Send us a text

What if the biggest breakthrough in pathology AI isn’t a new algorithm—but finally sharing the data we already have?

In this episode, I’m joined by Jeroen van der Laak and Julie Boisclair from the IMI BigPicture consortium, a European public-private initiative building one of the world’s largest digital pathology image repositories. The goal isn’t to create a single AI model—but to enable thousands by making high-quality, legally compliant data accessible at scale.

We unpack what it really takes to build a 3-million-slide repository across 44 partners, why GDPR and data-sharing agreements delayed progress by 18 months, and how sustainability, trust, and collaboration are just as critical as technology. This conversation is about the unglamorous—but essential—work of building infrastructure that will shape pathology AI for decades.

⏱️ Highlights with Timestamps

• [00:00–01:40] Why BigPicture focuses on data—not algorithms
• [01:40–03:16] Scope of the project: 44 partners, 15–18 countries, 3M images
• [03:16–06:20] The 18-month delay caused by legal frameworks and GDPR
• [06:20–11:52] Extracting data from heterogeneous lab infrastructures
• [11:52–13:38] Current status: 115,000 slides uploaded and growing
• [13:38–18:39] Why LLMs and foundation models make curated data more valuable than ever
• [18:39–23:49] Industry collaboration and shared negotiating power
• [23:49–28:06] Data access models and governance after project independence
• [28:06–31:59] Sustainability plans and nonprofit foundation model
• [37:02–43:18] Tools developed: DICOMizer, artifact detection AI, image registration
  
  
  

📚 Resources from This Episode

• IMI BigPicture Consortium
• GDPR & Data Sharing Agreements (DSA)
• DICOMizer & SEND metadata tools
• Artifact detection AI for slide QC
• European AI Factories initiative

Support the show

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

Send us a text

What if the biggest transformation in digital pathology this year had nothing to do with new hardware—and everything to do with how we think about value, workflow, and readiness?

In this year-end recap livestream from the 11th Digital Pathology & AI Congress in London, I break down what truly mattered in 2025. Instead of focusing on buzzwords or hype cycles, this episode highlights the practical advances shaping diagnostics, patient care, and drug development—and the mindset shift our field must embrace to move forward.

Digital pathology is no longer “early adoption.” It’s becoming essential infrastructure. And yet the biggest barrier isn’t scanners or algorithms—it’s the knowledge and confidence needed to use them well.

Key Highlights & Timestamps

0:00 — Setting the Stage from London

An overview of the forces that shaped digital pathology in 2025: workflow integration, clinical readiness, and the move from theory to operational reality.

1:45 — Leica’s Expanded Portfolio & FDA-Cleared Collaborations

A look at Leica’s updated scanner lineup and co-developed, FDA-cleared solutions with Indicollabs. These launches reflect a broader industry trend toward highly specialized, clinically validated digital tools designed for end-to-end workflows.

4:12 — The Acceleration of Companion Diagnostics

From Artera’s de novo–approved prostate prognostic test to AstraZeneca’s TROP2 scoring efforts, 2025 pushed computational pathology directly into therapeutic decision-making.

6:20 — Why Workflow Integration Became the Theme of 2025

Partnerships like BioCare + Hamamatsu + Visgen and Zeiss + MindPeak show where the field is heading: full-stack solutions, not isolated tools. Labs want interoperability, reliability, and simplified digital workflows.

9:10 — Adoption Challenges: ROI, Education & AI Uncertainty

We explore the realities slowing digital transformation:
– ROI is real, but requires workflow change
– AI anxiety persists among clinicians and patients
– Education is still the strongest driver of adoption

12:00 — 2025’s Innovation Highlights

Breakthroughs shaping the next phase of digital pathology include:
– emerging agentic AI platforms
– voice-enabled image management systems
– improved multiplexing technologies like Hamamatsu’s Moxiplex

15:40 — The Growing Intersection of Pathology & Genomics

AI models predicting genomic alterations from H&E images gained traction, especially for cases with minimal tissue. Tempus acquiring Paige signals the deepening connection between digital workflows and molecular data.

