Multi-resolution 3D CNN for MRI Brain Tumor Segmentation and Survival Prediction

Abstract

In this study, an automated three dimensional (3D) deep segmentation approach for detecting gliomas in 3D pre-operative MRI scans is proposed. Then, a classification algorithm based on random forests, for survival prediction is presented. The objective is to segment the glioma area and produce segmentation labels for its different sub-regions, i.e. necrotic and the non-enhancing tumor core, the peritumoral edema, and enhancing tumor. The proposed deep architecture for the segmentation task encompasses two parallel streamlines with two different resolutions. One deep convolutional neural network is to learn local features of the input data while the other one is set to have a global observation on whole image. Deemed to be complementary, the outputs of each stream are then merged to provide an ensemble complete learning of the input image. The proposed network takes the whole image as input instead of patch-based approaches in order to consider the semantic features throughout the whole volume. The algorithm is trained on BraTS 2019 which included 335 training cases, and validated on 127 unseen cases from the validation dataset using a blind testing approach. The proposed method was also evaluated on the BraTS 2019 challenge test dataset of 166 cases. The results show that the proposed methods provide promising segmentations as well as survival prediction. The mean Dice overlap measures of automatic brain tumor segmentation for validation set were 0.86, 0.77 and 0.71 for the whole tumor, core and enhancing tumor, respectively. The corresponding results for the challenge test dataset were 0.82, 0.72, and 0.70, respectively. The overall accuracy of the proposed model for the survival prediction task is 55% for the validation and 49% for the test dataset.