BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Cancer ID - From Spectral Segmentation to Deep Learning - Christop
 h Brune (Universiteit Twente)
DTSTART:20171030T120000Z
DTEND:20171030T125000Z
UID:TALK94012@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:One of the most important challenges in health is the fight ag
 ainst cancer. A desired goal is the early detection and guided therapy of 
 cancer patients. A very promising approach is the detection and quantifica
 tion of circulating tumor cells in blood\, called liquid biopsy. However\,
  this task is similar to looking for needles in a haystack\, where the nee
 dles even have unclear shapes and materials. There is a strong need for re
 liable image segmentation\, classification and a better understanding of t
 he generative composition of tumor cells.  For a robust and reproducible q
 uantification of tumor cell features\, automatic multi-scale segmentation 
 is the key. In recent years\, new theory and algorithms for nonlinear\, no
 n-local eigenvalue problems via spectral decomposition have been developed
  and shown to result in promising segmentation and classification results.
  We analyze different nonlinear segmentation approaches and evaluate how i
 nformative the resulting spectral responses are. The success of our analys
 is is supported by results of simulated cells and first European clinical 
 studies.  In the last part of this talk we switch the viewpoint and study 
 first results for deep learning of tumor cells. Via generative models ther
 e is hope for understanding tumor cells much better\, however many mathema
 tical questions arise.  This is a joint work with Leonie Zeune\, Stephan v
 an Gils\, Guus van Dalum and Leon Terstappen.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR