BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Explainable deep neural networks for medical image analysis - Krzy
 sztof Geras (New York University)
DTSTART:20210301T173000Z
DTEND:20210301T183000Z
UID:TALK157810@talks.cam.ac.uk
CONTACT:74143
DESCRIPTION:Although deep neural networks have already achieved a good per
 formance in many medical image analysis tasks\, their clinical implementat
 ion is slower than many anticipated a few years ago. One of the critical i
 ssues that remains outstanding is the lack of explainability of the common
 ly used network architectures imported from computer vision. In my talk\, 
 I will explain how we created a new deep neural network architecture\, tai
 lored to medical image analysis\, in which making a prediction is insepara
 ble from explaining it. I will demonstrate how we used this architecture t
 o build strong networks for breast cancer screening exam interpretation an
 d COVID-19 prognosis.
LOCATION:https://cern.zoom.us/j/68040442212?pwd=Z3pjNG0xOGE2aDF1eExoVkJkYn
 JtQT09
END:VEVENT
END:VCALENDAR