Send us a text

Can one AI system learn from every organ — and teach us something new about all of them?

In this edition of DigiPath Digest #31, I explore how artificial intelligence is transforming pathology across multiple organ systems, revealing connections that help us diagnose faster, more consistently, and more accurately than ever before.

From glomerulonephritis to hepatocellular carcinoma, AI is no longer confined to a single specialty — it’s becoming the connective tissue between them.

What’s Inside:

1️⃣ AI for Bladder Cancer Classification
We begin with a multicenter study validating AI models for urothelial neoplasm classification using over 12,000 whole-slide images. Both CNNs and transformer models achieved high accuracy (AUC 0.983, F1 score 0.9). I discuss why the F1 score matters — and what it tells us about model balance between sensitivity and specificity.

2️⃣ AI in Colorectal Cancer Care
Next, we explore multimodal AI — integrating histopathology, radiology, genomics, and blood markers to modernize colorectal cancer workflows. AI now helps detect adenomas, infer microsatellite instability (MSI) from H&E slides, and predict treatment outcomes. I highlight the critical need for external validation, interpretability, and governance as AI enters clinical use.

3️⃣ AI for Glomerular Nephritis Diagnosis
A deep learning model trained on over 100,000 kidney biopsy images identified four nephritis types — FSGS, IgA, MN, and MCD — with over 85% accuracy. This technology could ease workloads and improve turnaround time in renal pathology. Still, I share why AI support may feel both empowering and unsettling for many pathologists.

4️⃣ AI in Liver Disease (MASLD & HCC)
AI is advancing noninvasive fibrosis staging and risk prediction in liver pathology. From large consortia like NIMBLE and LITMUS to predictive models for HCC therapy response, AI is moving us closer to precision hepatology. I also discuss the challenge of translating these tools from research to regulatory approval.

5️⃣ Lightweight AI for Domain Generalization
Finally, we look at one of pathology AI’s biggest challenges: domain shift — when a model trained on one scanner or staining style performs poorly elsewhere. The new Histolite framework shows how lightweight, self-supervised models can generalize across data sources — trading some accuracy for reliability in real-world use.

My Takeaway

Across every study, a single message stands out:
AI isn’t replacing pathologists — it’s amplifying our vision.
By connecting kidney, colon, liver, and bladder insights, AI is teaching us that medicine works best when it learns across boundaries.

Episode Highlights

• Bladder cancer AI validation (06:41)
• Multimodal colorectal AI (12:38)
• Glomerular nephritis deep learning (19:29)
• AI in liver pathology (29:55)
• Domain shift & Histolite framework (38:17)
• Halloween wrap-up + SITC preview (46:18)

Join me next time for updates from the SITC 2025 Conference, where I’ll be live at Booth 415 with Hamamatsu and Biocare, discussing how AI and spatial biology are converging to drive clinical utility.

#DigitalPathology #AIinHealthcare #ComputationalPathology #CancerDiagnostics #LiverPathology #RenalPathology #FutureOfMedicine #DigiPathDigest

Support the show

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

Send us a text

If artificial intelligence can match—or even surpass—our diagnostic accuracy, what happens to the role of the pathologist?

That’s the question I explore in this episode of DigiPath Digest #30, where I break down three fascinating papers showing how AI is changing the way we diagnose, classify, and predict outcomes in renal transplant biopsies, thyroid cytology, and gastrointestinal cancers.

These studies don’t just prove AI’s potential—they reveal what it means for us, the humans behind the microscope.

Study 1 — Renal Transplant Biopsies: Precision in Every Pixel

A Japanese team examined how deep neural networks and large language models improve diagnostic consistency in renal transplant pathology.

They highlighted how the Banff Digital Pathology Working Group is retraining AI models alongside updated Banff classifications—creating a dynamic feedback loop between human expertise and machine learning.

In the U.S., over ten digital pathology systems are now FDA-cleared for primary diagnosis, showing that AI can support both accuracy and accountability. It’s not replacing us—it’s working with us.

Study 2 — Thyroid Cytology: From Overdiagnosis to Optimization

As someone who’s personally experienced thyroid cancer, this study hit close to home.

