BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:EE Distinguished Lecturer Seminar: Inverse problems in medical ima
 ging – view the invisible
DTSTART:20190614T131500
DTEND:20190614T141500
DTSTAMP:20260604T000331Z
UID:f33766969c23caad0cf6824379e13a83d56d393f5bc3c9c8dcccabe4
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Thiran is author or co-author of 1 book\, 9 book chapte
 rs\, more than 200 journal papers and more than 250 peer-reviewed papers
  published in the proceedings of international conferences. He holds 9 i
 nternational patents. Among other duties\, he has been Co-Editor- in-Chie
 f of the Signal Processing journal\, an associate editor of the IEEE Tra
 nsactions on Image Processing\, the general chairman of the 2008 Europea
 n Signal Processing Conference (EUSIPCO 2008) and the Technical Co-chair 
 of the 2015 IEEE International Conference on Image Processing (IEEE ICIP
  2015 - Quebec City\, Canada). He is a senior member of the IEEE.\nAbstr
 act: Over the last decade\, thanks to the development of both mathematic
 al methods and computational power\, medical imaging has been evolving r
 apidly from classical image visualization and post-processing to the ext
 raction of more subtle quantitative information about the organ/tissue at
  hand. This domain is now known as computational medical imaging. In thi
 s context\, I will present how the resolution of a regularized linear in
 verse problem can reveal unprecedented information in medical imaging. I 
 will first consider the relatively recent modality of diffusion Magnetic
  Resonance Imaging (MR)\, and show how we can extract unique information
  from the raw data by properly modeling the forward problem and carefully
  inverting it. Our work allows extracting information about the brain ti
 ssue architecture that is several orders of magnitude smaller than the M
 R imaging resolution\, leading to so-called brain microstructure analysis
 . I will also show how different MR contrasts can be used jointly to rec
 onstruct an even more complete picture of the tissue microstructure\, pa
 ving the way towards what I call MR microscopy. I will also show how th
 e same concepts apply to other medical imaging problems\, namely ultrasou
 nd image reconstruction and radiotherapy planning\, and I will finish by
  discussing how machine learning can contribute to this field.
LOCATION:ELA 2 https://plan.epfl.ch/?room==ELA%202
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR