Title: MCRformer: Morphological Constraint Reticular Transformer for 3D Medical Image Segmentation
Abstract: Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL MCRformer: Morphological Constraint Reticular Transformer for 3D Medical Image Segmentation 32 Pages Posted: 4 Nov 2022 See all articles by Jun LiJun LiFujian Agriculture and Forestry UniversityNan ChenFujian Agriculture and Forestry UniversityHan ZhouFujian Agriculture and Forestry UniversityTaotao LaiMinjiang UniversityHeng DongFujian Agriculture and Forestry UniversityChunhui FengFujian Agriculture and Forestry UniversityRiqing ChenFujian Agriculture and Forestry UniversityChangcai YangFujian Agriculture and Forestry UniversityFanggang CaiFujian Medical UniversityLifang WeiFujian Agriculture and Forestry University Abstract Background and objective: Medical image segmentation is essential in medical image analysis since it can provide reliable assistance in computer-aided clinical diagnosis, treatment planning, and intervention. Although deep learning algorithms based on CNNs and Transformers have made notable progress in medical image segmentation, it is still challenging owing to the objects with complex structures, low discrimination and differences between individuals. Methods: To alleviate the problems, we propose a novel 3D medical image segmentation network based on Transformers and CNNs combining morphological information and reticular mechanism. Firstly, the morphological constraint stream is designed to learn the prior shape information based on the CNN model for enhancing the interpretability of the ultimate trained model and accelerating the convergence. Secondly, the Reticular Transformer is utilized to obtain multi-scale information based on the Transformer, which can bind the local texture information and underlying semantic information to further acquire the feature maps with sufffficient details and receptive field. Results: The experiments demonstrate that our proposed method outperforms many existing segmentation models in terms of the performance in metrics DSC and HD (80.46% in DSC on the Synapse dataset and 90.83% in DSC on the ACDC dataset). The code will be released at https://github.com/rocklijun/MCRformer. Conclusions: Our proposed method can not only achieve superior performance compared with most of the current state-of-the-art methods, but also enhance the robustness and interpretability of the model. Furthermore, the proposed morphological constraint stream has the potential to be transferred to other frameworks for different medical image analysis tasks. Note: Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 62171130, 62172197, in part by the Natural Science Foundation of Fujian Province under Grant 2020J01573, 2022J01131257, 2022J01607, and in part by the Fund of Cloud Computing and Big Data for Smart Agriculture under Grant 117-612014063. Conflict of Interests: The authors declare that there are no conflicts of interest. Keywords: Convolutional neural network, medical image segmentation, morphologicalconstraint, reticular mechanism, transformer Suggested Citation: Suggested Citation Li, Jun and Chen, Nan and Zhou, Han and Lai, Taotao and Dong, Heng and Feng, Chunhui and Chen, Riqing and Yang, Changcai and Cai, Fanggang and Wei, Lifang, MCRformer: Morphological Constraint Reticular Transformer for 3D Medical Image Segmentation. Available at SSRN: https://ssrn.com/abstract=4253383 Jun Li Fujian Agriculture and Forestry University ( email ) Fujian RoadFuzhou, 350002China Nan Chen Fujian Agriculture and Forestry University ( email ) Fujian RoadFuzhou, 350002China Han Zhou Fujian Agriculture and Forestry University ( email ) Fujian RoadFuzhou, 350002China Taotao Lai Minjiang University ( email ) 1 Wenxian RdMinhou, FuzhouFujianChina Heng Dong Fujian Agriculture and Forestry University ( email ) Fujian RoadFuzhou, 350002China Chunhui Feng Fujian Agriculture and Forestry University ( email ) Fujian RoadFuzhou, 350002China Riqing Chen Fujian Agriculture and Forestry University ( email ) Fujian RoadFuzhou, 350002China Changcai Yang Fujian Agriculture and Forestry University ( email ) Fujian RoadFuzhou, 350002China Fanggang Cai Fujian Medical University ( email ) FuzhouChina Lifang Wei (Contact Author) Fujian Agriculture and Forestry University ( email ) Fujian RoadFuzhou, 350002China Download This Paper Open PDF in Browser Do you have a job opening that you would like to promote on SSRN? Place Job Opening Paper statistics Downloads 2 Abstract Views 7 PlumX Metrics Related eJournals Applied Computing eJournal Follow Applied Computing eJournal Subscribe to this fee journal for more curated articles on this topic FOLLOWERS 227 PAPERS 4,261 Radiology & Medical Imaging eJournal Follow Radiology & Medical Imaging eJournal Subscribe to this fee journal for more curated articles on this topic FOLLOWERS 47 PAPERS 460 Feedback Feedback to SSRN Feedback (required) Email (required) Submit If you need immediate assistance, call 877-SSRNHelp (877 777 6435) in the United States, or +1 212 448 2500 outside of the United States, 8:30AM to 6:00PM U.S. Eastern, Monday - Friday. Submit a Paper Section 508 Text Only Pages SSRN Quick Links SSRN Solutions Research Paper Series Conference Papers Partners in Publishing Jobs & Announcements Newsletter Sign Up SSRN Rankings Top Papers Top Authors Top Organizations About SSRN SSRN Objectives Network Directors Presidential Letter Announcements Contact us FAQs Copyright Terms and Conditions Privacy Policy We use cookies to help provide and enhance our service and tailor content. To learn more, visit Cookie Settings. This page was processed by aws-apollo-4dc in 0.265 seconds