{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:59:24Z","timestamp":1791568764025,"version":"4.3.4"},"reference-count":42,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accurate and efficient polyp segmentation is essential for computer-aided colorectal cancer screening, yet achieving a favorable balance among segmentation accuracy, computational efficiency, and cross-dataset generalization remains challenging. Recent studies suggest that Mamba-based state-space modeling can enhance long-range dependency modeling with relatively low complexity, but how lightweight Mamba integration strategies affect dense prediction frameworks for polyp segmentation remains insufficiently understood. In this study, we present LiteMamba-Seg, a lightweight polyp segmentation framework built on a U-Net-like encoder\u2013decoder architecture with a ResNet34 backbone, and conduct an empirical evaluation of different lightweight Mamba integration strategies. Specifically, we investigate bottleneck-only integration as well as alternative second-stage placements at an encoder-side intermediate stage and a decoder-side reconstruction stage. Experimental results on four public benchmark datasets show that LiteMamba-Seg achieves competitive segmentation performance while maintaining a lightweight design and real-time model-level inference, with 26.81 M parameters, 13.89 GFLOPs, and 167.73 FPS. Further ablation, controlled placement, multi-seed, robustness, boundary, calibration, and false-positive analyses indicate that the effect of Mamba integration depends on its placement within the network. In particular, decoder-side reconstruction-stage integration yields more favorable quantitative and qualitative results than encoder-side intermediate placement across the evaluated benchmarks. These findings suggest that, for lightweight polyp segmentation frameworks, Mamba integration should be considered jointly with placement strategy rather than simply increasing the number of sequence modeling blocks.<\/jats:p>","DOI":"10.1371\/journal.pone.0353562","type":"journal-article","created":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:44:51Z","timestamp":1791567891000},"page":"e0353562","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient and real-time polyp segmentation: An empirical evaluation of lightweight Mamba integration strategies"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8382-8205","authenticated-orcid":true,"given":"Si","family":"Chen","sequence":"first","affiliation":[{"name":"Universiti Teknologi Malaysia","place":["Johor Bahru, Malaysia"],"department":["Faculty of Computing"]},{"name":"Guangzhou Institute of Science and Technology","place":["Guangzhou, China"],"department":["School of Artificial Intelligence"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohd Shafry","family":"Mohd Rahim","sequence":"additional","affiliation":[{"name":"Universiti Teknologi Malaysia","place":["Johor Bahru, Malaysia"],"department":["Faculty of Computing"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiew Moi","family":"Sim","sequence":"additional","affiliation":[{"name":"Universiti Teknologi Malaysia","place":["Johor Bahru, Malaysia"],"department":["Faculty of Computing"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yee Yong","family":"Pang","sequence":"additional","affiliation":[{"name":"Universiti Teknologi Malaysia","place":["Johor Bahru, Malaysia"],"department":["Faculty of Computing"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei Kian","family":"Teo","sequence":"additional","affiliation":[{"name":"Southern University College","place":["Johor Bahru, Malaysia"],"department":["Faculty of Art and Design"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ei Lin","family":"Ong","sequence":"additional","affiliation":[{"name":"Southern University College","place":["Johor Bahru, Malaysia"],"department":["Faculty of Art and Design"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei Jer","family":"Lim","sequence":"additional","affiliation":[{"name":"Southern University College","place":["Johor Bahru, Malaysia"],"department":["Faculty of Engineering and Information Technology"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,9]]},"reference":[{"key":"pone.0353562.ref001","doi-asserted-by":"crossref","first-page":"1652","DOI":"10.7326\/ANNALS-24-00981","article-title":"Artificial intelligence\u2013assisted colonoscopy for polyp detection","volume":"177","author":"S Soleymanjahi","year":"2024","journal-title":"Ann Intern Med"},{"issue":"10","key":"pone.0353562.ref002","doi-asserted-by":"crossref","first-page":"1813","DOI":"10.1136\/gutjnl-2018-317500","article-title":"Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: