Automated Cardiac-Tissue Identification in Composite Strain-Encoded (C-SENC) Images Using Fuzzy K-Means and Bayesian Classifier
Composite Strain Encoding (C-SENC) is an MRIacquisition technique for simultaneous acquisition of cardiactissue viability and contractility images. It combines the use ofblack-blood delayed-enhancement imaging to identify theinfracted (dead) tissue inside the heart wall muscle and the abilityto image myocardial deformation (MI) from the strain-encoding(SENC) imaging technique. In this work, we propose anautomatic image processing technique to identify the differentheart tissues. This provides physicians with a better clinicaldecision-making tool in patients with myocardial infarction. Thetechnique is based on using Bayesian classifier to identify thebackground regions in the C-SENC images, and fuzzy clusteringtechnique to identify the different types of the heart tissues. Theproposed method is tested using numerical simulations of theheart C-SENC images with MI and real images of patients. Theresults show that the proposed technique is able to identify thedifferent components of the image with a high accuracy.
Abdallah G.Motaal Neamat El-Gayar Nael F.Osman
Center for Informatics Sciences Nile University Cairo, Egypt Radiology Department School of Medicine, Johns Hopkins University Baltimore, MD, USA
国际会议
成都
英文
1-4
2010-06-18（万方平台首次上网日期，不代表论文的发表时间）