Similarity attention-based CNN for robust 3D medical image registration. (March 2023)

• Record Type: Journal Article
• Authors: Zhu, Fei; Wang, Sheng; Li, Dun; Li, Qiang
• Is Part Of: Biomedical signal processing and control. Volume 81(2023)
• Publication Date: 2023-03
• Subjects: Convolutional neural network -- Medical image registration -- Similarity -- Attention -- Multi-scale; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104403
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The similarity-based local attention is proposed for learning-based registration. The multi-scale structure is combined with the similarity attention to build CNN. Our method provides higher registration accuracy than the compared methods. Abstract: In recent years, deep learning (DL)-based registration technology has significantly improved the calculation speed of medical image registration. Existing DL-based registration methods generally use raw data features to predict the deformation field. However, this strategy may not be very effective for difficult registration tasks. Hence, in this study, we propose a similarity attention-based convolutional neural network (CNN) for accurate and robust three-dimensional medical image registration. We first introduce a similarity-based local attention model as an auxiliary module for building a displacement searching space, instead of a direct displacement prediction based on raw data. The proposed model can help the network focus on spatial correspondences with high similarities and ignore those with low similarities. A multi-scale CNN is then integrated with the similarity-based local attention for providing non-local attention, lightweight network, and coarse-to-fine registration. We evaluated the proposed method for various applications, such as the registration of large-scope abdominal computerized tomography (CT) images and chest CT images acquired at different respiratory phases, and atlas registration in magnetic resonance imaging. The experimental results demonstrate that the proposed method can provide a more accurate and robust registration performance than state-of-the-art registration methods.