Automatic brain extraction from 3D fetal MR image with deep learning-based multi-step framework. (March 2021)

• Record Type: Journal Article
• Authors: Chen, Jian; Fang, Zhenghan; Zhang, Guofu; Ling, Lei; Li, Gang; Zhang, He; Wang, Li
• Is Part Of: Computerized medical imaging and graphics. Volume 88(2021)
• Publication Date: 2021-03
• Subjects: Fetal MRI -- Brain extraction -- Densely-connected U-Net -- Fusion network -- Extraction; 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.2020.101848
• Languages: English
• ISSNs: 0895-6111

Abstract

Highlights: A global localization network and a local refinement network are proposed for brain extraction from 3D fetal MR image. A fusion network is proposed to fuse the probability maps from different networks. Our method achieves good performance on some abnormal fetal MRI. Abstract: Brain extraction is a fundamental prerequisite step in neuroimage analysis for fetus. Due to surrounding maternal tissues and unpredictable movement, brain extraction from fetal Magnetic Resonance (MR) images is a challenging task. In this paper, we propose a novel deep learning-based multi-step framework for brain extraction from 3D fetal MR images. In the first step, a global localization network is applied to estimate probability maps for brain candidates. Connected-component labeling algorithm is applied to eliminate small erroneous components and accurately locate the candidate brain area. In the second step, a local refinement network is implemented in the brain candidate area to obtain fine-grained probability maps. Final extraction results are derived by a fusion network with the two cascaded probability maps obtained from previous two steps. Experimental results demonstrate that our proposed method has superior performance compared with existing deep learning-based methods.