{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T12:28:12Z","timestamp":1791980892750,"version":"4.4.0"},"reference-count":56,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T00:00:00Z","timestamp":1744848000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["202162106067"],"award-info":[{"award-number":["202162106067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Cardiac magnetic resonance imaging (CMR) provides critical pathological information, such as scars and edema, which are vital for diagnosing myocardial infarction (MI). However, due to the limited pathological information in single\u2010sequence CMR images and the small size of pathological regions, automatic segmentation of myocardial pathology remains a significant\u00a0challenge.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>In the paper, we propose a novel two\u2010stage anatomical\u2010pathological segmentation framework combining Kolmogorov\u2013Arnold Networks (KAN) and Mamba, aiming to effectively segment myocardial pathology in multi\u2010sequence CMR\u00a0images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>First, in the coarse segmentation stage, we employed a multiline parallel MambaUnet as the anatomical structure segmentation network to obtain shape prior information. This approach effectively addresses the class imbalance issue and aids in subsequent pathological segmentation. In the fine segmentation stage, we introduced a novel U\u2010shaped segmentation network, KANMambaNet, which features a Dual\u2010Stream Fusion Mamba module. This module enhances the network's ability to capture long\u2010range dependencies while improving its capability to distinguish different pathological features in small regions. Additionally, we developed a Kolmogorov\u2013Arnold Network\u2010based multilayer perceptron (KAN MLP) module that utilizes learnable activation functions instead of fixed nonlinear functions. This design enhances the network's flexibility in handling various pathological features, enabling more accurate differentiation of the pathological characteristics at the boundary between edema and scar regions. Our method achieves competitive segmentation performance compared to state\u2010of\u2010the\u2010art models, particularly in terms of the Dice\u00a0coefficient.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We validated our model's performance on the MyoPS2020 dataset, achieving a Dice score of 0.8041\u00a0\u00a00.0751 for myocardial edema and 0.9051\u00a0\u00a00.0240 for myocardial scar. Compared to the baseline model MambaUnet, our edema segmentation performance improved by 0.1420, and scar segmentation performance improved by 0.1081.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We developed an innovative two\u2010stage anatomical\u2010pathological segmentation framework that integrates KAN and Mamba, effectively segmenting myocardial pathology in multi\u2010sequence CMR images. The experimental results demonstrate that our proposed method achieves superior segmentation performance compared to other state\u2010of\u2010the\u2010art\u00a0methods.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.17812","type":"journal-article","created":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T23:28:46Z","timestamp":1744932526000},"page":"4567-4584","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["U\u2010shaped network combining dual\u2010stream fusion mamba and redesigned multilayer perceptron for myocardial pathology segmentation"],"prefix":"10.1002","volume":"52","author":[{"given":"Wenjie","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering Henan University of Technology Zhengzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiejun","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou China"},{"name":"Key Laboratory of Grain Information Processing and Control (HAUT) Ministry of Education Zhengzhou China"},{"name":"Henan Key Laboratory of Grain Photoelectric Detection and Control (HAUT) Zhengzhou Henan China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacheng","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering Henan University of Technology Zhengzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering Henan University of Technology Zhengzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingzhu","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering Henan University of Technology Zhengzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering Henan University of Technology Zhengzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyu","family":"Miao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,4,17]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2016.05.049"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(08)61237-4"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjcard.2007.04.029"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/j.2040-4603.2015.tb00658.x"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2019.05.024"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrthm.2011.07.027"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.111.961946"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2010.11.015"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2009.06.059"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9317-3"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10554-004-5806-z"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-36961-2_8"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2019.100004"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65651-5_4"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2020.101785"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102362"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3215536"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3288046"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102808"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102694"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.25285"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2512711"},{"key":"e_1_2_9_24_1","doi-asserted-by":"crossref","unstructured":"Merino\u2010CaviedesS