18:30 — What 2026 Will Require

Priorities for the coming year include:
– building agentic AI solutions capable of real workflow orchestration
– strengthening validation and QC
– sharing real-world deployment case studies
– expanding training and hands-on learning

RESOURCES:

1. The Lucerne Toolbox 3: digital health and artificial intelligence to optimise the patient journey in early breast cancer-a multidisciplinary consensus

2. Artificial intelligence (AI) molecular analysis tool assists in rapid treatment decision in lung cancer: a case report

Support the show

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

Send us a text

Have you ever thought, “Digital pathology sounds amazing, but without a scanner, what’s the point of learning it now?”
If so, this episode will change how you see your role in the future of pathology.

In this talk, I challenge one of the most persistent myths in our field: the belief that you need expensive hardware before you can begin your digital pathology journey. Through personal experience and the remarkable story of another pathologist who started with even less, I show why knowledge—not infrastructure—is what truly opens doors.

Highlights and Key Themes

0:00 – The Limiting Belief

I open with the core misconception I hear from pathologists worldwide: “I need a scanner before I can start.” I explain why hesitation, not lack of equipment, is the real barrier—and why waiting for perfect conditions keeps many people stuck.

2:24 – My Early Digital Pathology Story

I describe my residency in 2013, when a single scanner was “off limits” to trainees. Faced with a research project requiring consistent cell counting, I improvised using a microscope camera and Microsoft Paint.
It wasn’t sophisticated, but it was digital, consistent, and reproducible.
This experience taught me a foundational lesson: if you can measure something, measure it; don’t rely on visual estimation.

7:01 – How This Led to My First Digital Pathology Job

That basic Paint-and-dots project became my gateway to working at Definiens (now part of AstraZeneca).
I wasn’t hired for computational expertise; I was hired because I understood tissue, biology, and the value of quantifying what we see. Working alongside image analysis scientists showed me the exponential power of combining tissue knowledge with computational tools.

10:03 – Dr. Tala Zafar’s Story

I share the inspiring journey of Dr. Tala Zafar from Karachi, Pakistan, who began with no access to scanners and only a microscope camera.
During COVID shutdowns, she taught herself the foundations of digital pathology, joined global organizations, conducted a nationwide survey, and contacted AI vendors for access to platforms.
After many rejections, one vendor offered a trial account. In just six weeks, she completed three AI projects using microscope camera images—each one published in a peer-reviewed journal.
Her story highlights a universal truth: starting with curiosity and persistence matters far more than having perfect tools.

14:14 – Two Paths After a Conference

I explain the difference between the “forgetting loop” and the “learning path.”
Many attendees leave inspired but slip back into routine. Others commit to one consistent learning habit—journal clubs, vendor webinars, DigiPath Digest sessions—and return a year later with clarity, confidence, and momentum. These individuals become the people others seek out for guidance in digital pathology.

18:04 – Where to Begin

You don’t need a scanner or an institutional budget to start. What you need is structured knowledge.
I introduce my book, Digital Pathology One on One, and encourage listeners to choose one learning habit to build on after the episode. The only wrong choice is choosing nothing.

19:06 – Final Message

Knowledge drives adoption, not infrastructure.
Scanners, AI tools, and computational platforms already exist. What’s missing are people who understand how to interpret tissue digitally, collaborate with computational teams, and bridge biology with technology.
You have

Support the show

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

Send us a text

What happens when AI becomes powerful enough to diagnose—not just one disease, but entire fields of medicine at once?
In this episode of DigiPath Digest #33, I break down four new PubMed abstracts shaping the future of digital pathology, clinical AI integration, federated learning, and multidisciplinary cancer care. Across every study, one message is clear: AI is accelerating, but human oversight defines its safe adoption.

Below are the full timestamps, key insights, and referenced research to help you explore each topic more deeply.

