RSNA 2026 lab teaches radiologists to spot why high-AUC models fail in the clinic
PRouzrokh · x · 2026-10-31
RSNA 2026 Deep Learning Lab 04 (Mon, Nov 30, 9:30–10:30 AM CT, McCormick Place S401A-B) tackles why models that score well in papers can still fail in the clinic — and how to catch it before patients are affected.
Led by Shahriar Faghani (University of Pennsylvania) and Mana Moassefi (Mayo Clinic), the Core-level session needs only a laptop and a Google account. It goes beyond AUC to cover data shift and drift, generalizability, calibration, uncertainty-based drift flagging, a deployment-readiness checklist, and how radiologist oversight keeps things safe — no heavy coding required.
More from Companies & People
- Talk: how AI is reshaping education, from edtech builders to university classrooms — Cohere · 2026-10-31
- Google: AI Mode, AI Overviews and Search merging into one unified product — gaganghotra_ · 2026-10-31
- HubSpot co-founder: startups die from suicide, not homicide — competition isn't the real killer — nathanbenaich · 2026-10-31
- Anthropic culture anecdote: co-founder balked at office sushi, 'I'd prefer rice and beans' — himanshustwts · 2026-10-31
- Meta exec: Llama 3.2 was the first named model to run in space, back in April 2025 — Ahmad_Al_Dahle · 2026-10-31
- First NeurIPS trip: creator shares registration for NeurIPS 2026 in Sydney — HowDevelop · 2026-10-31