FRANÇAIS
A showcase of ÉTS researchers’ publications and other contributions
SEARCH

A convex max-flow segmentation of LV using subject-specific distributions on cardiac MRI

Downloads

Downloads per month over past year

Nambakhsh, Mohammad Saleh, Yuan, Jing, Ben Ayed, Ismail, Punithakumar, Kumaradevan, Goela, Aashish, Islam, Ali, Peters, Terry et Li, Shuo. 2011. « A convex max-flow segmentation of LV using subject-specific distributions on cardiac MRI ». In Information Processing in Medical Imaging. 22nd International Conference, IPMI 2011, Kloster Irsee, Germany, July 3-8, 2011. Proceedings (Kloster Irsee, Germany, July 3-8, 2011) Coll. « Lecture Notes in Computer Science », vol. 6801. pp. 171-183. Springer Verlag.
Compte des citations dans Scopus : 4.

[thumbnail of Ben Ayed I 2011 10557 A convex max-flow segmentation of LV using subject-specific distributions on cardiac MRI.pdf]
Preview
PDF
Ben Ayed I 2011 10557 A convex max-flow segmentation of LV using subject-specific distributions on cardiac MRI.pdf

Download (382kB) | Preview

Abstract

This work studies the convex relaxation approach to the left ventricle (LV) segmentation which gives rise to a challenging multi-region seperation with the geometrical constraint. For each region, we consider the global Bhattacharyya metric prior to evaluate a gray-scale and a radial distance distribution matching. In this regard, the studied problem amounts to finding three regions that most closely match their respective input distribution model. It was previously addressed by curve evolution, which leads to sub-optimal and computationally intensive algorithms, or by graph cuts, which result in heavy metrication errors (grid bias). The proposed convex relaxation approach solves the LV segmentation through a sequence of convex sub-problems. Each sub-problem leads to a novel bound of the Bhattacharyya measure and yields the convex formulation which paves the way to build up the efficient and reliable solver. In this respect, we propose a novel flow configuration that accounts for labelingfunction variations, in comparison to the existing flow-maximization configurations. We show it leads to a new convex max-flow formulation which is dual to the obtained convex relaxed sub-problem and does give the exact and global optimums to the original non-convex sub-problem. In addition, we present such flow perspective gives a new and simple way to encode the geometrical constraint of optimal regions. A comprehensive experimental evaluation on sufficient patient subjects demonstrates that our approach yields improvements in optimality and accuracy over related recent methods.

Item Type: Conference proceeding
ISBN: 03029743
Editors:
Editors
ORCID
Székely, Gábor
UNSPECIFIED
Hahn, Horst K.
UNSPECIFIED
Professor:
Professor
Ben Ayed, Ismail
Affiliation: Autres
Date Deposited: 11 Sep 2015 15:38
Last Modified: 29 Jan 2016 01:58
URI: https://espace2.etsmtl.ca/id/eprint/10557

Actions (login required)

View Item View Item