Abstract
Among all body organs heart is a one of the most vital of organs of human body. Dysfunction of heart function even for a couple of moments can be fatal, therefore, efficient monitoring of its physiological state is essential for the patients with cardiovascular diseases. In the recent past, various computer assisted medical imaging systems have been proposed for the segmentation of the organ of interest. However, for the segmentation of heart using MRI, only few methods have been proposed each with its own merits and demerits. For further advancement in this area of research, we analyze automated heart segmentation methods for magnetic resonance images. The analysis are based on deep learning methods that processes a full MR scan in a slice by slice fashion to predict desired mask for heart region. We design two encoder-decoder type fully convolutional neural network models (1) Multi-Channel input scheme (also known as 2.5D method), (2) a single channel input scheme with relatively large size network. Both models are evaluated on real MRI dataset and their performances are analysed for different test samples on standard measures such as Jaccard score, Youden's index and Dice score etc. Python implementation of our code is made publicly available at https://github.com/Shak97/iceest2019 for performance evaluation.