BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Computer vision beyond human vision – the medical perspective - 
 David Pertzborn\, Clinical Biophotonics\, Jena University Hospital\, Germa
 ny
DTSTART:20241129T173000Z
DTEND:20241129T180000Z
UID:TALK224929@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:Traditional computer vision and AI are often applied to tasks 
 that humans can perform equally well or even better. In these cases\, huma
 n experts typically generate the ground truth values on which algorithms a
 re trained. The advantages of machine learning in such applications includ
 e cost savings\, reduced bias\, and the broad availability of expert knowl
 edge. Typical tasks range from self-driving cars to localizing tumors in l
 arge datasets.\nHowever\, machine learning can also be used for tasks that
  are challenging or impractical for human experts alone\, or where AI is n
 ecessary to enable human experts to achieve specific goals. In medical ima
 ging\, there is a trend toward increasingly advanced imaging methods\, whi
 ch produce datasets that are difficult for human observers to visualize an
 d interpret. Beyond the sheer size of these datasets\, a key factor contri
 buting to this complexity is the higher-dimensional nature of the data\, w
 hich can be thought of as images with (often many) more than three channel
 s per pixel. Examples of these advanced imaging types include hyperspectra
 l imaging\, quantitative MRI mass spectrometry imaging\, and Raman imaging
 . Each of these fields relies on machine learning as an essential\, though
  currently insufficient\, component to integrate new imaging modalities in
 to medical practice. In this lecture\, I will outline current applications
 \, challenges\, and unmet needs of machine learning when implementing adva
 nced imaging modalities that go beyond human vision and interpretability.\
 nhttps://meet.google.com/kns-mqbz-jkq
LOCATION:Lecture Theatre 2
END:VEVENT
END:VCALENDAR