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

Why do some pathologists still hesitate to trust digital slides—even after the FDA says “yes”? Because accuracy in digital pathology isn’t just about pixels—it’s about precision, validation, and confidence.

In this episode, I talk with Dr. Keith Wharton, MD, PhD, Global Medical Director at Roche Diagnostics, about how the Roche Digital Pathology DX system earned its FDA clearance for primary diagnosis—and what that means for the field.

We explore the science and strategy behind whole slide imaging (WSI) validation, the challenges of feature recognition, the meaning of non-inferiority, and the future of interoperability and AI in diagnostic systems.

If you’ve ever wondered what it takes to make a digital system clinically equivalent to the microscope—this episode is your roadmap.

🔹 Highlights with Timestamps

• [00:00–02:30] What “primary diagnosis” really means—and how the human brain processes histopathology features.
• [02:30–06:00] How Roche achieved FDA clearance for its DP200 and DP600 scanners—and why it’s “clearance,” not “approval.”
• [06:00–11:00] Breaking down the Roche Digital Pathology DX System components: scanner, viewer (Navify DP), and monitor.
• [11:00–16:00] Understanding the pixel pathway—the heart of system validation.
• [16:00–19:00] How the FDA defines precision and accuracy in validation studies.
• [19:00–30:00] Inside the massive multi-year validation studies: design, washout periods, and thousands of slide reads.
• [30:00–33:00] The non-inferiority margin (−4%)—why it matters and how Roche exceeded the benchmark.
• [39:00–45:00] The surprising “nuclear groove” discovery and what it reveals about how pathologists adapt to digital.
• [1:10:00–1:13:00] Future-ready systems and FDA flexibility through predetermined change control plans (PCCP).
• [1:25:00–1:35:00] Keith’s reflection: bridging the gap between discovery and clinical impact, and why the future of digital pathology is brighter than ever.
  
  
  

Resources from This Episode

• Roche Digital Pathology DX (DP200 & DP600) – FDA-cleared systems for primary diagnosis
• FDA Guidance (2016) – Technical performance standards for WSI
• American Journal of Clinical Pathology – Paper in press on validation study design
• Book: Chasing the Invisible by Dr. Thomas Grogan
• Frontiers Journal (2021) – Tissue Multiplex Analyte Detection in Anatomic Pathology (co-authored by Aleks and Keith)
• AJCP Paper
• Aleks and Keith’s Paper - Frontiers | Tissue Multiplex Analyte Detection in Anatomic Pathology – Pathways to Clinical Implementation
  
  
  

Key Takeaways

✅ FDA clearance requires rigorous demonstration of precision, accuracy, and statistical confidence.
✅ Non-inferiority margins (typically −4%) define the threshold for clinical equivalence to microscopy.
✅ Feature recognition in digital environments (like nuclear grooves) challenges perception and training.
✅ Interoperability and predetermined change control plans (PCCP) may accelerate system evolution.
✅ Digital pathology’s foundation is the pixel pathway—where scanner, viewer, and monitor all align.
✅ The field’s future depends on bridging discovery and practice, guided by robust validation.

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!

Send us a text

What if the way we quantify pathology is more guesswork than science? In this episode of DigiPath Digest, I take you through the latest research where AI is not just supporting but challenging traditional methods of image analysis in neuropathology, nephrology, hematology, and cytology. From Boston brain banks to Mayo Clinic kidney models, we look at how advanced AI compares to human vision—and where it already outperforms us.

Episode Highlights:

• [00:02:49] Neuropathology image analysis (Boston VA & BU) – Why traditional semiquantitative scoring often fails, and how AI-based density quantification reveals more subtle pathology in CTE.
• [00:13:16] Chronic kidney changes with AI (Mayo Clinic, Cambridge, Emory, Geneva) – A 20-class AI model trained on 20,500 annotations, showing how multiclass segmentation outperforms human guesswork in renal pathology.
• [00:21:09] Digital hematology review (University of Pennsylvania) – Current hurdles in AI for blood and bone marrow evaluation: regulatory oversight, data standardization, and resistance to change.
• [00:25:52] AI in cytology review (Journal of Cytopathology) – From BD FocalPoint to deep learning: two decades of digital cytology, stagnation, and why adoption still lags despite proven benefits.
• [00:32:09] Neuropathology goes digital – Where digital neuropathology is already routine (Ohio State, Mayo Clinic, Leeds, Granada) and why this specialty is crucial for pushing adoption.
• [00:34:19] Personal note – Why I believe learning, sharing, and experimenting with AI tools now will shape the way we practice pathology tomorrow.

Resources from this Episode

• Comparison of quantitative strategies in neuropathologic image analysis – Boston VA / BU Brain Bank study.
• Multiclass AI model for chronic kidney changes – Mayo Clinic, Cambridge, Emory, Georgia Tech, Geneva collaboration.
• Review: Digital hematology in the AI era – International Journal of Laboratory Hematology.
• Review: AI and machine learning in cytology – Journal of the American Society of Cytopathology.
• Digital Pathology 101 (by me, Dr. Aleksandra Zuraw) – Free PDF & Amazon print edition.
• Pathology AI Makeover Course – Practical training for AI in pathology workflows.

Support the show

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

Send us a text

What if the AI tools we trust for cancer diagnosis are not always correct? This episode of DigiPath Digest takes on the uncomfortable but critical question: can AI “lie” to us—and how do we verify its performance before adopting it in clinical practice?

Highlights:

• [00:02:00] Foundation models in action: Deployment of a fine-tuned pathology foundation model for EGFR biomarker detection in lung cancer—reducing the need for rapid molecular tests by 43%.
• [00:08:41] Bone marrow AI misclassifications: Why automated digital morphology still struggles with consistency across leukemia and lymphoma cases.
• [00:14:45] Lossy DICOM conversion: How file format changes can subtly—but significantly—affect AI model performance.
• [00:21:45] Federated tumor segmentation challenge: Coordinating 32 international institutions to benchmark healthcare AI fairly across diverse datasets.
• [00:27:47] AI in gynecologic cytology: Reviewing AI-driven Pap smear screening—promise, limitations, and why rigorous validation remains essential.
• [00:32:27] Takeaway: Trust but verify—AI tools must be validated before they can support or replace clinical decisions.

Resources from this Episode

• Nature Medicine – Fine-tuned pathology foundation model for lung cancer EGFR biomarker detection.
• Scientific Reports (Germany) – Study on how DICOM conversion impacts AI performance in digital pathology.
• Federated Tumor Segmentation Challenge – Benchmarking AI across 32 global institutions.
• Acta Cytologica – Review on AI in gynecologic cytology and Pap smear screening.

Support the show

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