EVAC+: Multi-scale V-net with Deep Feature CRF Layers for Brain Extraction

Abstract Brain extraction is an indispensable computational necessity for all researchers using brain imaging data. However, the complex structure of the interfaces between the brain, meninges and human skull have not allowed a highly robust solution to emerge. While previous methods have used machine learning with structural and geometric priors in mind, with the development of Deep Learning (DL), there has been an increase in proposed Neural Network architectures to solve such problems. Most DL approaches focus on improving the training data with little change in the DL architecture. However, the amount and quality of accessible training data with expert-labeled ground truth varies between groups. Thus, the performance of many methods heavily depends on the amount and quality of training data. In this paper, we propose a novel architecture we call EVAC+. EVAC+ has 3 characteristics to work around this major issue: (1) a smart augmentation strategy that improves training efficiency, (2) a unique way of using a Conditional Random Fields Recurrent Layer that improves accuracy and (3) a new loss function that fine-tunes the segmentation output. We compare our model to state-of-the-art non-DL and DL methods. Results show that even with limited training resources, EVAC+ outperforms in most cases, achieving a high and stable Dice Coefficient and Jaccard Index along with a desirable lower Surface (Hausdorff) Distance. More importantly, our approach accurately segmented clinical and pediatric data, despite the fact that the training dataset only contains healthy adults. Ultimately, our model provides a reliable way of accurately reducing segmentation errors in complex multi-tissue interfacing areas of the brain. We expect our method, which is publicly available and open-source, to be beneficial to a wide range of researchers.