BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Biomedical Image Analysis: Models and Methods for 
 Reverse-engineering the Worm
DTSTART:20150319T101500
DTEND:20150319T113000
DTSTAMP:20260408T033620Z
UID:6abdf08d7685499a55e1840fc56664e2c7b95c551cc2b9b477a50f84
CATEGORIES:Conferences - Seminars
DESCRIPTION:By : Dagmar Kainmueller - MPI-CBG\nIC Faculty candidateAbstrac
 t :\nBiomedical image analysis tasks like segmentation and tracking are co
 mmonly approached by (1) modeling the task by means of an optimization pro
 blem\, and (2) solving the optimization problem by an appropriate inferenc
 e method. The respective objective function typically combines prior knowl
 edge about the sought object\, like e.g. its shape\, appearance and dynami
 cs\, with cues obtained from the observed image data.\nIn my talk I will e
 xplore how capturing prior knowledge is vital for successful automation of
  challenging biomedical image analysis tasks. I will showcase a range of s
 uch tasks I have tackled. I will focus in detail on the task of segmenting
  and annotating (i.e. labeling) cell nuclei in the nematode worm C. Elegan
 s in 3d microscopic images.\nAutomated segmentation and annotation of nucl
 ei in C. Elegans is essential for the biological goal of "reverse engineer
 ing" how the DNA of the worm encodes its development. The model I will pre
 sent for this task integrates the popular active shape models into a spars
 e graph matching objective\, hence combining the benefits of global and lo
 cal prior statistical shape models. Together with a novel inference method
  this model allows for fully automatic simultaneous segmentation and annot
 ation of nuclei with unprecedented accuracy.Bio :\nDagmar Kainmueller is a
  computer scientist working on biomedical image analysis. She is currently
  an ELBE postdoctoral researcher in Gene Myers' lab at the Max Planck Inst
 itute of Molecular Cell Biology and Genetics\, where she investigates prio
 r models\, machine learning and inference techniques for accurate automati
 c analysis of microscopic images. \nDagmar studied computer science at th
 e University of Karlsruhe\, and obtained her PhD in medical image analysis
  from the University of Luebeck and Zuse-Institute Berlin in 2013. For her
  thesis she received the BVM award from the German society for image proce
 ssing in medicine. With her methods she won a series of MICCAI Grand Chall
 enges\, among which the liver segmentation challenge in 2007. Her respecti
 ve method to date still ranks first on benchmark data.More information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR