Send us a text

“AI in Pathology Isn’t Coming — It’s Already Here. Are You Ready?”

From confusion to clarity — that’s what this episode is all about. I sat down with Drs. Liron Pantanowitz, Hooman Rashidi, and Matthew Hanna to dissect one of the most important and comprehensive AI-in-pathology resources ever created: the 7-part Modern Pathology series from UPMC’s Computational Pathology & AI Center of Excellence (CPAiCE). This isn’t just another opinion piece — it's your complete guide to understanding, implementing, and navigating AI in pathology with real-world insights and a global lens.

Together, we discuss:

• Why pathologists and computer scientists are often lost in translation
  
  
• How AI bias, regulation, and ethics are being addressed — globally
  
  
• What it really takes to operationalize AI in patient care today
  
  

If you’ve ever asked, “Where do I even start with AI in pathology?” — this is your answer.

🔍 Highlights & Timestamps
00:00 – The importance of earned trust in AI
01:00 – Education gaps in AI for both pathologists & developers
03:00 – Why CPAiCE was built & the three missions it serves
07:00 – The seven-part series: a blueprint for AI literacy
10:00 – Making AI education accessible without losing technical integrity
13:00 – How this series is being used for global teaching (including by me!)
17:00 – Generative AI in creating figures vs. human-authored content
21:00 – Eye-opening global AI regulations that pathologists MUST know
24:00 – Ethics, bias & strategies to mitigate real clinical risks
30:00 – What’s next: CPAiCE’s mission to reshape pathology education & practice
34:00 – A teaser: the first CPAiCE textbook is on the way!

📚 Resources from This Episode

📰 Read the full series (open access!):
Modern Pathology 7-Part AI Series: https://www.modernpathology.org/article/S0893-3952(25)00001-8/fulltext

👨‍⚕️ UPMC’s Computational Pathology & AI Center of Excellence (CPAiCE)
🌍 Creative Commons licensing means YOU can reuse, remix & teach from these resources — just cite the source.

Support the show

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

Send us a text

You think Saturday mornings are for coffee? Try diving into bone marrow morphology, organ donor kidney biopsies, and AI-driven metastasis detection at sunrise. That’s how I do it—and you’re invited to join.

Welcome to another data-packed episode of DigiPath Digest, where we explore the latest frontier in digital pathology and AI. This time, I reviewed some of the most exciting recent abstracts spanning cancer grading, T-cell quantification, and AI agents in oncology decision-making.

These studies aren’t just fascinating—they’re redefining what’s possible in diagnostics, especially in under-resourced areas where digital pathology can create game-changing access and efficiency.

🔬 Highlights with Timestamps

[00:04:00] Detecting Metastases with Vision Transformers
A team from Leeds Teaching Hospital developed a model for identifying lymph node and omental metastases in ovarian and peritoneal cancers with 99.8% AUROC and 100% balanced accuracy—this isn’t hype; it’s real AI pre-screening that could reduce diagnostic strain on pathologists.

[00:08:00] DeepHeme: Bone Marrow Smears Meet AI
UCSF and Memorial Sloan Kettering collaborated on DeepHeme, an ensemble deep learning model that classifies bone marrow aspirate cells with expert-level accuracy. With over 30K training images and strong external validation, it outperforms humans in both speed and detail.

[00:16:00] Multimodal AI for Head & Neck Cancer
This review showcases how integrating radiology, histopathology, and genomics with AI enhances personalized treatment and prognosis. Spoiler alert: Multimodal > unimodal.

[00:24:00] Real-Time Kidney Biopsy Evaluation via AI
Shoutout to our Digital Pathology Place sponsor, Techcyte, for their AI-powered tool improving accuracy and halving the time it takes to evaluate frozen kidney biopsies. This is the kind of innovation we need in organ transplantation.

[00:32:00] GPT-4 as an Oncology Agent?
Heidelberg researchers created an autonomous AI agent using GPT-4 plus vision models and OncoKB to handle oncology case decisions with 91% accuracy. This isn’t ChatGPT guessing—it’s a hybrid system citing guidelines and performing complex reasoning.