TIMESTAMPS & HIGHLIGHTS

0:00 — Welcome & Opening Question
How far can AI safely scale across medicine—and where must humans stay in control?

4:10 — AI in Forensic Medicine: Accuracy Meets Ethical Limits

Based on a systematic review, we discuss:

• AI advances in personal identification, pathology, toxicology, radiology, anthropology.
  
  
  
• Benefits: reduced diagnostic error, faster case resolution.
  
  
  
• Challenges: data diversity gaps, limited validation, lack of ethical frameworks.
  📌 Source: PubMed abstract on AI in forensic disciplines
  
  
  

10:55 — Confocal Endomicroscopy + AI for Pancreatic Cysts

Researchers trained a deep model on 291,045 endomicroscopy frames to detect papillary and vascular structures in IPMNs:

• 70% faster review time
  
  
  
• More consistent structure identification
  
  
  
• A step toward scalable “optical biopsy” workflows
  📌 Source: IPMN / confocal endomicroscopy AI abstract
  
  
  

16:40 — Federated Learning in Computational Pathology

A comprehensive review of FL for:

• Tissue segmentation
  
  
  
• Whole-slide image classification
  
  
  
• Clinical outcome prediction
  Key takeaway: FL can match or outperform centralized training—without sharing patient data—yet still struggles with heterogeneity, interoperability, and standardization.
  📌 Source: Federated learning review
  
  
  

22:15 — The Lucerne Toolbox 3: A Digital Health Roadmap for Early Breast Cancer

A global consortium of 112 experts identified 15 high-impact knowledge gaps and proposed 13 trial designs to integrate AI across early breast cancer care:

• AI-based mammography screening
  
  
  
• Personalized screening strategies
  
  
  
• Digital knowledge databases
  
  
  
• AI-driven treatment optimization
  
  
  
• Digitally delivered follow-up & supportive care
  📌 Source: The Lucerne Toolbox 3 (Lancet Oncology)
  
  
  

28:50 — Big Picture: AI Expands What’s Possible—but Humans Define What’s Acceptable

We close with the essential takeaway echoed across all four publications:
AI is getting smarter, faster, and more integrated—but clinical responsibility, validation, transparency, and multidisciplinary alignment remain irreplaceable.

1. Confocal Endomicroscopy + AI for IPMN — hi

Support the show

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

Send us a text

Why does it take three years to deploy a digital pathology tool that only took three weeks to build? That’s the reality no one talks about—but every lab feels every time they deploy a new tool...

In this episode, I sit down with Andrew Janowczyk, Assistant Professor at Emory University and one of the leading voices in computational pathology, to unpack the practical, messy, real-world truth behind deploying, validating, and accrediting digital pathology tools in the clinic.

We walk through Andrew’s experience building and implementing an H. pylori detection algorithm at Geneva University Hospital—a project that exposed every hidden challenge in the transition from research to a clinical-grade tool.

From algorithmic hardening, multidisciplinary roles, usability studies, and ISO 15189 accreditation, to the constant tug-of-war between research ambition and clinical reality… this conversation is a roadmap for anyone building digital tools that actually need to work in practice.

Episode Highlights

• [00:00–04:20] Why multidisciplinary collaboration is the non-negotiable cornerstone of clinical digital pathology deployment
• [04:20–08:30] Real-world insight: The H. pylori detection tool and how it surfaces “top 20” likely regions for pathologist review
• [08:30–12:50] The painful truth: Algorithms take weeks to build—but years to deploy, validate, and accredit
• [12:50–17:40] Why curated research datasets fail in the real world (and how to fix it with unbiased data collection)
• [17:40–23:00] Algorithmic hardening: turning fragile research code into production-ready clinical software
• [23:00–28:10] Why every hospital is a snowflake: no standard workflows, no copy-paste deployments
• [28:10–33:00] The 12 validation and accreditation roles every lab needs to define (EP, DE, QE, IT, etc.)
• [33:00–38:15] Validation vs. accreditation—what they are, how they differ, and when each matters
• [38:15–43:40] Version locking, drift prevention, and why monitoring is as important as deployment
• [43:40–48:55] Deskilling concerns: how AI changes perception and what pathologists need before adoption
• [48:55–55:00] Usability testing: why naive users reveal the truth about your UI
• [55:00–61:00] Scaling to dozens of algorithms: bottlenecks, documentation, and the future of clinical digital pathology and AI workflows
  