A prospective randomised controlled study","volume":"68","author":"P Wang","year":"2019","journal-title":"Gut"},{"key":"pone.0353562.ref003","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1007\/s11633-022-1371-y","article-title":"Video polyp segmentation: A deep learning perspective","volume":"19","author":"GP Ji","year":"2022","journal-title":"Mach Intell Res"},{"key":"pone.0353562.ref004","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1007\/978-3-030-87193-2_66","article-title":"Shallow Attention Network for Polyp Segmentation.","author":"J Wei","year":"2021","journal-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021"},{"key":"pone.0353562.ref005","doi-asserted-by":"crossref","unstructured":"Rahman MM, Marculescu R. Medical Image Segmentation via Cascaded Attention Decoding. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). 2023. pp. 6222\u201331. Available from: https:\/\/openaccess.thecvf.com\/content\/WACV2023\/html\/Rahman_Medical_Image_Segmentation_via_Cascaded_Attention_Decoding_WACV_2023_paper.html","DOI":"10.1109\/WACV56688.2023.00616"},{"issue":"1","key":"pone.0353562.ref006","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1038\/s41597-023-01981-y","article-title":"A multi-centre polyp detection and segmentation dataset for generalisability assessment","volume":"10","author":"S Ali","year":"2023","journal-title":"Sci Data"},{"key":"pone.0353562.ref007","first-page":"1314","article-title":"Searching for MobileNetV3.","author":"A Howard","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"pone.0353562.ref008","first-page":"1580","article-title":"GhostNet: More Features From Cheap Operations.","author":"K Han","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"pone.0353562.ref009","doi-asserted-by":"crossref","first-page":"208801","DOI":"10.1109\/ACCESS.2025.3637778","article-title":"Mamba-based deep learning methods in medical image analysis: A systematic literature review","volume":"13","author":"YI Kurniawan","year":"2025","journal-title":"IEEE Access"},{"key":"pone.0353562.ref010","author":"J Ma","year":"2024"},{"key":"pone.0353562.ref011","author":"A Gu","year":"2024"},{"key":"pone.0353562.ref012","author":"W Liao","year":"2024"},{"key":"pone.0353562.ref013","doi-asserted-by":"crossref","unstructured":"Islam MF, Ahmed T, Chanda P, Mondal JJ, Manab MA, Zabeen S, et al. BAMPolyp: Bi-Axial Mamba Bottleneck for Gastrointestinal Polyp Segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW). 2025. pp. 1093\u2013103. Available from: https:\/\/openaccess.thecvf.com\/content\/ICCV2025W\/CVAMD\/html\/Islam_BAMPolyp_Bi-Axial_Mamba_Bottleneck_for_Gastrointestinal_Polyp_Segmentation_ICCVW_2025_paper.html","DOI":"10.1109\/ICCVW69036.2025.00118"},{"key":"pone.0353562.ref014","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation.","author":"O Ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015"},{"key":"pone.0353562.ref015","first-page":"3","article-title":"UNet: A Nested U-Net Architecture for Medical Image Segmentation.","author":"Z Zhou","year":"2018","journal-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support"},{"key":"pone.0353562.ref016","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/978-3-030-59725-2_26","article-title":"PraNet: Parallel Reverse Attention Network for Polyp Segmentation.","author":"D-P Fan","year":"2020","journal-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020"},{"key":"pone.0353562.ref017","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1007\/978-3-030-59725-2_25","article-title":"Adaptive Context Selection for Polyp Segmentation.","author":"R Zhang","year":"2020","journal-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020"},{"issue":"6","key":"pone.0353562.ref018","doi-asserted-by":"crossref","first-page":"545","DOI":"10.3390\/bioengineering11060545","article-title":"LightCF-Net: A lightweight long-range context fusion network for real-time polyp segmentation","volume":"11","author":"Z Ji","year":"2024","journal-title":"Bioengineering (Basel)"},{"key":"pone.0353562.ref019","doi-asserted-by":"crossref","first-page":"102802","DOI":"10.1016\/j.media.2023.102802","article-title":"Transformers in medical imaging: A survey","volume":"88","author":"F Shamshad","year":"2023","journal-title":"Med Image Anal"},{"key":"pone.0353562.ref020","first-page":"5998","article-title":"Attention is All You Need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"pone.0353562.ref021","author":"J