dual review with discrepancy tracking
Goal: digital must be non-inferior to glass.
[29:03] AI in digital pathology
AI supports quantification (Ki-67, HER2, ER/PR, PD-L1), tumor detection, and future multimodal predictions — but pathologists remain central.
[33:26] Intraoperative telepathology
<5-minute scan-to-view time.
Minimum 100 Mbps upload.
Redundancy and safety protocols required.
[34:50] Can digital cameras replace scanners?
Hybrid workflows exist. Regulatory compliance still applies.
[38:19] Adoption checklist summary
Certified scanners (CE-IVD/FDA), calibrated monitors, scalable storage, phased validation, and documented QC.
Key Takeaways
Digital pathology adoption is a structured process — not just buying a scanner.
Validation is individualized and tissue-specific.
Infrastructure and quality control are as important as image quality.
AI enhances reproducibility and quantification but does not replace pathologists.
Regulatory compliance and data governance are non-negotiable.
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!

Send a text
This session is a practical walkthrough of where digital pathology and AI truly stand in early 2026—based on five recent PubMed papers and real-world implementation experience.
In this episode, I review new clinical adoption guidelines, AI applications in liver cancer imaging and pathology, AI-ready metadata for whole slide images, non-destructive tissue quality control from H&E slides, and machine learning–assisted IHC scoring in precision oncology.
This conversation is not about hype. It’s about standards, validation, data integrity, and clinical translation—the factors that decide whether AI tools stay in research or reach patient care.
Episode Highlights
01:21 – Practical digital pathology adoption guidelines (Polish Society of Pathologists)
08:05 – AI in liver cancer imaging & pathology, and why framework alignment matters
18:10 – AI-generated tissue maps as metadata for WSI archives
23:01 – PathQC: predicting RNA integrity and autolysis from H&E slides
32:14 – ML-assisted IHC scoring in genitourinary cancers
29:42 – Digital Pathology 101 book + community updates
Key Takeaways
Digital pathology adoption still requires clear standards and validation workflows
AI performs best when aligned with existing diagnostic frameworks (e.g., LI-RADS)
Metadata extraction is a low-effort, high-impact AI use case
Slide-based quality control can support biobanking and biomarker research
Automated IHC scoring improves consistency—but adoption remains uneven globally
Resources Mentioned 
Digital Pathology 101 (free PDF & audiobook)
Publication Links:  a. https://pubmed.ncbi.nlm.nih.gov/41618426/                                                                 b. https://pubmed.ncbi.nlm.nih.gov/41616271/                                                                   c. https://pubmed.ncbi.nlm.nih.gov/41610818/                                                                 d. https://pubmed.ncbi.nlm.nih.gov/41595938/                                                                 e. https://pubmed.ncbi.nlm.nih.gov/41590351/ 
Support the show
Get the "Digital Pathology 101" FREE E-book and join us!