3D hemisphere-based convolutional neural network for whole-brain MRI segmentation. (January 2022)

• Record Type: Journal Article
• Authors: Yee, Evangeline; Ma, Da; Popuri, Karteek; Chen, Shuo; Lee, Hyunwoo; Chow, Vincent; Ma, Cydney; Wang, Lei; Beg, Mirza Faisal
• Is Part Of: Computerized medical imaging and graphics. Volume 95(2022)
• Publication Date: 2022-01
• Subjects: MRI -- Segmentation -- 3D CNN; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2021.102000
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract: Whole-brain segmentation is a crucial pre-processing step for many neuroimaging analyses pipelines. Accurate and efficient whole-brain segmentations are important for many neuroimage analysis tasks to provide clinically relevant information. Several recently proposed convolutional neural networks (CNN) perform whole brain segmentation using individual 2D slices or 3D patches as inputs due to graphical processing unit (GPU) memory limitations, and use sliding windows to perform whole brain segmentation during inference. However, these approaches lack global and spatial information about the entire brain and lead to compromised efficiency during both training and testing. We introduce a 3D hemisphere-based CNN for automatic whole-brain segmentation of T1-weighted magnetic resonance images of adult brains. First, we trained a localization network to predict bounding boxes for both hemispheres. Then, we trained a segmentation network to segment one hemisphere, and segment the opposing hemisphere by reflecting it across the mid-sagittal plane. Our network shows high performance both in terms of segmentation efficiency and accuracy (0.84 overall Dice similarity and 6.1 mm overall Hausdorff distance) in segmenting 102 brain structures. On multiple independent test datasets, our method demonstrated a competitive performance in the subcortical segmentation task and a high consistency in volumetric measurements of intra-session scans.