iiinova — where your digital self keeps evolving

Reposted by @frazierhuo.bsky.social

Jason Alan Fries @jason-fries.bsky.social · 23/04/2025

🎉 Excited to present our #ICLR2025 work—leveraging future medical outcomes to improve pretraining for prognostic vision models. 🖼️ "Time-to-Event Pretraining for 3D Medical Imaging" 👉 Hall 3+2B #23 📍 Sat 26 Apr, 10 AM–12:30 PM 🔗 iclr.cc/virtual/2025...

iclr.cc

ICLR Poster Time-to-Event Pretraining for 3D Medical ImagingICLR 2025

011

frazierhuo.bsky.social @frazierhuo.bsky.social · 13/02/2025

🚀 Public releases 𝘁𝗵𝗿𝗲𝗲 𝗱𝗲-𝗶𝗱𝗲𝗻𝘁𝗶𝗳𝗶𝗲𝗱 𝗹𝗼𝗻𝗴𝗶𝘁𝘂𝗱𝗶𝗻𝗮𝗹 𝗘𝗛𝗥 𝗱𝗮𝘁𝗮𝘀𝗲𝘁𝘀 (EHRSHOT, INSPECT, MedAlign) with 25,991 patients & 295M clinical events (1997-2023)—now freely available! These datasets support 𝗺𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴, 𝘁𝗶𝗺𝗲-𝘁𝗼-𝗲𝘃𝗲𝗻𝘁 𝗺𝗼𝗱𝗲𝗹𝗶𝗻𝗴, and 𝗳𝗲𝘄-𝘀𝗵𝗼𝘁 𝘁𝗮𝘀𝗸𝘀.

010

frazierhuo.bsky.social @frazierhuo.bsky.social · 02/02/2025

[1/4] Excited to share that our paper 𝘛𝘪𝘮𝘦-𝘵𝘰-𝘌𝘷𝘦𝘯𝘵 𝘗𝘳𝘦𝘵𝘳𝘢𝘪𝘯𝘪𝘯𝘨 𝘧𝘰𝘳 3𝘋 𝘔𝘦𝘥𝘪𝘤𝘢𝘭 𝘐𝘮𝘢𝘨𝘪𝘯𝘨 is accepted at ICLR 2025! 🚀 We introduce 𝗧𝗧𝗘 𝗽𝗿𝗲𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴, using EHR-linked imaging to improve AI-driven prognosis—essential for assessing disease progression. 🔗 Paper: arxiv.org/abs/2411.09361

arxiv.org

Time-to-Event Pretraining for 3D Medical Imaging

With the rise of medical foundation models and the growing availability of imaging data, scalable pretraining techniques offer a promising way to identify imaging biomarkers predictive of future disea...

141