Enhanced brain parcellation via abnormality inpainting for neuroimage-based consciousness evaluation of hydrocephalus patients by lumbar drainage

• Published in: Brain informatics Vol. 10; no. 1; pp. 3 - 15
• Main Authors: Zang, Di, Zhao, Xiangyu, Qiao, Yuanfang, Huo, Jiayu, Wu, Xuehai, Wang, Zhe, Xu, Zeyu, Zheng, Ruizhe, Qi, Zengxin, Mao, Ying, Zhang, Lichi
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2023; Springer; Springer Nature B.V; SpringerOpen
• Subjects: Artificial Intelligence; Biomarkers; Brain; Brain parcellation; Cerebrospinal fluid; Cognitive Psychology; Computation by Abstract Devices; Computer Science; Consciousness; Deformation effects; Drainage; Health Informatics; Hydrocephalus; Magnetic resonance imaging; Medical imaging; Network analysis; Neurophysiology; Neurosciences; Structural imaging; Synthesis; Traumatic brain injury; China; Brain parcellation; Traumatic brain injury; Hydrocephalus; Consciousness; Structural imaging
• ISSN: 2198-4018; 2198-4026
• DOI: 10.1186/s40708-022-00181-5

Brain network analysis based on structural and functional magnetic resonance imaging (MRI) is considered as an effective method for consciousness evaluation of hydrocephalus patients, which can also be applied to facilitate the ameliorative effect of lumbar cerebrospinal fluid drainage (LCFD). Automatic brain parcellation is a prerequisite for brain network construction. However, hydrocephalus images usually have large deformations and lesion erosions, which becomes challenging for ensuring effective brain parcellation works. In this paper, we develop a novel and robust method for segmenting brain regions of hydrocephalus images. Our main contribution is to design an innovative inpainting method that can amend the large deformations and lesion erosions in hydrocephalus images, and synthesize the normal brain version without injury. The synthesized images can effectively support brain parcellation tasks and lay the foundation for the subsequent brain network construction work. Specifically, the novelty of the inpainting method is that it can utilize the symmetric properties of the brain structure to ensure the quality of the synthesized results. Experiments show that the proposed brain abnormality inpainting method can effectively aid the brain network construction, and improve the CRS-R score estimation which represents the patient’s consciousness states. Furthermore, the brain network analysis based on our enhanced brain parcellation method has demonstrated potential imaging biomarkers for better interpreting and understanding the recovery of consciousness in patients with secondary hydrocephalus.