Data-Driven Feature Learning for Myocardial Segmentation of CP-BOLD MRI

Anirban Mukhopadhyay, Ilkay Oksuz*, Marco Bevilacqua, Rohan Dharmakumar, Sotirios A. Tsaftaris

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Cardiac Phase-resolved Blood Oxygen-Level-Dependent (CP-BOLD) MR is capable of diagnosing an ongoing ischemia by detecting changes in myocardial intensity patterns at rest without any contrast and stress agents. Visualizing and detecting these changes require significant post-processing, including myocardial segmentation for isolating the myocardium. But, changes in myocardial intensity pattern and myocardial shape due to the heart's motion challenge automated standard CINE MR myocardial segmentation techniques resulting in a significant drop of segmentation accuracy. We hypothesize that the main reason behind this phenomenon is the lack of discernible features. In this paper, a multi scale discriminative dictionary learning approach is proposed for supervised learning and sparse representation of the myocardium, to improve the myocardial feature selection. The technique is validated on a challenging dataset of CP-BOLD MR and standard CINE MR acquired in baseline and ischemic condition across 10 canine subjects. The proposed method significantly outperforms standard cardiac segmentation techniques, including segmentation via registration, level sets and supervised methods for myocardial segmentation.

Original languageEnglish
Title of host publicationFUNCTIONAL IMAGING AND MODELING OF THE HEART (FIMH 2015)
EditorsH VanAssen, P Bovendeerd, T Delhaas
PublisherSpringer-Verlag Berlin Heidelberg
Pages189-197
Number of pages9
ISBN (Print)978-3-319-20308-9
DOIs
Publication statusPublished - 2015
Externally publishedYes
Event8th International Conference on Functional Imaging and Modeling of the Heart(FIMH) - Maastricht, Netherlands
Duration: 25 Jun 201527 Jun 2015

Publication series

NameLecture Notes in Computer Science
PublisherSPRINGER-VERLAG BERLIN
Volume9126
ISSN (Print)0302-9743

Conference

Conference8th International Conference on Functional Imaging and Modeling of the Heart(FIMH)
Country/TerritoryNetherlands
Period25/06/1527/06/15

Keywords / Materials (for Non-textual outputs)

  • Dictionary learning
  • CP-BOLD MR
  • CINE MR
  • Segmentation
  • SPARSE REPRESENTATION
  • REGISTRATION
  • IMAGES
  • TRACKING

Fingerprint

Dive into the research topics of 'Data-Driven Feature Learning for Myocardial Segmentation of CP-BOLD MRI'. Together they form a unique fingerprint.

Cite this