Automatic segmentation of CMRIs for LV contour detection

• Main Authors: Amjad, Khan, Dayang Nurfatimah F, Awang Iskandar, Hamimah, Ujir, Chai, Wangyin
• Format: Article
• Language: English
• Published: Springer Verlag 2017
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://ir.unimas.my/id/eprint/14939/2/Automatic%20segmentation.pdf; http://ir.unimas.my/id/eprint/14939/; https://www.scopus.com/inward/record.uri?eid=2-s2.0-84992724603&doi=10.1007%2f978-981-10-1721-6_34&partnerID=40&md5=02af1bc3ac27506ed80138904d694742

Research on detecting, recognising and interpreting cardiovascular magnetic resonance images (CMRIs) has started since the 1980s. Time consuming and the need of expert evaluation are the key problems in the manual tracing efforts of CMRIs in a routine investigation. CMRIs manual tracing is also dependent on image quality, and there is no one-size-fits-all MRI setting for an optimum image result. In this paper, we present an approach using 2-Standard Division (2-SD) correlation along with the Sum of Absolute Difference technique and Otsu Watershed to automatically detect the left ventricle (LV) wall and blood pool in the effort to automatically assist the assessment of cardiac function. We test the approach using the Sunnybrook Cardiac Data, a standard benchmark dataset. The results shown that the proposed method had improved the automatic detection of the epicardium and endocardium