Researchers in China developed AI-TFNA, a multimodal system that combines whole-slide images and BRAF mutation data from over 20,000 thyroid fine-needle aspirations across seven centers.

The model achieved 93% accuracy, reducing unnecessary surgeries and improving clinical decisions. What’s especially impressive is Image Appearance Migration (IAM)—a technique that helps AI adapt across scanners and labs, ensuring reliable performance worldwide.

Study 3 — GI Cancer: Prognosis Reimagined

An international collaboration of over 2,400 patients introduced a Deep Learning Pathomics Signature (DLPS) that merges nuclear features, tumor microenvironment, and spatial single-cell data.

This AI-driven model predicted patient survival and therapy response more accurately than traditional TNM staging—even identifying which patients are most likely to benefit from chemotherapy or immunotherapy.

It’s precision medicine powered by pathology.

Reflections:

Each of these studies made me think about the balance between trust and technology. We’ve reached a point where AI can truly enhance diagnostic precision—but it also challenges us to stay actively engaged, curious, and informed.

Because the real risk isn’t that AI will outperform us—it’s that we’ll stop thinking critically once it does.

That’s why collaboration between pathologists, data scientists, and industry innovators matters more than ever.

AI isn’t replacing us—it’s redefining what excellence looks like in pathology.

#DigitalPathology #AIinHealthcare #ComputationalPathology #RenalPathology #ThyroidCytology #CancerDiagnostics #DigiPathDigest

Support the show

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

Send us a text

Live from Pathology Visions 2025 in San Diego, I share highlights from Day 2 of the world’s leading digital pathology conference, where experts explored how AI, empathy, and training are shaping the next generation of pathologists.

This episode captures the shift from technology as a tool to technology as a bridge — helping us connect with patients in more meaningful ways.

What I Talk About

1️⃣ From Pixels to Patients
We’ve built the infrastructure; now it’s about applying it. Pathology is no longer just digital — it’s personal, accessible, and human-centered.

2️⃣ Dr. Leah Lijah Joseph’s Keynote — Pathologists as Patients
Dr. Joseph, a cancer pathologist and survivor, shared her journey from diagnosing others to understanding her own slides. She now runs a patient pathology clinic, empowering people to see and learn from their own tissue samples.

3️⃣ The Power of Visualization
Dr. Joseph described how visualization and mental imagery support healing — a reminder that empathy and imagination can coexist with precision science.

4️⃣ AI & Imaging Innovation
From Google Research’s JPEG AXL format reducing file size by 30%, to discussions on color fidelity with DICOM’s David Clooney, we explored how innovation and accuracy must move hand-in-hand.

5️⃣ Cytology Goes Digital
With Hologic’s Genius Digital Diagnostic and AIXMed’s AI-assisted QC, cytology is entering a new era — faster, more accurate, and fully traceable through 100% AI quality control.

6️⃣ The Human Side of AI
I also share a personal story about my mother’s medical experience — and how even with all the tech, empathy remains the missing link. AI can’t replace compassion, but it can help us focus on it by automating what takes time away from patients.

Key Takeaways

• AI is enhancing accuracy and accessibility in diagnostics.
• Pathologists are taking on more patient-facing roles.
• Cytology digitization is revolutionizing quality and speed.
• Innovation must balance efficiency with color and data integrity.
• Empathy and communication will always define great medicine.

I hope this episode helps you see how AI, empathy, and education are shaping the next era of diagnostics.

Let’s continue building the bridge from pixels to patients, one slide at a time. 💡

#PathVision25

Support the show

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

Send us a text

Live from Pathology Visions 2025 in beautiful San Diego, I sat down with Imogen Fitt from Signify Research to explore how AI, digital pathology, and interoperability are transforming the way we diagnose cancer and deliver patient care.

The conference theme, “From Pixels to Patients,” perfectly captures this year’s shift — from theoretical discussions about AI to real-world implementation and measurable outcomes.

We’re no longer just asking “what can AI do?” — we’re seeing how it’s actually improving accuracy, reducing barriers, and connecting pathologists and labs worldwide.

