{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-light-weight-rectangular-decomposition","title":"A light-weight rectangular decomposition large kernel convolution network for deformable medical image registration.","arxiv_id":null,"date":"2024-05-27","proceeding":"Biomedical Signal Processing and Control 2024 5","authors":["Yuzhu Cao","Weiwei Cao","Ziyu Wang","Gang Yuan","Zeyi Li","Xinye Ni","Jian Zheng"],"abstract":"The performance and speed of medical image registration have been greatly boosted by advanced deep-learning based methods. However, most current methods are challenged by large deformations between input images, which necessitate a compromise in computational cost to enhance the model’s receptive field and its ability to model long-range spatial relationships for improving registration performance. In order to enhance the performance of registration for images with large deformations at a lower computational cost, in this paper, we propose a light-weight registration model with the ability to model large receptive fields and long-range spatial relationships, named LL-Net. The core components of LL-Net consist of a Rectangular Decomposition Large Kernel Attention (RD-LKA) layer and a Spatial and Channel Fusion Attention (SC-Fusion) layer. The RD-LKA layer utilizes anisotropic depth-wise large kernel convolutions to capture large receptive fields with an extremely low parameter count while modeling long-range spatial relationships. Moreover, the SC-Fusion layer enhances the model’s feature fusion capability and strengthens feature representations at critical locations. Our LL-Net exhibits state-of-the-art performance across multiple datasets. Specifically, it achieves a Dice score of 76.7% and an HD95 of 2.983 mm on the IXI dataset, and a Dice score of 87.8% and an HD95 of 1.042 mm on the OASIS dataset. Experimental results substantiate the efficacy of LL-Net in capturing large receptive fields and modeling long-range spatial relationships. The code for LL-Net is available at https://github.com/BoyOfChu/LL_Net.","url_abs":"https://doi.org/10.1016/j.bspc.2024.106476","url_pdf":"https://www.sciencedirect.com/science/article/pii/S1746809424005342/pdfft?md5=fd936d8eaf65054ce0abeb8a1841d0dd&pid=1-s2.0-S1746809424005342-main.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-light-weight-rectangular-decomposition","repo_url":"https://github.com/BoyOfChu/LL_Net","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deformable-medical-image-registration","task_name":"Deformable Medical Image Registration"},{"task_slug":"image-registration","task_name":"Image Registration"},{"task_slug":"medical-image-registration","task_name":"Medical Image Registration"}],"methods":[{"method_slug":"oasis","method_name":"OASIS"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/medical-image-registration-on-ixi","task":"Medical Image Registration","dataset":"IXI","model":"LL_Net","rank_in_archive_order":1,"of":8,"metrics":{"DSC":"0.767"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}