The @ProteinAtlas was absolutely essential to this work. The HPA graciously made their data CC-BY-SA-4.0, which enabled this work. I'm so fortunate to be a part of this outstanding team! And thanks to my postdoc mentor, @yeung_levy who encouraged me to pursue this direction.
Thanks, @ZhiHuangPhD! Shout-out to @Prof_Lundberg, a brilliant scientist and wonderful person who has been at the HPA for years! The Human @ProteinAtlas has been ongoing for >20 years. and is a testament to large-scale open science initiatives.
#hpa#digitalpathology#ihc
🚀 Introducing iSight: toward expert–AI collaboration for #immunohistochemistry (IHC) assessment
Preprint: https://t.co/xpQK8p8jyR
🚀 What we built:
🖼️ HPA10M, the world’s largest open-access IHC dataset: https://t.co/6FmJHw7GcB
• 10,495,672 IHC images (Over 10M!)
• 17,000+ protein markers
• 45 normal tissues + 20 cancer types
• Fully curated, standardized, and publicly available on @huggingface.
We trained iSight, a multi-task AI system for automated IHC assessment
• Jointly predicts staining location, intensity, and quantity
• Outperforms fine-tuned pathology foundation models
• Produces well-calibrated, clinically interpretable outputs
@PennPathLabMed #DigitalPathology #AIinHealthcare #Immunohistochemistry #HumanAI #Pathology
Check out PaperSearchQA, which I'll present at EACL in Morocco this March! We built an RL training environment for teaching LLMs to search and reason over scientific papers. 60k question-answer pairs + 16M papers to search over + benchmarks. RL training improves the model.
Excited to share that our lab’s latest work, Melan-Dx, a knowledge-enhanced vision-language framework for improving the differential diagnosis of melanocytic neoplasms in pathology, is now published in @npjDigitalMed! Read it at: https://t.co/z9hoZipoqO @PennPathLabMed #DigitalPathology #Dermpath
We're hiring! The Nirschl & Kolb (@hckolb ) labs @UWMadison are seeking a Scientist I/II to help develop novel PET tracers for neurodegenerative diseases.
- Tissue assays, autoradiography, SPR, protein biochem experience desired.
Apply here: https://t.co/XF1tCv4wuG
#PETimaging
Recently we released a 3000+ word book chapter written by @KeremTurgutlu, based on @karpathy's marvelous "Let's built the GPT tokenizer" video. It's got pics, links, code, diagrams, …
Kerem has now written a detailed walk-through of how he made it:
https://t.co/EIiejHe8hS
Wow! https://t.co/JgHStEpCTx has reached over 1700 users in the first 30 days and almost 500 downloads 🚀🔥! What an impressive achievement by my team. So proud of my students! We will keep shipping the code, fixing the bugs, and improve user experiences. Check out the first co-evolving agentic AI system for medical image analysis! 👉https://t.co/NoX7bMTdha #TissueLab #AIAgent #AgenticAI #pathology #radiology