ACEnet: Anatomical Context-Encoding Network for Neuroanatomy Segmentation
This addresses the need for efficient and accurate neuroanatomy segmentation in medical imaging, though it is incremental as it builds on existing 2D methods by adding context modules.
The paper tackled the problem of brain structure segmentation from MR scans by developing ACEnet, a 2D CNN that incorporates 3D spatial and anatomical contexts to improve accuracy while maintaining computational efficiency, achieving promising performance on three benchmark datasets.
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.