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

TL;DR

This paper introduces EVAC+, a novel multi-scale deep learning architecture with CRF layers for robust brain extraction from MRI, achieving high accuracy with limited training data and minimal architectural modifications.

Contribution

EVAC+ combines multi-scale inputs, a specialized loss function, and CRF layers to improve brain extraction robustness and accuracy with less training data and simpler architecture.

Findings

Achieves high Dice and Jaccard scores compared to state-of-the-art methods.

Maintains stable performance with limited training data.

Reduces segmentation errors in complex brain regions.

Abstract

Brain extraction is one of the first steps of pre-processing 3D brain MRI data and a prerequisite for any forthcoming brain imaging analyses. However, it is not a simple segmentation problem due to the complex structure of the brain and human head. Although multiple solutions have been proposed in the literature, we are still far from having truly robust methods. While previous methods have used machine learning with structural/geometric priors, with the development of Deep Learning (DL), there has been an increase in proposed Neural Network architectures. Most models focus on improving the training data and loss functions with little change in the architecture. However, the amount of accessible training data with expert-labelled ground truth vary between groups. Moreover, the labels are created not from scratch but from outputs of non-DL methods. Thus, most DL method's performance depend on the amount and quality of data one has. In this paper, we propose a novel architecture we call EVAC+ to work around this issue. We show that EVAC+ has 3 major advantages compared to other networks: (1) Multi-scale input with limited random augmentation for efficient learning, (2) a unique way of using Conditional Random Fields Recurrent Layer and (3) a loss function specifically created to enhance this architecture. We compare our model to state-of-the-art non-DL and DL methods. Results show that even with little change in the traditional architecture and limited training resources, EVAC+ achieves a high and stable Dice Coefficient and Jaccard Index along with a desirable lower surface distance. Ultimately, our model provides a robust way of accurately reducing segmentation errors in complex multi-tissue interfacing areas of brain.