Brain CT registration using hybrid supervised convolutional neural network

• Published in: Biomedical engineering online Vol. 20; no. 1; p. 131
• Main Authors: Yuan, Hongmei, Yang, Minglei, Qian, Shan, Wang, Wenxin, Jia, Xiaotian, Huang, Feng
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 29.12.2021; BioMed Central; BMC
• Subjects: Accuracy; Algorithms; Artificial neural networks; Brain; Brain - diagnostic imaging; Brain CT; Brain mapping; Cerebrovascular disease; Cerebrovascular diseases; Computed tomography; CT imaging; Deep learning; Diagnosis; Elastic deformation; Error analysis; Health aspects; Humans; Hybrid supervision; Image Processing, Computer-Assisted; Image registration; Intersubject; Medical imaging; Methods; Neural networks; Neural Networks, Computer; Qualitative analysis; Registration; Soft tissues; Tissue analysis; Tomography, X-Ray Computed; China; Deep learning; Image registration; Hybrid supervision; Intersubject; Brain CT
• ISSN: 1475-925X; 1475-925X
• DOI: 10.1186/s12938-021-00971-8

Image registration is an essential step in the automated interpretation of the brain computed tomography (CT) images of patients with acute cerebrovascular disease (ACVD). However, performing brain CT registration accurately and rapidly remains greatly challenging due to the large intersubject anatomical variations, low resolution of soft tissues, and heavy computation costs. To this end, the HSCN-Net, a hybrid supervised convolutional neural network, was developed for precise and fast brain CT registration. HSCN-Net generated synthetic deformation fields using a simulator as one supervision for one reference-moving image pair to address the problem of lack of gold standards. Furthermore, the simulator was designed to generate multiscale affine and elastic deformation fields to overcome the registration challenge posed by large intersubject anatomical deformation. Finally, HSCN-Net adopted a hybrid loss function constituted by deformation field and image similarity to improve registration accuracy and generalization capability. In this work, 101 CT images of patients were collected for model construction (57), evaluation (14), and testing (30). HSCN-Net was compared with the classical Demons and VoxelMorph models. Qualitative analysis through the visual evaluation of critical brain tissues and quantitative analysis by determining the endpoint error (EPE) between the predicted sparse deformation vectors and gold-standard sparse deformation vectors, image normalized mutual information (NMI), and the Dice coefficient of the middle cerebral artery (MCA) blood supply area were carried out to assess model performance comprehensively. HSCN-Net and Demons had a better visual spatial matching performance than VoxelMorph, and HSCN-Net was more competent for smooth and large intersubject deformations than Demons. The mean EPE of HSCN-Net (3.29 mm) was less than that of Demons (3.47 mm) and VoxelMorph (5.12 mm); the mean Dice of HSCN-Net was 0.96, which was higher than that of Demons (0.90) and VoxelMorph (0.87); and the mean NMI of HSCN-Net (0.83) was slightly lower than that of Demons (0.84), but higher than that of VoxelMorph (0.81). Moreover, the mean registration time of HSCN-Net (17.86 s) was shorter than that of VoxelMorph (18.53 s) and Demons (147.21 s). The proposed HSCN-Net could achieve accurate and rapid intersubject brain CT registration.