Brain MRI study for glioma segmentation using convolutional neural networks and original post-processing techniques with low computational demand
This work addresses the challenge of segmenting heterogeneous brain tumors for improved medical diagnosis and treatment, representing an incremental advance by matching but not surpassing existing state-of-the-art performance.
The paper tackled glioma segmentation in brain MRI by proposing convolutional neural networks combined with original low-computational-demand post-processing techniques, achieving state-of-the-art results with Dice coefficients of 0.8934, 0.8376, and 0.8113 for whole tumor, tumor core, and enhancing tumor core, respectively.
Gliomas are brain tumors composed of different highly heterogeneous histological subregions. Image analysis techniques to identify relevant tumor substructures have high potential for improving patient diagnosis, treatment and prognosis. However, due to the high heterogeneity of gliomas, the segmentation task is currently a major challenge in the field of medical image analysis. In the present work, the database of the Brain Tumor Segmentation (BraTS) Challenge 2018, composed of multimodal MRI scans of gliomas, was studied. A segmentation methodology based on the design and application of convolutional neural networks (CNNs) combined with original post-processing techniques with low computational demand was proposed. The post-processing techniques were the main responsible for the results obtained in the segmentations. The segmented regions were the whole tumor, the tumor core, and the enhancing tumor core, obtaining averaged Dice coefficients equal to 0.8934, 0.8376, and 0.8113, respectively. These results reached the state of the art in glioma segmentation determined by the winners of the challenge.