{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:22:00Z","timestamp":1781713320232,"version":"3.54.5"},"reference-count":58,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Rectal cancer often originates from polyps. Early detection and timely removal of polyps are crucial for preventing colorectal cancer and inhibiting its progression to malignancy. While polyp segmentation algorithms are essential for aiding polyp removal, they face significant challenges due to the diverse shapes, unclear boundaries, and varying sizes of polyps. Additionally, capturing long-range dependencies remains difficult, with many existing algorithms struggling to converge effectively, limiting their practical application.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To address these challenges, we propose a novel Dual Encoder Multi-Scale Feature Fusion Network, termed VMDU-Net. This architecture employs two parallel encoders: one incorporates Vision Mamba modules, and the other integrates a custom-designed Cross-Shape Transformer. To enhance semantic understanding of polyp morphology and boundaries, we design a Mamba-Transformer-Merge (MTM) module that performs attention-weighted fusion across spatial and channel dimensions. Furthermore, Depthwise Separable Convolutions are introduced to facilitate multi-scale feature extraction and improve convergence efficiency by leveraging the inductive bias of convolution.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Extensive experiments were conducted on five widely-used polyp segmentation datasets. The results show that VMDU-Net significantly outperforms existing state-of-the-art methods, especially in terms of segmentation accuracy and boundary detail preservation. Notably, the model achieved a Dice score of 0.934 on the Kvasir-SEG dataset and 0.951 on the CVC-ClinicDB dataset.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The proposed VMDU-Net effectively addresses key challenges in polyp segmentation by leveraging complementary strengths of Transformer-based and Mamba-based modules. Its strong performance across multiple datasets highlights its potential for practical clinical application in early colorectal cancer prevention.<\/jats:p><\/jats:sec><jats:sec><jats:title>Code availability<\/jats:title><jats:p>The source code is publicly available at: <jats:ext-link>https:\/\/github.com\/sulayman-lee0212\/VMDUNet\/tree\/4a8b95804178511fa5798af4a7d98fd6e6b1ebf7<\/jats:ext-link>.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2025.1557508","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:47:20Z","timestamp":1750225640000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["VMDU-net: a dual encoder multi-scale fusion network for polyp segmentation with Vision Mamba and Cross-Shape Transformer integration"],"prefix":"10.3389","volume":"8","author":[{"given":"Peng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chia S.","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"108464","DOI":"10.1016\/j.cmpb.2024.108464","article-title":"Multi-scale dual-channel feature embedding decoder for biomedical image segmentation","volume":"257","author":"Agarwal","year":"2024","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref2","author":"Alexey","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2020.3015607","article-title":"Polyp-net: a multimodel fusion network for polyp segmentation","volume":"70","author":"Banik","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.compmedimag.2015.02.007","article-title":"WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians","volume":"43","author":"Bernal","year":"2015","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref5","author":"Cao","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"106487","DOI":"10.1016\/j.bspc.2024.106487","article-title":"DEMF-net: a dual encoder multi-scale feature fusion network for polyp segmentation","volume":"96","author":"Cao","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref7","author":"Chen","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.isprsjprs.2020.01.013","article-title":"ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data","volume":"162","author":"Diakogiannis","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref9","author":"Dong","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"80575","DOI":"10.1109\/ACCESS.2022.3195241","article-title":"Colonformer: an efficient transformer based method for colon polyp segmentation","volume":"10","author":"Duc","year":"2022","journal-title":"IEEE Access"},{"key":"ref11","author":"Fan","year":"2020"},{"key":"ref12","article-title":"SliceMamba for medical image segmentation","volume-title":"arXiv","author":"Fan","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-024-20416-3","article-title":"Compound attention embedded dual channel encoder-decoder for ms lesion segmentation from brain MRI","volume":"177","author":"Ghosal","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref14","author":"Gu","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"110491","DOI":"10.1016\/j.patcog.2024.110491","article-title":"UCTNet: uncertainty-guided CNN-transformer hybrid networks for medical image segmentation","volume":"152","author":"Guo","year":"2024","journal-title":"Pattern Recogn."