Slice-Level-Guided Convolutional Neural Networks to study the Right Ventricular Segmentation using MRI Short-Axis sequences

The cardiac right ventricle has a vital role in the cardiac cycle. To assess its function using Magnetic Resonance Imaging (MRI), the segmentation is an important task, but it is challenged by the complex shape of this cavity, its thin borders, and shape variability. Accordingly, several approaches have been proposed to overcome these issues. Yet, a significant divergence of precision still appears among the spatial slices. In this paper, we attempt to study the impact of short-axis slices from base to apex on the segmentation process. First, a comparative study is enabled to assess the segmentation quality among these slices using a U-Net- based convolutional neural network. Two public labelled datasets are exploited with our prepared data to allow the training process. The dice-coefficient assessment of each slice-level exhibits a significant accuracy decrease for the basal and apical slices. Next, a personalized investigation is carried out for each slice level apart. Accordingly, three sub-sets are retrieved from the initial training set regrouping slices into basal, central, and apical. Furthermore, to monitor the segmentation behaviour using these sub-datasets, different U-Net-based models are trained and evaluated. The obtained results show that the central slices scores enhanced from 0.87 to 0.92 using slice-level based. On the other hand, basal and apical slices obtained higher results using the global dataset.