Development of Softcomputing Tool to Evaluate Heart MRI Slices

Abstract

Magnetic Resonance Imaging (MRI) is a common imaging procedure widely adopted in hospitals to examine the disease in internal organs. Compared to other imaging techniques, MRI can be recorded with a variety of modalities, such as Flair, T1, T1C, T2, Diffused Weighting (DW) and fMRI. Further, it can provide a reconstructed Three-Dimensional (3D) view of the internal organ under study. In this work, a hybrid approach based on the combination of thresholding and segmentation is implemented to examine the congenital heart defect using the Heart MRI (HMRI) recorded using T2 modality. The thresholding is implemented with Differential Evolution (DE) based Shannon's Entropy (SE) and the segmentation are implemented using the Level Set (LS). In this work, the axial view of the HMRI images of the HVSMR 2016benchmark dataset is considered for the analysis. The main aim of this work is to extract the Region Of Interest (ROI) from the HMRI and compare the extracted section with the Ground Truth (GT) images. The experimental investigation of the proposed work confirms that, proposed work offers enhanced average image similarity values (> 88%) on the considered dataset.