BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Variational Methods for Medical Ultrasound Imaging - Daniel Tenbri
 nck (Universität Münster)
DTSTART:20130821T133000Z
DTEND:20130821T140000Z
UID:TALK46823@talks.cam.ac.uk
CONTACT:Carola-Bibiane Schoenlieb
DESCRIPTION:Automated image processing of medical ultrasound images offers
  great challenges for computer vision due to the impact of physical noise 
 phenomena\, e.g.\, the characteristical speckle noise. In this talk three 
 different concepts are proposed to tackle these problems with the help of 
 variational methods in the context of automated image segmentation. On the
  one hand\, segmentation is formulated as a statistically motivated invers
 e problem based on Bayesian modeling. In contrast to this exact modeling o
 f noise distributions\, an alternative approach based on level set methods
  is elaborated subsequently\, which performs segmentation based on the res
 ults of a discriminant analysis of medical ultrasound images. Motivated by
  the presence of structural artifacts in the data\, e.g.\, shadowing effec
 ts\, the latter two segmentation methods are extended by a shape prior bas
 ed on Legendre moments in order to give additional support in terms of tra
 ined knowledge about expected shapes. The proposed methods are compared qu
 alitatively and quantitatively on real patient data from echocardiography.
  
LOCATION:MR11\, Centre for Mathematical Sciences
END:VEVENT
END:VCALENDAR