🧠 Resources From This Episode

• 📰 Multiple Instance Learning for Metastases Detection in Ovarian Cancer – Cancers journal
• 🧬 DeepHeme: Generalizable Bone Marrow Cell Classifier – Science Translational Medicine
• 📚 AI in Head and Neck Cancer: A Multimodal Review – Cancers journal
• 🧪 AI-Assisted Review of Donor Kidney Pathology – Techcyte & Digital Pathology Place demo
• 🤖 Autonomous AI Agent for Oncology Decisions – Heidelberg Group
• 🎙️ Podcast on GPT-4 agents with Dr. Nina Kolker
• 🧵 Earrings mentioned in the livestream? Find them in the DPP Store

I’d love to hear your feedback, your projects, and what digital pathology means to you. You can always reach out through comments, LinkedIn, or email.

Support the show

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

Send us a text

AI Pathology & Genomics: A New Benchmark for Predicting Gene Mutations

If you still think visual quantification is “good enough” in pathology, think again.
In this 27th episode of DigiPath Digest, I break down four transformative abstracts that show how AI is shifting our diagnostic landscape—from breast cancer segmentation to fibrosis assessment, and all the way to spatial immunology and the evolving immunoscore.

If you’re still relying on manual scoring, static staging systems, or single-marker immunohistochemistry, this episode will challenge you to look deeper—literally and algorithmically.

🔬 Episode Highlights & Timestamps

[02:00] Abstract 1 – AI + IHC for epithelial cell segmentation in breast cancer
[07:30] Abstract 2 – Deep learning quantifies TILs in esophageal cancer
[14:30] Abstract 3 – Biopsy size impacts SHGTPF-based liver fibrosis staging
[22:30] Abstract 4 – Immunoscore in colorectal cancer: promise & limits

🧬 Key Insights & Takeaways

1. IHC-Guided Segmentation for Breast Cancer
Using immunohistochemistry as a ground truth for AI segmentation reveals how effective our models can be—but also where they fall short. The challenge? Accurately subclassifying benign, in situ, and invasive epithelial cells. Spoiler: We’re not quite there yet.

2. Tumor-Infiltrating Lymphocytes in Esophageal SCC
A Chinese team trained deep learning algorithms to analyze TILs spatially. Result? High TIL counts in both intra- and peritumoral zones correlated with better survival—highlighting the emerging power of spatial immunology.

3. Liver Fibrosis Staging with SHGTPF Microscopy
Second harmonic generation two-photon microscopy gives us label-free imaging of unstained tissue. The takeaway: bigger biopsies (20–26mm) yield better fibrosis quantification. Biopsy position? Surprisingly irrelevant. A game-changer for MASLD diagnostics.

4. Immunoscore for Colorectal Cancer
This image analysis-based tool outperforms traditional TNM staging, helping stratify patients for immunotherapy. But adoption is hampered by cost and digital slide access. Integrating AI could take it to the next level—something we should all watch closely.

🎓 Resources from This Episode

• Breast cancer segmentation using IHC-guided AI (Trondheim, Norway)
• Esophageal SCC & spatial TILs (Cancer Medicine, China)
• SHGTPF microscopy in liver fibrosis (UK/US multi-center study)
• Immunoscore in colorectal cancer (Jerome Galon group origins)

💡 Bonus: I show off some histology-inspired earrings and talk about the story behind them—multinucleated giant cells, cartilage, and more. Check them out if you’re into pathology fashion!

We’re not just validating AI anymore—we're redefining diagnostics. From high-res, label-free imaging to robust spatial biology insights, the path forward in pathology is clearer and more precise than ever. Whether you’re a practicing pathologist, researcher, or innovator, this episode offers tools and perspectives you can apply today.

Support the show

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

Send us a text

If our visual scoring is still based on gut feeling, how do we scale precision?
In this week’s DigiPath Digest, I explored four new AI-focused papers that could reshape how we diagnose prostate, bladder, gastroesophageal, and endocrine cancers.

From automated IHC scoring to predicting urethral recurrence post-cystectomy, these studies highlight the growing value—and responsibility—of integrating AI into our pathology workflows.

And yes, I also reveal where to get my histology-inspired earrings 😉

Episode Highlights

[06:00] Muse Vet Platform launch + STP talk
[11:00] Tools I use: Perplexity, RAG, ChatGPT, and AI citation traps
[14:00] AI’s promise—and its pitfalls

Paper 1: IHC Scoring in GEC (Caputo et al.)

Manual PD-L1 and HER2 scoring is subjective. This study shows AI can standardize and improve accuracy using digital tools for GEC.

[20:00] AI reduces visual bias
[23:00] Potential to replace expensive assays

Paper 2: ASAP in Prostate Biopsies

Page Prostate AI matched final diagnoses 85% of the time—more than human reviewers.

[24:00] ASAP = gray zone diagnosis
[27:00] AI matched final calls more often than humans

Paper 3: Recurrence Prediction Post-Cystectomy

Chinese study developed a recurrence model using ML on clinical data. AUC: 0.86 (train), 0.77 (test).

[30:00] Risk factors: CIS, bladder neck involvement
[32:00] SHAP explained model insights

Paper 4: Reticulin Framework in Endocrine Pathology

Reticulin stains are cheap but powerful. This paper calls for AI to take notice.

[36:00] Reticulin separates benign from malignant
[40:00] Let’s train AI on these patterns

📚 Resource from this Episode

• Caputo et al., Pathology Research & Practice
• Page Prostate study on ASAP
• ML model predicting urethral recurrence
• Reticulin stains in endocrine tumor grading

AI is already enhancing diagnostic precision—we just need to guide its use responsibly. From special stains to advanced models, this episode covers where we're headed next.

Support the show

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

Send us a text

If we don’t learn to work with LLMs now, we might end up competing with them. 🧠
In this week’s DigiPath Digest, I return to our Journal Club to unpack the latest research on AI in tumor classification, focusing on GPT-4o, LLaMA, and other LLMs. Can these models really outperform traditional tools when analyzing pathology reports?

Surprisingly—yes. But don’t panic. This episode is about understanding what LLMs actually bring to the table, how they’re being evaluated, and what we need to consider as digital pathology continues to evolve.

It’s also a special week for me personally—I recorded this episode the morning of my U.S. citizenship ceremony, and I used AI to help write my speech! I’ll share more about that next time.

⏱️ Episode Highlights

[00:00] – Life update + AI-written speech for my citizenship
[04:00] – Journal Club: Austrian study on LLMs in pathology report analysis
[05:00] – Why cancer registries need better documentation tools
[06:00] – LLMs tested on synthetic pathology reports—game-changing idea
[07:00] – GPT-4 and LLaMA outperform score-based models in accuracy
[08:00] – Use case: AI-enhanced text mining across whole archives
[09:00] – How my PhD could’ve been easier with these tools
[10:00] – Second paper: A public synthetic dataset for benchmarking LLMs
[11:00] – Tools used: ChatGPT, Perplexity, Copilot to generate report variations
[13:00] – Benefits of synthetic data for de-identification
[14:00] – Thoughts on bias, annotation workflows, and future-proofing
[16:00] – Polish research on hybrid annotation for follicular lymphoma
[19:00] – Foundation models, bootstrapping, weak supervision in action
[22:00] – Charles River: AI for thyroid hypertrophy scoring in tox path
[23:00] – Subjectivity of scoring thresholds and reproducibility
[24:00] – Morphology-driven scoring architecture improves accuracy

📚 Resource from this Episode

1. LLM Performance in Malignancy Detection from Pathology Reports
   🔗 Read Article
2. Synthetic Dataset for Evaluating LLMs in Medical Text Classification
   🔗 Read Article

🧰 Tools & Topics Mentioned

• LLMs: GPT-4o, LLaMA, Copilot, Perplexity
• Synthetic Data for AI model testing
• Annotation strategies: weak supervision, bootstrapping
• Pathology AI applications: tumor detection, thyroid activity, lymphoma
• Research teams: Austria, Poland, Charles River Labs

The big takeaway? AI tools are improving fast—and it’s up to us to decide how they’re used in our field. This episode breaks down the latest advancements and opens the door to practical, safe integration in pathology workflows.

🎧 Let’s keep pushing the boundaries—together.

Support the show

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

Send us a text

AI in Pathology: ML-Ops and the Future of Diagnostics

What if the most advanced AI models we’re building today are doomed to die in the machine learning graveyard? 🤯 That’s the haunting question I tackled in the final episode of our 7-part series exploring the Modern Pathology AI publications.

In this session, I explored machine learning operations (ML-Ops)—what they mean for digital pathology —and why even the most brilliant algorithm can fail without proper deployment strategies, data infrastructure, and lifecycle management.

But we don’t stop there. I take you on a future-forward tour through multi-agent frameworks, edge computing, AI deployment strategies, and even virtual/augmented reality for medical education. This isn’t sci-fi. This is happening now, and as pathology professionals, we need to be prepared.

🔗 Full episode reference:
Modern Pathology - Article 7: AI in Pathology ML-Ops and the Future of Diagnostics
Read the paper

🔍 Episode Highlights & Timestamps

[00:00] – Tech check, community shout-outs, and livestream reflections
[02:00] – Overview of ML-Ops: What it is and why pathologists should care
[03:45] – What’s a Machine Learning Graveyard? Personal examples of models I’ve built that went nowhere
[05:30] – Machine learning platforms: from QPath to commercial image analysis tools
[06:45] – The lifecycle of ML models: Development, deployment, and monitoring
[09:00] – Mayo Clinic and Techcyte partnership: Real-world deployment integration
[12:30] – Frameworks & DevOps tools: Docker, Git, version control, metadata mapping
[14:30] – Model cards in pathology: Structuring ML model metadata
[16:30] – Deployment strategies: On-premise, cloud, and edge computing
[20:00] – PromanA and QA via edge computing: Doing quality assurance during scanning
[23:00] – Measuring ROI: From patient outcomes to institutional investment
[25:00] – Multi-agent frameworks: AI agents collaborating in real-time
[28:00] – Narrow AI vs. General AI and orchestrating narrow tools
[30:00] – Real-world applications: Diagnosis generation via AI collaboration
[32:00] – Virtual & Augmented Reality in pathology training: From smearing to surgical simulation
[35:00] – AI in drug discovery and virtual patient interviews
[38:00] – Scholarly research with LLMs: Structuring research ideas from unstructured data
[41:00] – Regulatory considerations: Recap of episode 5 for frameworks and guidelines
[42:00] – Recap and future updates: Book announcements, giveaways, and next steps

Resource from this episode

• 🔗 Modern Pathology Article #7: AI in Pathology ML-Ops and the Future of Diagnostics
  
  
• 🛠️ Tools/References mentioned:
  • QPath (Free Image Analysis Tool)
  • Techcyte & Aiforia for model development and deployment
  • PromanA for edge computing and real-time QA
  • Model Cards (Pathology-specific metadata structure)
  • Apple Vision Pro, Meta Oculus, HoloLens for VR/AR learning
  • Dr. Hamid Ouiti Podcast on software failure in medicine
  • Dr. Candice C

Support the show

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

Send us a text

Can We Ever Eliminate Bias in AI for Pathology?

Every time we think we’ve trained a “neutral” algorithm, we discover our own fingerprints all over it. Our biases. Unconscious. Systemic. Data-driven. And if we ignore them, AI won’t just fail—it will fail patients.

Welcome back, my digital pathology trailblazers! In this sixth episode of our 7-part AI in Pathology series, we tackle one of the most uncomfortable yet necessary conversations: Ethics and Bias in AI and Machine Learning. These are not abstract philosophical concerns—they are critical decisions that affect diagnostic accuracy, fairness, and patient safety.

We lean heavily on the brilliant work co-authored by Matthew Hanna, Liam Pantanowitz, and Hooman Rashidi, published in Modern Pathology, which you can read here: Ethics and Bias in AI for Pathology.

Let’s explore where bias creeps in, how we can mitigate it, and what it means to be a responsible data steward in digital pathology.

