Direct Segmentation-based Full Quantification for Left Ventricle via Deep Multi-task Regression Learning Network

Quantitative analysis of the heart is extremely necessary and significant for detecting and diagnosing heart disease, yet there are still some challenges such as the high variability of cardiac structure and the complexity of temporal dynamics. In this study, we propose a new end-to-end segmentation-based deep multi-task regression learning model (Indices-JSQ) to make a holonomic quantitative analysis of the left ventricle (LV), which contains a segmentation network (Img2Contour) and multi-task regression network (Contour2Indices). First of all, Img2Contour, which contains a deep convolutional encoder-decoder module, is designed to obtain the LV contour. Then, the predicted contour is feed as input to the next deep multi-task learning network (Contour2Indices) for full quantification. On the whole, we take into account the relationship between different tasks, which can serve as a complementary advantage. Meanwhile, instead of using images directly from the original dataset, we creatively use the segmented contour of the original image to estimate the cardiac indices to achieve better and more accurate results. We make experiments on MR sequences of 145 subjects and gain the experimental results of 157 mm2, 2.43 mm, 1.29 mm, and 0.87 on areas, dimensions, regional wall thicknesses (RWTs), and Dice Metric (DM), respectively. It intuitively shows that the proposed method outperforms the other state-of-the-art methods and demonstrates that our method has a great potential in cardiac MR images segmentation, comprehensive clinical assessment, and diagnosis.