BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//sebbo.net//ical-generator//EN
URL:https://lectures.london/imperial-college/the-look-of-why-causality-mat
 ters-in-medical-imaging-ai/calender.ics
NAME:Lectures London
X-WR-CALNAME:Lectures London
TIMEZONE-ID:Europe/London
X-WR-TIMEZONE:Europe/London
BEGIN:VEVENT
UID:68636519-05ed-4c8c-9e1d-fd3652ceaf86
SEQUENCE:0
DTSTAMP:20261010T113552
DTSTART:20261014T163000
DTEND:20261014T173000
SUMMARY:The look of why: causality matters in medical imaging AI
LOCATION:Imperial College: Lecture theatre 200\, City and Guilds Building
DESCRIPTION:Join Professor Ben Glocker\, Professor in Machine Learning for
  Imaging\, to discover how causality could help make medical imaging AI sa
 fer\, fairer and more reliable. \nPlease register to attend in person. A l
 ive stream link for online attendance is available here. \nWe look forwar
 d to seeing you on Wednesday 14 October!\nImperial Inaugurals are term-t
 ime lectures that celebrate our newest Professors\, recognising their acad
 emic journey and showcasing their research.\nAbstract\nArtificial intellig
 ence is transforming medical imaging\, promising more accurate diagnosis
 \, earlier detection of disease\, and better clinical decision-making. But
  the path from research prototype to trusted clinical tool remains diffi
 cult. AI systems can silently fail when new data differs from the data on 
 which they were trained. Changes in patient populations\, imaging protocol
 s\, and healthcare settings across geographic regions can cause distributi
 on shifts that undermine the reliability\, robustness\, and fairness of AI
  predictions.\nIn this inaugural lecture\, Professor Ben Glocker explores
  why causality matters for understanding when AI works and when it fails. 
 He will discuss the role of ‘what-if’ reasoning and the use of the lat
 est causal generative models to create realistic counterfactual images tha
 t can stress-test AI systems\, expose blind spots\, and mitigate bias. Ul
 timately\, causality may be the missing ingredient that turns medical ima
 ging AI from a promising technology into a life-saving reality.\nBiography
 \nBen Glocker is a Professor in Machine Learning for Imaging at Imperial
 ’s Department of Computing where he co-leads the Biomedical Image Analys
 is Group. He holds a Royal Academy of Engineering Research Chair in Safe D
 eployment of Medical Imaging AI\, and also leads the Heartflow-Imperial
  Research Lab. He received his PhD from TU Munich\, was a postdoc at Micro
 soft and a Research Fellow at the University of Cambridge. His research is
  at the intersection of medical imaging and artificial intelligence\, aimi
 ng to build safe and ethical computational tools for improving image-based
  detection and diagnosis of disease.
URL;VALUE=URI:https://www.imperial.ac.uk/events/212238/the-look-of-why-cau
 sality-matters-in-medical-imaging-ai/
END:VEVENT
END:VCALENDAR