⏱️ Highlights & Timestamps

[00:00:00] Welcome back! Kicking off from Pennsylvania at 6:00 AM and reflecting on USCAP highlights, upcoming podcasts, and a pivotal lawsuit on LDTs.
[00:03:00] Defining today’s topic: Bias in AI—why it matters, and how pathologists are key players in shaping ethical, trustworthy algorithms.
[00:05:00] Who are the “data stewards”? A new term you need to own. We explore the role of healthcare professionals in AI development and deployment.
[00:07:00] Ethical principles decoded—autonomy, beneficence, non-maleficence, justice, and accountability—and how they translate to AI and ML.
[00:11:00] From voting rights to data rights: A surprising analogy from my U.S. citizenship interview about the evolution of fairness.
[00:12:00] 12 types of bias explained—from data bias to feedback loops, representation to confirmation bias—with real pathology examples.
[00:22:00] Temporal bias and transfer bias: Why yesterday’s data may not apply to today’s patients.
[00:26:00] Walkthrough of the AI lifecycle and how bias seeps in at every stage—from research to regulatory approval.
[00:29:00] Clinical trials & guidelines: Learn the difference between STARD-AI, TRIPOD-AI, QUADAS-AI, and CONSORT-AI.
[00:33:00] Visual case study: Gleason score distribution by region shows how biased training data leads to misdiagnosis.
[00:37:00] Real-world mitigation: I spotlight Digital Diagnostics Foundation and Big Picture Consortium as proactive models for bias reduction.
[00:41:00] Why explainability and introspection are more than buzzwords—they are our tools for ensuring accountability.
[00:44:00] FAIR data principles—Findability, Accessibility, Interoperability, and Reusability—and why annotations often fall short.
[00:48:00] Practical steps: How to build better algorithms with built-in fairness, bias detectors, and responsible data sharing.

📚 Resource from this Episode:

📄 Featured Publication:
Ethics and Bias Considerations in Artificial Intelligence and Pathology
➡️ Access Full Article

Let’s keep creating technology that doesn’t just do what we tell it to—but does what is right for everyone. See you in the next and final episode of this

Support the show

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

Send us a text

The Most Overlooked Risk in AI for Pathology? It’s Not What You Think…

Welcome, my trailblazing digital pathologists! In this episode, I dive headfirst into the regulatory maze of Artificial Intelligence (AI) in pathology, covering global frameworks, safety risks, ethics, and the future of software as a medical device. While regulation might not be the flashiest part of AI, ignoring it could cost us innovation—or worse, patient safety.

We’re on Part 5 of our 7-part AI in Pathology series, and this one’s vital for anyone developing, using, or simply curious about AI and machine learning tools in healthcare.

If you thought regulation was boring, think again—it’s what separates a helpful algorithm from a dangerous black box.

🎧 Listen to the full episode and reference the latest study discussed here: Modern Pathology Journal Article

🔍 Highlights & Timestamps

[00:00:00] Welcome & Why Regulation Matters
Pixelation aside, I introduce today's critical topic—regulatory frameworks that define how AI tools are used, approved, and reimbursed in pathology.

[00:03:00] The Risks AI Brings to Healthcare
We’re not just talking about patient data—think security, ethical biases, economic consequences, and even environmental impact from heavy computation.

[00:05:00] HIPAA, GDPR, and the Common Rule Explained
What protects patient privacy globally? Dive into U.S. and European legislation like HIPAA and GDPR, and how IRBs and the Common Rule ensure ethical compliance in clinical research.

[00:08:00] FDA & Global Agencies Breakdown
Get to know the role of Health Canada, UK’s MHRA, Japan’s PMDA, and others in approving AI tools. Discover how the U.S. FDA sets the gold standard—and why CE Mark devices often hit Europe first.

[00:17:00] What Makes Software a Medical Device (SaMD)?
Four critical questions to ask to determine if your AI tool is considered a regulated device. If the software diagnoses, directs, or lacks transparency—chances are, it’s a device.

[00:22:00] FDA Pathways: Clearance vs. Approval
I break down Class I, II, and III device categories, and what 510(k) clearance means versus pre-market approval (PMA). Yes, we even cover why some tools like Paige AI needed full PMA.

[00:40:00] Why Reimbursement Is the Elephant in the Room
No billing codes, no incentives. I share a personal story about my husband’s five-year reimbursement battle and the challenges of proving economic and clinical value.

[00:45:00] The LDT (Lab Developed Test) Controversy
In 2024, the FDA formally categorized LDTs as medical devices, igniting debate about oversight, innovation, and compliance.

[00:47:00] Generative AI: A New Beast to Regulate
ChatGPT and similar tools pose fresh challenges: reproducibility, explainability, and dynamic outputs. Current frameworks simply can’t keep up—but regulation must.

[00:51:00] USCAP Event Invite & Digital Pathology Collaboration
I’m thrilled to invite you to Muse Microscopy’s USCAP presentation—join live or virtually! Plus, learn how we’re reshaping the digital pathology workflow with direct-to-digital imaging.

🧠 Resource From This Episode

Referenced Study:
📄 Artificial Intelligence in Pathology: Regulatory Challenges & Opportunities
👉

Support the show

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!