Appearance based Spatiotemporal Constraint for LV Segmentation in 4D Cardiac SPECT

Yang Ronghua, Majid Mirmehdi, Xie Xianghua, Hall David

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

We propose a novel appearance based spatiotemporal constraint and combine it with a level set based deformable model, which can be used for Left Ventricle segmentation in 4D gated cardiac SPECT, particularly in the presence of perfusion defects. Unlike current shape based constraint works, ours incorporates texture in addition to shape information into a probabilistic constraint, and utilizes spatiotemporal regularization via a Maximum A Posteriori framework. We present comparative results to illustrate the improvement gain.
Original languageEnglish
Title of host publicationMICCAI Workshop on Cardiovascular Intervetional Imaging and Biophysical Modelling
Publication statusPublished - 2009

Bibliographical note

Other page information: 84-93
Conference Proceedings/Title of Journal: MICCAI Workshop on Cardiovascular Intervetional Imaging and Biophysical Modelling
Other identifier: 2001036

Fingerprint Dive into the research topics of 'Appearance based Spatiotemporal Constraint for LV Segmentation in 4D Cardiac SPECT'. Together they form a unique fingerprint.

  • Cite this

    Ronghua, Y., Mirmehdi, M., Xianghua, X., & David, H. (2009). Appearance based Spatiotemporal Constraint for LV Segmentation in 4D Cardiac SPECT. In MICCAI Workshop on Cardiovascular Intervetional Imaging and Biophysical Modelling http://www.cs.bris.ac.uk/Publications/pub_master.jsp?id=2001036