Cordero\u2010GrandeL Rodr\u00edguezMP et\u00a0al.A variational method for scar segmentation with myocardial contour correction in DE\u2010CMR images. In:2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).IEEE;2016:956\u2010959.","DOI":"10.1109\/ISBI.2016.7493423"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2837502"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101554"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101657"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0261-2"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13436"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14022"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"e_1_2_9_32_1","doi-asserted-by":"crossref","unstructured":"VielzeufV LechervyA PateuxS JurieF.Centralnet: a multilayer approach for multimodal fusion. In:Proceedings of the European Conference on Computer Vision (ECCV) Workshops.Springer;2018:575\u2010589.","DOI":"10.1007\/978-3-030-11024-6_44"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108942"},{"key":"e_1_2_9_34_1","unstructured":"GuA GoelK R\u00e9C.Efficiently modeling long sequences with structured state spaces.arXiv preprint arXiv:2111.00396.2021."},{"key":"e_1_2_9_35_1","article-title":"Vision mamba: efficient visual representation learning with bidirectional state space model","author":"Zhu L","year":"2024","journal-title":"arXiv preprint arXiv:2401.09417"},{"key":"e_1_2_9_36_1","article-title":"Vmamba: visual state space model","author":"Liu Y","year":"2024","journal-title":"arXiv preprint arXiv:2401.10166"},{"key":"e_1_2_9_37_1","article-title":"U\u2010mamba: enhancing long\u2010range dependency for biomedical image segmentation","author":"Ma J","year":"2024","journal-title":"arXiv preprint arXiv:2401.04722"},{"key":"e_1_2_9_38_1","article-title":"Vm\u2010unet: vision mamba unet for medical image segmentation","author":"Ruan J","year":"2024","journal-title":"arXiv preprint arXiv:2402.02491"},{"key":"e_1_2_9_39_1","article-title":"Mamba\u2010unet: unet\u2010like pure visual mamba for medical image segmentation","author":"Wang Z","year":"2024","journal-title":"arXiv preprint arXiv:2402.05079"},{"key":"e_1_2_9_40_1","article-title":"Segmamba: long\u2010range sequential modeling mamba for 3d medical image segmentation","author":"Xing Z","year":"2024","journal-title":"arXiv preprint arXiv:2401.13560"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"e_1_2_9_42_1","doi-asserted-by":"crossref","unstructured":"CaoH WangY ChenJ et\u00a0al.Swin\u2010unet: unet\u2010like pure transformer for medical image segmentation. In:European Conference on Computer Vision.Springer;2022:205\u2010218.","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"e_1_2_9_43_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA NathV TangY YangD RothHR XuD.Swin unetr: swin transformers for semantic segmentation of brain tumors in MRI images. In:International MICCAI Brainlesion Workshop.Springer;2021;272\u2010284.","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"e_1_2_9_44_1","article-title":"P\u2010mamba: marrying Perona Malik diffusion with mamba for efficient pediatric echocardiographic left ventricular segmentation","author":"Ye Z","year":"2024","journal-title":"arXiv preprint arXiv:2402.08506"},{"key":"e_1_2_9_45_1","article-title":"Swin\u2010umamba: mamba\u2010based unet with imagenet\u2010based pretraining","author":"Liu J","year":"2024","journal-title":"arXiv preprint arXiv:2402.03302"},{"key":"e_1_2_9_46_1","article-title":"Weak\u2010Mamba\u2010UNet: visual Mamba makes CNN and ViT work better for scribble\u2010based medical image segmentation","author":"Wang Z","year":"2024","journal-title":"arXiv preprint arXiv:2402.10887"},{"key":"e_1_2_9_47_1","article-title":"Semi\u2010mamba\u2010UNet: pixel\u2010level contrastive cross\u2010supervised visual mamba\u2010based UNet for semi\u2010supervised medical image segmentation","author":"Wang Z","year":"2024","journal-title":"arXiv preprint arXiv:2402.07245"},{"key":"e_1_2_9_48_1","article-title":"Vivim: a video vision mamba for medical video object segmentation","author":"Yang Y","year":"2024","journal-title":"arXiv preprint arXiv:2401.14168"},{"key":"e_1_2_9_49_1","article-title":"Kan: Kolmogorov\u2010Arnold networks","author":"Liu Z","year":"2024","journal-title":"arXiv preprint arXiv:2404.19756"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2858779"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-12177-8_1"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.recesp.2018.07.026"},{"key":"e_1_2_9_53_1","article-title":"KAN you see it? KANs and sentinel for effective and explainable crop field segmentation","author":"Cambrin DR","year":"2024","journal-title":"arXiv preprint arXiv:2408.07040"},{"key":"e_1_2_9_54_1","doi-asserted-by":"crossref","unstructured":"ZhuangX.Multivariate mixture model for cardiac segmentation from multi\u2010sequence MRI. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2016:581\u2010588.","DOI":"10.1007\/978-3-319-46723-8_67"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2869576"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"e_1_2_9_57_1","doi-asserted-by":"crossref","unstructured":"AghdamEK AzadR ZarvaniM MerhofD.Attention swin u\u2010net: cross\u2010contextual attention mechanism for skin lesion segmentation. In:2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI).IEEE;2023:1\u20105.","DOI":"10.1109\/ISBI53787.2023.10230337"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T08:04:04Z","timestamp":1762934644000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17812"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,17]]},"references-count":56,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10.1002\/mp.17812"],"URL":"https:\/\/doi.org\/10.1002\/mp.17812","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,17]]},"assertion":[{"value":"2024-07-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}