What We Discuss

1️⃣ From Hype to Application
This year, the buzz wasn’t about AI’s potential — it was about how it’s being used. We highlight case studies showing how digital tools are reducing diagnostic errors, improving collaboration, and even helping smaller labs digitize faster and more affordably.

2️⃣ PathPresenter’s Expanding Role
We dive into PathPresenter’s innovative model that gives users access to digital pathology at no initial cost, opening the door for over 75,000 professionals across 62 institutions. I share why I personally use PathPresenter for teaching and how it’s helping lower the barrier to entry for education, consultations, and patient care.

3️⃣ New Scanning Technology and Accessibility
We talk about compact scanners like Grundium’s four-slide scanner and new miniature models that make digitization possible even in smaller labs. The message is clear: you don’t need a massive system to start going digital.

4️⃣ Collaboration and AI in Action
Imogen shares updates from across Europe and Asia, including how hospitals are tackling storage, AI regulation, and workflow efficiency. We discuss emerging partnerships—Fujifilm, Voicebrook, Dolby, and others—that are making voice dictation, chat agents, and real-time AI insights part of the modern pathology cockpit.

5️⃣ The Human Side of AI Adoption
We also reflect on how digital pathology is changing careers and training. Younger pathologists expect digital tools as part of their workflow — and many won’t settle for less. We discuss how this new generation is driving adoption and pushing institutions to modernize.

My Reflections

I still remember when digital pathology felt intimidating — when only a few people were “allowed” to touch the scanner. But today, that’s changed completely.

Now, we’re living in an era where AI and digital pathology are not optional — they’re essential. The technology has matured, and so has the mindset around it. What excites me most is seeing how collaboration and accessibility are becoming central to innovation.

Key Takeaways

• AI in pathology is moving from hype to practice — focused on improving patient outcomes.
• Accessibility matters: smaller, affordable scanners and open platforms are democratizing digital pathology.
• Collaboration between vendors, clinicians, and technologists is key to faster, smoother adoption.
• The next generation of pathologists expects — and demands — a digital-first workflow.

Listen Now to Learn:

• How AI is reshaping cancer diagnosis
• The tools driving real change in labs today
• How collaboration fuels digital transformation in pathology

Support the show

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

Send us a text

Will AI make doctors and specialists less skilled—or even replace them?

That’s the question I explore in this episode of DigiPath Digest #29. As someone working where AI meets digital pathology, I’m both excited and cautious about how automation shapes our skills and professional identity.

In this episode, I discuss two studies that ask tough questions about AI, expertise, and the future of medicine.

What I Talk About:

1️⃣ Endoscopist Deskilling After AI Exposure (Lancet, 2025)
A multicenter Polish study found that after frequent AI-assisted colonoscopy use, endoscopists’ adenoma detection rate dropped by ~6% when performing procedures without AI. It suggests overreliance on automation can subtly dull vigilance.

It reminded me of how we depend on GPS instead of remembering routes—or how driving an automatic car changes focus. Could medicine be facing a similar shift?

2️⃣ “Will My Expertise Be Devalued by Machines?” (Bangladesh, 2024)
Healthcare professionals shared concerns about:

• Job security and evolving roles 💼
• Ethics, accountability, and trust ⚖️
• Losing the human touch ❤️
• The need for AI training and oversight 📚

AI adoption isn’t just technical—it’s behavioral, cultural, and deeply human.

My Take:

I see AI as a partner, not a threat. I use it every day for research and content, but I never outsource judgment. AI can boost efficiency—but only if we stay curious, critical, and engaged.

We can’t let convenience replace competence. AI should augment our expertise, not erode it.

🌍 PathVision 2025 — Sept 5–7, 2025

I’m also thrilled to share that I’ll be livestreaming PathVision 2025 from September 5–7, 2025, on LinkedIn and YouTube! 🎥

This year’s conference is packed with innovations in AI, digital pathology, and cancer diagnostics. I’ll bring you live insights, interviews, and key takeaways from the sessions—so mark your calendars and tune in!

🧩 Key Takeaways

• Continuous AI use may lower independent performance.
• Professionals worry about trust, ethics, and losing skill.
• The goal isn’t to resist AI—but to use it critically and consciously.
• The best outcomes happen when AI and human expertise work together.