  

Resources From This Episode

• Janowczyk & Ferrari: Guide to Deploying Clinical Digital Pathology Tools (discussed)
• Sectra Image Management System (IMS)
• Endoscopist deskilling risk after exposure to artificial intelligence in colonoscopy: a multicentre, observational study - PubMed
• Digital Pathology 101 (Aleksandra Zuraw)
  
  

Key Takeaways

• Algorithm creation is the easy part—deployment is the mountain.
• Clinical algorithms require multidisciplinary ownership across 12 institutional roles.
• Real-world data is messy—and that’s exactly why algorithms must be trained on it.
• No two hospitals are alike; every deployment requires local adaptation.
• Usability matters as much as accuracy—naive users expose real workflow constraints.
• Patho

Support the show

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

Send us a text

Why are billions of people still invisible in genomic research—and what does that mean for the future of precision medicine?

In this episode, I sit down with Victor Angel Mosti, founder and CEO of Omica.Ai, for one of the most insightful conversations I’ve recorded about data equity and building ethical, community-centered AI.

Victor shares not only his personal cancer story but also the staggering truth: Hispanic and Latino populations make up less than 1% of genomic datasets. This underrepresentation isn’t just a data gap—it’s a clinical risk.

We dive into disparities between healthcare systems, the promise of digital pathology as a low-cost entry point, the dangers of “parachute science,” and how Victor is building a living, ethical, transparent biobank through Omica. AI—built for true precision medicine rooted in community trust.

Highlights with Timestamps

• [00:00–01:40] Personal cancer experiences and diagnostic uncertainty
• [01:40–06:50] Victor’s medical journey across Mexico and the U.S.
• [06:50–11:42] The digitization gap: empathy vs. tech
• [11:42–16:43] The “coffee diversity” metaphor for genomic diversity
• [16:43–19:34] Funding disparities & the biotech cold-start problem
• [19:34–25:44] Digital pathology as a gateway to precision medicine
• [25:44–31:44] Avoiding “parachute science” and building community-first research
• [31:44–36:05] The Nagoya Protocol and benefit-sharing
• [36:05–41:47] Omica.Ai’s work, goals, and clinical-embedded approach
• [41:47–49:36] Creating future-proof, embedded biobanks
• [49:36–53:35] Blockchain for transparency and patient trust
• [53:35–54:39] Victor’s call to action: collaborate, include, and stay human
  
  

Resources from This Episode

• Omica.Ai – Community-driven precision medicine platform
• Nagoya Protocol – Framework for equitable biological use
  
  

Key Insights

• Cancer is personal—even for experts
• <1% representation of Latino genomes threatens clinical accuracy
• Digital pathology + AI can leapfrog infrastructure gaps
• Ethical biobanking requires trust, transparency, and local benefit
• Avoiding “parachute science” is essential
• Genetic diversity drives discovery—but only if we capture it
• Blockchain + dynamic consent = future of patient-centered data
  
  

Support the show

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

Send us a text

How far can AI go in helping us diagnose disease—without losing the human judgment patients rely on?

In this episode, I break down four studies shaping the future of digital pathology, oncology, and neurology. From spatial biology updates at SITC to voice-based Alzheimer’s detection, deep learning for sarcoma prognosis, and new guidelines for safe AI deployment, this week’s digest highlights where AI is making a real impact—and where caution still matters.

