AUTHOR=Banerjee Subhashis , Mitra Sushmita 

TITLE=Novel Volumetric Sub-region Segmentation in Brain Tumors

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 14 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2020.00003

DOI=10.3389/fncom.2020.00003

ISSN=1662-5188

ABSTRACT=A novel deep learning based model called Multi-Planar Spatial Convolutional Neural Network (MPS-CNN) is proposed for effective, automated segmentation of different sub-regions \textit{viz.} peritumoral edema ($ED$), necrotic core ($NCR$), enhancing and non-enhancing tumor core ($ET / NET$), from multi-modal MR images of the brain. An encoder-decoder type CNN model is designed for pixel-wise segmentation of the tumor along three anatomical planes (axial, sagittal and coronal) at the slice level. These are then combined, by incorporating a consensus fusion strategy with a fully connected Conditional Random Field (CRF) based post refinement, to produce the final volumetric segmentation of the tumor and its constituent sub-regions. Concepts such as spatial-pooling and unpooling are \st{introduced} used to preserve the spatial locations of the edge pixels, for reducing segmentation error around the boundaries. A new aggregated loss function is also developed for effectively handling data imbalance. The MPS-CNN is trained and validated on the recent  Multimodal Brain Tumor Segmentation Challenge (BraTS) 2018 dataset. The Dice scores obtained for the validation set for whole tumor ($WT:  NCR/NE + ET + ED$), tumor core ($TC: NCR/NET + ET$) and enhancing tumor ($ET$) are  $0.90216$, $0.87247$ and $0.82445$. The proposed MPS-CNN is found to perform the best (based on leaderboard scores) for $ET$ and $TC$ segmentation tasks, in terms of both the quantitative measures (\textit{viz.} Dice and Hausdorff). In case of the $WT$ segmentation it also achieved the second highest accuracy, with a score which was only $1 \%$ less than that of the best performing method.