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1109\/TMI.2020.3046843","article-title":"Learn to threshold: Thresholdnet with confidence-guided manifold mixup for polyp segmentation","volume":"40","author":"Guo","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s10462-023-10621-1","article-title":"A systematic review of deep learning based image segmentation to detect polyp","volume":"57","author":"Gupta","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1055\/s-0029-1242458","article-title":"Colorectal cancer epidemiology: incidence, mortality, survival, and risk factors","volume":"22","author":"Haggar","year":"2009","journal-title":"Clin. Colon Rectal Surg."},{"key":"ref19","author":"Isensee","year":"2018"},{"key":"ref20","author":"Jha","year":"2019"},{"key":"ref21","author":"Jha","year":"2019"},{"key":"ref22","author":"Jha","year":"2024"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1109\/JPROC.2019.2950506","article-title":"Wireless capsule endoscopy: a new tool for cancer screening in the colon with deep-learning-based polyp recognition","volume":"108","author":"Jia","year":"2019","journal-title":"Proc. IEEE"},{"key":"ref24","author":"Kim","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TPAMI.2022.3164083","article-title":"Contextual transformer networks for visual recognition","volume":"45","author":"Li","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref26","first-page":"1","article-title":"Ds-transunet: dual swin transformer u-net for medical image segmentation","volume":"71","author":"Lin","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref27","author":"Liu","year":"2021"},{"key":"ref28","author":"Liu","year":"2024"},{"key":"ref29","author":"Ma","year":"2024"},{"key":"ref30","author":"Narayanan","year":"2023"},{"key":"ref31","author":"Oktay","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1093\/jcde\/qwac018","article-title":"SwinE-net: hybrid deep learning approach to novel polyp segmentation using convolutional neural network and Swin transformer","volume":"9","author":"Park","year":"2022","journal-title":"J. Comput. Design Eng."},{"key":"ref33","author":"Ratheesh","year":"2016"},{"key":"ref34","author":"Ronneberger","year":"2015"},{"key":"ref35","author":"Ruan","year":"2024"},{"key":"ref36","author":"Sanderson","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.patrec.2021.12.014","article-title":"An unsupervised approach of colonic polyp segmentation using adaptive Markov random fields","volume":"154","author":"Sasmal","year":"2022","journal-title":"Pattern Recogn. Lett."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s11548-013-0926-3","article-title":"Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer","volume":"9","author":"Silva","year":"2014","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref39","author":"Sun","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1109\/TMI.2015.2487997","article-title":"Automated polyp detection in colonoscopy videos using shape and context information","volume":"35","author":"Tajbakhsh","year":"2015","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"8427","DOI":"10.1007\/s11760-024-03484-8","article-title":"RM-UNet: UNet-like mamba with rotational SSM module for medical image segmentation","volume":"18","author":"Tang","year":"2024","journal-title":"SIViP"},{"key":"ref42","author":"Tomar","year":"2022"},{"key":"ref43","article-title":"Attention is all you need","volume":"14","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2017\/4037190","article-title":"A benchmark for endoluminal scene segmentation of colonoscopy images","volume":"2017","author":"V\u00e1zquez","year":"2017","journal-title":"J. Healthcare Eng."},{"key":"ref45","author":"Waleffe","year":"2024"},{"key":"ref46","author":"Wang","year":"2022"},{"key":"ref47","author":"Wang","year":"2022"},{"key":"ref48","article-title":"META-Unet: multi-scale efficient transformer attention Unet for fast and high-accuracy polyp segmentation","volume":"53","author":"Wu","year":"2023","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref49","article-title":"CTNet: contrastive transformer network for polyp segmentation","volume":"50","author":"Xiao","year":"2024","journal-title":"IEEE Trans. Cybern."},{"key":"ref50","author":"Xie","year":"2021"},{"key":"ref51","author":"Xing","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"104815","DOI":"10.1016\/j.compbiomed.2021.104815","article-title":"Focus U-net: a novel dual attention-gated CNN for polyp segmentation during colonoscopy","volume":"137","author":"Yeung","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref53","author":"Zhang","year":"2024"},{"key":"ref54","author":"Zhang","year":"2020"},{"key":"ref55","author":"Zhang","year":"2021"},{"key":"ref56","author":"Zhou","year":"2018"},{"key":"ref57","author":"Zhu","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","first-page":"102759","DOI":"10.1016\/j.inffus.2024.102759","article-title":"Polyp-mamba: a hybrid multi-frequency perception gated selection network for polyp segmentation","volume":"115","author":"Zhu","year":"2025","journal-title":"Inf. Fusion"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1557508\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:47:22Z","timestamp":1750225642000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1557508\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,18]]},"references-count":58,"alternative-id":["10.3389\/frai.2025.1557508"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1557508","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,18]]},"article-number":"1557508"}}