ACEnet: Anatomical Context-Encoding Network for Neuroanatomy Segmentation

TL;DR

ACEnet introduces a novel approach that enhances 2D CNNs with 3D anatomical and spatial context encoding, significantly improving brain structure segmentation accuracy and efficiency in MR scans.

Contribution

The paper presents ACEnet, a new network that effectively incorporates 3D contextual information into 2D CNNs for brain segmentation, addressing computational challenges.

Findings

Achieves superior segmentation accuracy compared to existing methods.

Maintains high computational efficiency with 2D CNNs.

Demonstrates robustness across multiple benchmark datasets.

Abstract

Segmentation of brain structures from magnetic resonance (MR) scans plays an important role in the quantification of brain morphology. Since 3D deep learning models suffer from high computational cost, 2D deep learning methods are favored for their computational efficiency. However, existing 2D deep learning methods are not equipped to effectively capture 3D spatial contextual information that is needed to achieve accurate brain structure segmentation. In order to overcome this limitation, we develop an Anatomical Context-Encoding Network (ACEnet) to incorporate 3D spatial and anatomical contexts in 2D convolutional neural networks (CNNs) for efficient and accurate segmentation of brain structures from MR scans, consisting of 1) an anatomical context encoding module to incorporate anatomical information in 2D CNNs and 2) a spatial context encoding module to integrate 3D image information in 2D CNNs. In addition, a skull stripping module is adopted to guide the 2D CNNs to attend to the brain. Extensive experiments on three benchmark datasets have demonstrated that our method achieves promising performance compared with state-of-the-art alternative methods for brain structure segmentation in terms of both computational efficiency and segmentation accuracy.