Campus Event Calendar
Event Entry
What and Who
A Learning Based Hierarchical Model for Vessel Segmentation
Richard Socher
IMPRS
Talk/Masterseminar
AG 1, AG 2, AG 3, AG 4, AG 5, SWS, RG1, RG2
Public Audience
English
Note: We use this to send email in the morning.
Date, Time and Location
Tuesday, 15 January 2008
13:15
45 Minutes
E1 4
024
Saarbrücken
Abstract
I present a learning based method for vessel segmentation in
angiographic videos. Vessel Segmentation is an important task in medical
imaging and has been investigated extensively in the past. Traditional
approaches often require pre-processing steps, standard conditions or
manually set seed points. Our method is completely automatic, fast,
robust towards noise often seen in low radiation X-ray images and can be
easily trained and used for any kind of tubular structure. We formulate
the segmentation task as a hierarchical learning problem over 3 levels:
border points, crosssegments and vessel pieces, corresponding to the
vessel's position, width and length. Following the Marginal Space
Learning paradigm, the detection on each level is performed by a learned
classifier. We use Probabilistic Boosting Trees with Haar and steerable
features. First results of segmenting the vessel which surrounds a guide
wire in 200 frames are presented and future additions are discussed.
angiographic videos. Vessel Segmentation is an important task in medical
imaging and has been investigated extensively in the past. Traditional
approaches often require pre-processing steps, standard conditions or
manually set seed points. Our method is completely automatic, fast,
robust towards noise often seen in low radiation X-ray images and can be
easily trained and used for any kind of tubular structure. We formulate
the segmentation task as a hierarchical learning problem over 3 levels:
border points, crosssegments and vessel pieces, corresponding to the
vessel's position, width and length. Following the Marginal Space
Learning paradigm, the detection on each level is performed by a learned
classifier. We use Probabilistic Boosting Trees with Haar and steerable
features. First results of segmenting the vessel which surrounds a guide
wire in 200 frames are presented and future additions are discussed.
Contact
IMPRS
9325-225
--email hidden
passcode not visible
logged in users only
Andrea Primm, 01/10/2008 11:15
Andrea Primm, 11/29/2007 09:29
Andrea Primm, 10/25/2007 11:48
Andrea Primm, 10/16/2007 13:16 -- Created document.
Andrea Primm, 11/29/2007 09:29
Andrea Primm, 10/25/2007 11:48
Andrea Primm, 10/16/2007 13:16 -- Created document.