Today’s AI radiology solutions don’t effectively account for past imaging findings despite their routine use by radiologists. BioViL-T jointly trains text and image encoders that can ground radiology text across longitudinal images: msft.it/6014glsLC

Great point from Nigam Shah at #CHIL23; to study ML in healthcare, we too often ignore the actions and policy sides of things, and just study the model. Without knowing what your actions or policies are, you can never know the benefit of your model.

I never forgot amazing advice of Dina D. Pomeranz 🟣 which is that some days the appropriate task scope looks like “1. Open data file”.

Full programme for our 20th Armitage Workshop is now confirmed. Fantastic line-up of speakers including from _hylandSL, Leiv Rønneberg, Brendan Murphy, Jessica Barrett & keynote by amy. Find out more & register FREE: mrc-bsu.cam.ac.uk/news-and-event…

🚨 Deadline Extension Alert 🚨 We’re extending our submission deadline to Feb 16th EoD! 🎉 Don’t miss the opportunity to polish your work & submit the best version of your paper! chilconference.org/call-for-paper… #CHIL2024 #CallForPapers #ml4h #machinelearning #ai #health #MoreTimeToShine

Our next Integrated Cancer Medicine and Cambridge MedAI Seminars Seminar a week today! Multimodal AI for Radiology Stephanie Hyland, Principal Researcher, Microsoft Research Cambridge 🗓️ Thur 18 April, 15:00-17:00 📌 Rayleigh seminar room Maxwell Centre Sign up 👉 eventbrite.co.uk/e/integrated-c…