Chen","year":"2021"},{"key":"pone.0353562.ref022","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/978-3-030-87193-2_2","article-title":"TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation.","author":"Y Zhang","year":"2021","journal-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021"},{"key":"pone.0353562.ref023","doi-asserted-by":"crossref","first-page":"9150015","DOI":"10.26599\/AIR.2023.9150015","article-title":"Polyp-PVT: Polyp segmentation with pyramid vision transformers","volume":"2","author":"B Dong","year":"2023","journal-title":"CAAI Artif Intell Res"},{"issue":"4","key":"pone.0353562.ref024","article-title":"DECTNet: Dual Encoder Network combined convolution and Transformer architecture for medical image segmentation","volume":"19","author":"B Li","year":"2024","journal-title":"PLoS One"},{"issue":"4","key":"pone.0353562.ref025","article-title":"DSCANet: Integrating dual encoder and spatial cross-attention for polyp segmentation","volume":"21","author":"J Su","year":"2026","journal-title":"PLoS One"},{"key":"pone.0353562.ref026","doi-asserted-by":"crossref","first-page":"103031","DOI":"10.52202\/079017-3273","article-title":"VMamba: Visual State Space Model","volume":"37","author":"Y Liu","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"issue":"3","key":"pone.0353562.ref027","article-title":"An optimal transport-based undersampling technique for handling imbalanced datasets","volume":"148","author":"S Seo","year":"2025","journal-title":"J Dyn Syst Meas Control"},{"key":"pone.0353562.ref028","article-title":"VM-UNet: Vision mamba UNet for medical image segmentation","author":"J Ruan","year":"2025","journal-title":"ACM Trans Multimedia Comput Commun Appl"},{"issue":"6","key":"pone.0353562.ref029","article-title":"SA-UMamba: Spatial attention convolutional neural networks for medical image segmentation","volume":"20","author":"L Liu","year":"2025","journal-title":"PLoS One"},{"key":"pone.0353562.ref030","author":"J Xie","year":"2024"},{"key":"pone.0353562.ref031","first-page":"455","article-title":"PolyMamba: Spatial-Prior Guided Mamba for Polyp Segmentation with High-Frequency Enhancement.","author":"R Fu","year":"2026","journal-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"},{"key":"pone.0353562.ref032","first-page":"770","article-title":"Deep Residual Learning for Image Recognition.","author":"K He","year":"2016","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"pone.0353562.ref033","first-page":"562","article-title":"Deeply-Supervised Nets.","volume-title":"Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"C-Y Lee","year":"2015"},{"key":"pone.0353562.ref034","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1007\/978-3-030-37734-2_37","article-title":"Kvasir-SEG: A segmented polyp dataset.","author":"D Jha","year":"2020","journal-title":"MultiMedia Modeling"},{"key":"pone.0353562.ref035","doi-asserted-by":"crossref","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":"J Bernal","year":"2015","journal-title":"Comput Med Imaging Graph"},{"key":"pone.0353562.ref036","doi-asserted-by":"crossref","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":"N Tajbakhsh","year":"2016","journal-title":"IEEE Trans Med Imaging"},{"issue":"2","key":"pone.0353562.ref037","doi-asserted-by":"crossref","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":"J Silva","year":"2014","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"pone.0353562.ref038","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"A Paszke","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"pone.0353562.ref039","author":"I Loshchilov","year":"2019"},{"key":"pone.0353562.ref040","author":"I Loshchilov","year":"2017"},{"issue":"2","key":"pone.0353562.ref041","doi-asserted-by":"crossref","first-page":"125","DOI":"10.3390\/info11020125","article-title":"Albumentations: Fast and flexible image augmentations","volume":"11","author":"A Buslaev","year":"2020","journal-title":"Information"},{"key":"pone.0353562.ref042","first-page":"335","article-title":"VM-UNET-V2: Rethinking Vision Mamba UNet for Medical Image Segmentation.","author":"M Zhang","year":"2024","journal-title":"Bioinformatics Research and Applications"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:44:59Z","timestamp":1791567899000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353562"}},"subtitle":[],"editor":[{"given":"Xiaowei","family":"Li","sequence":"first","affiliation":[{"name":"Sichuan University","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,9]]},"references-count":42,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0353562","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,9]]}}}