🕒 Episode Highlights

• 00:00–06:14 | Welcome & PathVision preview
• 06:14–17:46 | AI deskilling question
• 08:27–14:05 | Colonoscopy study results
• 27:11–38:10 | Healthcare workers’ AI concerns
• 43:59–51:05 | Reflections & responsible AI use
• 51:05–52:55 | Closing thoughts + PathVision invite

🧭 Mentioned

• Lancet Gastroenterology & Hepatology (2025): “Endoscopist deskilling risk after AI exposure”
• Bangladesh Study (2024): “Will my training be devalued by machines?”
• My Book: Digital Pathology 101 (Updated Edition Coming Soon)
• Event: PathVision 2025 – Sept 5–7, 2025 (Streaming Live!)

Thanks for listening to DigiPath Digest #29! I hope it inspires you to think critically about how we can embrace AI without losing what makes us human.

And don’t miss PathVision 2025 (Sept 5–7, 2025)—I’ll be streaming it live for three days of insights, innovation, and community. Let’s keep learning and leading the future of digital pathology tog

Support the show

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

Send us a text

What if climbing the digital pathology “mountain” isn’t about reaching the summit alone—but knowing where base camp is, and who you bring with you?

In this episode, I take you inside the Digital Diagnostic Summit in Park City, hosted by Lumea, where fewer than 100 digital pathology leaders gathered to share their journeys, challenges, and solutions.

From resilient metaphors of Everest climbs to practical strategies for workflow ownership, clinical trials, and AI-powered biomarkers, this summit showed that the future of diagnostics is built on collaboration, purpose-driven adoption, and trust in data custodianship.

🔑 Highlights with Timestamps

• [00:03–01:49] Summit kickoff – “Climbing the Digital Pathology Mountain” theme and why this summit feels different.
• [01:49–03:38] Everest keynote – lessons in resilience and why failure is part of innovation.
• [03:38–06:02] Collaboration over competition – why base camp is as important as the summit.
• [06:02–09:18] Workflow ownership – defining value-driven outcomes before choosing tools.
• [09:18–11:35] Data custodianship – protecting patient privacy while enabling ethical research.
• [11:35–15:16] Panel insights – choosing digital tools that integrate into workflows and prevent burnout.
• [15:16–17:31] Horseback networking – why informal conversations matter as much as panels.
• [17:31–19:18] Emerging health tech – 3D printing prosthetics and synthetic blood innovations.
• [19:18–23:54] Personalized biomarkers – outcome-driven diagnostics that move beyond human scoring.
• [23:54–29:16] Digital pathology in trials – Aperture platform launch and patient stratification in global studies.
• [29:16–31:42] Community impact – stories of career transformation and remote adoption.
• [31:42–32:37] Closing thoughts – why intimate summits accelerate adoption and what’s next.

📚 Resources from this Episode

• FDA Journal of Pathology & Informatics – Research on data custodianship and ethical use.
• Proscia Aperture Platform – New tool for clinical trial management and patient identification.
• Astro Zenica Digital Biomarker – Personalized biomarker validated by outcomes.
• Barco Healthcare White Paper – Why display quality matters in pathology.

.

✨ Key Insights from the Summit

✔ Success in digital pathology is not about scaling alone—partnerships matter.
✔ Labs must own their workflows and define outcomes before adopting tools.
✔ Data custodianship is central for protecting privacy while advancing research.
✔ Personalized biomarkers are shifting diagnostics toward outcome-driven AI.
✔ Clinical trials benefit from digital pathology in patient selection and stratification.
✔ Intimate summits provide mentorship, collaboration, and career transformation.
✔ Exciting health tech—from synthetic blood to 3D printing—complements digital pathology innovation.

Support the show

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

Send us a text

What if up to 35% of the diagnostic color data on your pathology slides never reaches your eyes—just because of your monitor? In this episode, sponsored by Barco, I sit down with Dr. Monika Lamba Saini (ADC Therapeutics) and Tom Kimpe (Barco) to uncover why color calibration in digital pathology isn’t optional anymore—it’s critical for diagnosis, efficiency, and AI readiness.

