⚡🎉 We are thrilled to introduce VORTEX, an AI-powered computational framework for predicting 3D Spatial Transcriptomics (ST) using 3D tissue images and minimal 2D ST! 🧬 By combining cutting-edge 3D non-destructive tissue imaging with AI, VORTEX imputes the 3D molecular

Today, I am very excited to announce AI-driven 3D ST prediction framework, VORTEX, that have been in works for the past few years! This is a beautiful multimodal extension of TriPath, AI-driven patient prognosis for 3D pathology that was published in Cell last year!

📢 USCAP attendees! Join us on March 23rd for "Dinner with Data: The AI Revolution in 2D & 3D Pathology." 🔬 Dr. Andrew H. Song (Harvard) shares how AI & weakly supervised ML improve disease prediction in pathology. 📝 RSVP now: alpenglowbiosciences.com/uscap-dinner-e…

Join our CTEU Seminar on 3/12 at 9 AM. Dr. Andrew H. Song from the Brigham and Women’s Hospital will give a talk entitled “When AI meets pathology – Harnessing AI for improved patient care.” Chat with us at mghcteu.org to join Zoom.

Happy #LearningWednesday! Today, let's review the excellent work "AI-driven 3D Spatial Transcriptomics.” Where VORTEX is presented: an AI framework that predicts 3D transcriptomic profiles from minimal 2D data: linkedin.com/feed/update/ur…

🔥 Dinner with Data: A Night of Insights & Innovation Packed room. Big ideas. Experts explored The AI Revolution in 2D & 3D Pathology. 💡 Key takeaways: 📌 2D & 3D spatial biology matter more than ever. 📌 AI is driving pathology’s future. Huge thanks to Andrew H. Song!

I am joining University of Alberta as a faculty member and Amii this June! Excited to build my research group, working at the intersection of inverse problems, representation learning, generative models, interpretability, and neuroAI for emergent intelligence. 1/

News feature from Nature Biotechnology highlights our work on 3D Spatial Transcriptomics - VORTEX, read our pre-print here: arxiv.org/pdf/2502.17761 nature.com/articles/s4158…

👉📣Introducing KRONOS, a panel-agnostic foundation model purpose-built for multiplex spatial proteomics! Access the pre-print here: arxiv.org/pdf/2506.03373 Trained self-supervised on 47 million single-marker patches spanning 175 protein markers, 16 tissue types, 8 imaging

Check out our latest work on deriving crucial insights for transferability of multiple instance learning (MIL) models in #computationalpathology to be presented in ICML Conference (Spotlight)! Kudos to Daniel Shao who led the study 😎

⚡🦠I'm excited to share that our latest work on the gut microbiome and metabolic dysfunction-associated steatotic liver disease (MASLD) is now published in Nature Metabolism, with hutlab & long nguyen! Check out the paper here: 🔗nature.com/articles/s4225… 👇Tweetorial

📣 If you're at ICML Conference ICML 2025, our superstar graduate student Daniel Shao will be presenting our work on transferability of MIL models and supervised foundation models for computational pathology. Poster session: 11 am - 1:30 pm PST at West Exhibition Hall B2-B3 #W-314

Why Participate? ✔ Influence the future of digital pathology ✔ Help build a stronger, connected pathology community ✔ Contribute to innovation in spatial and 3D pathology 👉 Take the survey now and share with your network: docs.google.com/forms/d/e/1FAI…