Segmentation and Classification of Left Ventricular Abnormalities in Cardiac MRI Using Initial Point Prediction based Deformable Model

Authors

Md. Asadur Rahman, Military Institute of Science and TechnologyFollow
Md. Al Noman, Khulna University of Engineering & TechnologyFollow
A. B. M. Aowlad Hossain, Khulna University of Engineering & TechnologyFollow

Abstract

The shape of the left ventricle (LV) of a cardiac magnetic resonance image (CMRI) helps physicians to diagnose different cardiac abnormalities. The similarity of pixel intensity and shape of LV with neighbor tissues, the imprecision of boundaries, and the presence of noise are the challenges to accurate segmentation of LV. This paper contributes to the successful implementation of an automatic edge contouring method to segment LV area from CMRI and detect whether the ventricle belongs to abnormalities. This method proposes the regression-based artificial neural network to predict the possible initial position of the deformable edge-based active contour model for precise segmentation of the LV. Using the segmented shapes of the LV from a series of CMRI slices, LV volumes are estimated to find the end-diastole and end-systole volumes. From the volumetric features of normal LV as a reference, the proposed work decides the patient's abnormalities with their corresponding CMRI images. The proposed method has been applied to a renowned database and found an overall prediction accuracy of 85.7%, as well as the accuracy for abnormality detection, which is 92.9%. The result is convincing for clinical applications to replace the manual efforts in LV-related abnormalities detection from CMRI images.

Recommended Citation

Rahman, Md. Asadur; Noman, Md. Al; and Hossain, A. B. M. Aowlad (2023) "Segmentation and Classification of Left Ventricular Abnormalities in Cardiac MRI Using Initial Point Prediction based Deformable Model," Future Computing and Informatics Journal: Vol. 8: Iss. 2, Article 3.
Available at: https://digitalcommons.aaru.edu.jo/fcij/vol8/iss2/3