Highlights:

• [00:03:42] Monika’s path from CROs to biopharma and why color consistency matters in clinical trials.
• [00:09:22] What “color science” means in pathology and why color is one-third of diagnosis.
• [00:12:40] When the same tissue looks different across labs and scanners—and how this causes diagnostic conflicts.
• [00:16:19] Why HER2 scoring and IHC rely on color intensity—and how poor color fidelity lowers diagnostic confidence.
• [00:18:34] Research showing up to 35% of H&E slide colors fall outside of the sRGB color space—meaning you never see them on a standard monitor.
• [00:22:23] Where the biggest sources of color variability occur across the imaging chain come from.
• [00:26:26] Calibrated displays and pathologist speed—why confidence = faster reads.
• [00:35:19] How monitors degrade over time and why calibration is essential.
• [00:41:27] Why choosing a monitor based on price is short-sighted—and the real ROI of medical-grade displays.
• [00:43:45] ICC profiles explained: the missing piece in end-to-end color consistency.
• [00:52:48] Training pathologists on color literacy and internal calibration strategies.
• [01:00:10] How color variability affects AI algorithm accuracy—up to a 30% drop if scanners differ.
• [01:14:57] The role of professional societies in building color literacy and regulatory guidance.
• [01:22:30] Final takeaways: if you’re skeptical about calibration, here’s why you should care.

Resources from this Episode

• FDA Research by Cheng – H&E slide colors beyond sRGB Reproducible Color Gamut of Hematoxylin and Eosin Stained Images in Standard Color Space.
• Barco White Paper – The Importance of Color in Modern Pathology.
• Barco eBook – Digital Pathology: What Are The Benefits
• Barco MDPC-8127 Monitor – Medical-grade display optimized for pathology.
  
  

Digital Pathology 101 (by me, Dr. Aleksandra Zuraw) – Free PDF & Amazon print edition.

Support the show

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

Send us a text

7 Counterintuitive Secrets from NCCN’s 2025 AI in Cancer Care Summit

When the National Comprehensive Cancer Network (NCCN) gathers healthcare leaders, people listen. I attended the 2025 Policy Summit on the evolving AI landscape in cancer care—and walked away with insights that were raw, practical, and surprisingly hopeful.

Instead of hype or overpromising, cancer care leaders shared honest strategies for implementing AI responsibly and effectively. In this episode, I break down the 7 counterintuitive secrets they’re using to fast-track adoption—while others remain stuck.

Whether you’re in digital pathology, oncology, or healthcare AI, these lessons matter for your projects.

KEY HIGHLIGHTS

• 0:04 – Reporting from Washington DC: what the NCCN AI Policy Summit revealed about the real state of AI in cancer care.
• 1:10 – Why NCCN guidelines shape cancer care worldwide.
• 1:36 – Even top cancer centers struggle with AI implementation—why delays and budget overruns are common.
• 3:16 – Secret #1: Stop chasing perfect AI tools—build strategic guardrail frameworks instead.
• 6:20 – Secret #2: Plan for biological drift from day one.
• 9:29 – Secret #3: Target underutilized care areas, not your strongest programs.
• 12:07 – Secret #4: Design AI for patients receiving care, not just providers giving it.
• 16:29 – Secret #5: Follow the pioneers—don’t reinvent from scratch.
• 19:09 – Secret #6: Build flexible systems for evolving regulatory pathways.
• 22:09 – Secret #7: Stop using human-level performance as the gold standard.
• 31:23 – Why integration is now as important as innovation in AI for pathology.
• 34:31 – What’s next: NCCN will publish a report based on these discussions.

THIS EPISODE'S RESOURCES

• NCCN – National Comprehensive Cancer Network
• Episode with Dr. Lija Joseph on patient-pathologist communication
• Aeffner F. et al. – The Gold Standard Paradox in Digital Image Analysis: Manual vs Automated Scoring as Ground Truth
• Artera AI FDA de novo authorization news (August 2025)
• Maryland AI Regulation (effective October 1, 2025)

If this episode resonated with you, please share it with colleagues. Speaking the same language around digital pathology and AI implementation will help us all move forward.

🎧 Thank you for trailblazing with me. Until next time, keep trailblazing however you can.

Support the show

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