Episode Highlights

1️⃣ SITC Trends & Spatial Biology (00:00 → 07:40)

I share key updates from SITC 2025, including the growing role of multiplex immunofluorescence (mIF) and the need for integrated staining-to-scanning workflows. I also preview new educational content and upcoming podcast guests in global AI research.

2️⃣ Digital Neuropathology & Alzheimer’s (07:40 → 13:01)

A major review confirms that digital neuropathology is now robust enough for large-scale Alzheimer’s studies—opening doors for computational tools to link histology with cognition.

3️⃣ Patient Safety in AI (13:01 → 19:56)

An Italian review underscores the foundations of trustworthy AI: dataset quality, transparency, oversight, and continuous validation. I discuss why “patient-centered AI” must remain our standard.

4️⃣ Voice Biomarkers for Cognitive Decline (19:56 → 26:43)

AI models analyzing short speech recordings are showing high accuracy for early Alzheimer’s detection. This could make future screening simple, noninvasive, and more accessible.

5️⃣ Deep Learning for Sarcoma Prognosis (34:06 → 35:59)

A multi-instance CNN outperforms FNCLCC grading by identifying prognostic patterns in tumor center and periphery regions, offering new insights into soft-tissue sarcoma biology.

Takeaways

• mIF is maturing quickly but needs standardized, end-to-end workflows.
• Digital neuropathology is ready for broader Alzheimer’s research.
• Safe AI requires multidisciplinary collaboration and rigorous validation.
• Voice biomarkers may become powerful tools for early cognitive assessment.
• Deep learning can refine prognosis and reveal hidden tumor patterns.

Resources

Hamamatsu (MoxiePlex) • Biocare Medical (ONCORE Pro X) • SITC Programs • Recent publications on AI biomarkers and computational pathology.

Thanks for listening—and for being part of this growing digital pathology community.

Support the show

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

Send us a text

If your pathology reports and other data could talk, what would they say about the future of precision medicine? The truth is, most labs already have the data—they’re just not having a conversation with it.

In this episode, I talk with Peter O’Toole, President and Chief Software Architect at mTuitive. We recorded live at Pathology Visions and are covering the power of structured data and how it’s redefining the future of pathology reporting, AI, and clinical decision support.

We explore how structured reporting evolved from checklists to intelligence, why data hygiene and workflow integration matter more than AI buzzwords, and how collaboration across companies like mTuitive is helping labs turn their reports into clinically actionable data.

Highlights with Timestamps

• [00:00–05:40] Data as the new currency in pathology — Why structured data is the foundation for clinical, research, and trial insights.
• [05:40–10:30] AI & Large Language Models (LLMs) — What AI can (and can’t) do when your data isn’t structured.
• [10:30–19:25] AI workflow integration & voice recognition — How AI and structured reporting work together inside the LIS and IMS.
• [19:25–25:27] Overcoming resistance — Why pathologists initially resisted structured reports and how perceptions are shifting globally.
• [25:27–29:53] Decision support & beyond cancer — Expanding structured data to liver, skin, and even mental health pathology.
• [29:53–34:15] Collaboration as the catalyst — How partnerships create seamless ecosystems for pathology data.
• [34:15–37:03] Demo: Synoptic reporting in action — Real-time staging, automation, and compliance made easy.
  
  

Resources from this Episode

• mTuitive website: https://mtuitive.com
• CAP Synoptic Reporting Protocols – Standardized templates for structured pathology reports.
• Pathology Visions Conference 2025 – Event where this discussion took place.
  
  

Key Takeaways

✅ Structured reporting transforms pathology data from static text into actionable intelligence.
✅ AI and LLMs complement structured data—but can’t replace its clinical readiness.
✅ Clean data in = clean data out—data hygiene defines AI reliability and efficiency.
✅ Workflow integration and user-friendly design drive real-world adoption.
✅ Structured data unlocks clinical trials access, research potential, and decision support tools.
✅ Collaboration is key to building the connected ecosystem pathology needs.

Support the show

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