LAUSR

BACKGROUND Image registration has long been an active research area in the society of medical image computing, which is to perform spatial transformation between a pair of images and establish a point-wise correspondence to achieve spatial consistency. PURPOSE Previous work mainly focused on learning complicated deformation fields by maximizing the global-level (i.e., foreground plus background) image similarity. We argue that taking the background similarity into account may not be a good solution, if we only seek the accurate alignment of target organs/regions in real clinical practice. METHODS We therefore propose a novel concept of Salient Registration and introduce a novel deformable network equipped with a saliency module. Specifically, a multi-task learning based saliency module is proposed to discriminate the salient regions-of-registration in a semi-supervised manner. Then our deformable network analyzes the intensity and anatomical similarity of salient regions, and finally conducts the salient deformable registration. RESULTS We evaluate the efficacy of the proposed network on challenging abdominal multi-organ CT scans. The experimental results demonstrate that the proposed registration network outperforms other state-of-the-art methods, achieving a mean Dice similarity coefficient (DSC) of 40.2%, Hausdorff distance (95HD) of 20.8mm, and average symmetric surface distance (ASSD) of 4.58mm. Moreover, even by training using one labeled data, our network can still attain satisfactory registration performance, with a mean DSC of 39.2%, 95HD of 21.2mm, and ASSD of 4.78mm. CONCLUSIONS The proposed network provides an accurate solution for multi-organ registration and has the potential to be used for improving other registration applications. The code is publicly available at https://github.com/Rrrfrr/Salient-Deformable-Network. This article is protected by copyright. All rights reserved.