Location aware tumor segmentation on `MRI images

Abstract

In our research, we introduce an innovative approach to the segmentation of braintumors, utilizing a convolutional neural network (CNN) architecture that incorporateslocalization awareness. This approach represents a significant advancementin tumor segmentation, as it effectively addresses two critical challenges encounteredin this field: limited resources and the requirement for precise localization.To overcome these challenges, our methodology leverages 2D slices duringtraining and integrates registration operations for MRI images during application.The proposed method is evaluated extensively on the BRATS-2018 dataset andits augmented dataset version, encompassing distinct variations of CNN-basedmodels. Furthermore, it exhibits computational efficiency during inference, enablingthe segmentation of the entire brain in a matter of seconds. The outcomes ofour research position our deep learning model as a promising tool with immensepotential for both research purposes and clinical applications, offering good segmentationoutcomes.