{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T07:09:50Z","timestamp":1780384190840,"version":"3.54.1"},"reference-count":63,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T00:00:00Z","timestamp":1780358400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T00:00:00Z","timestamp":1780358400000},"content-version":"tdm","delay-in-days":1,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Accurate polyp segmentation in colonoscopy images is crucial for early colorectal cancer diagnosis but remains challenging due to irregular shapes, weak boundaries, and low contrast. Although foundation segmentation models like SAM2 offer powerful representations, their generic decoders often lack the multi-scale modeling and cross-layer semantic constraints needed for precise medical image analysis, particularly under weak-boundary conditions. To address this, we propose SAM2-RFANet, a novel network that synergistically couples multi-receptive-field feature extraction with collaborative attention mechanisms. Our framework introduces three core modules: an adaptive receptive field modulation module for dynamic context modeling via learnable hybrid pooling and multi-scale dilated convolutions; a multi-scale feature decoding module employing direction-aware large-kernel decomposition to better capture anisotropic structures like polyp boundaries; and a semantic feature alignment module for gated, semantically consistent fusion of multi-level features. Extensive experiments on five public datasets show that SAM2-RFANet achieves highly competitive and generally strong performance across both in-distribution and unseen test sets. Although it does not obtain the best score on every metric, it demonstrates a favorable balance between overlap accuracy, structural consistency, and cross-dataset generalization. Notably, it attains mean Dice scores of 0.923 on Kvasir-SEG and 0.942 on CVC-ClinicDB, while showing strong generalization on more challenging datasets (e.g. 0.813 on CVC-ColonDB). These results confirm the effectiveness of integrating multi-receptive-field modeling with cross-layer semantic alignment for robust polyp segmentation in complex endoscopic scenarios. Our work illustrates how task-specific architectural innovations can effectively adapt powerful foundation models to the nuanced demands of medical image analysis. The code will be available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/253458lgc\/SAM2-RFANet\">https:\/\/github.com\/253458lgc\/SAM2-RFANet<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/ae71d7","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T22:48:11Z","timestamp":1779490091000},"page":"035054","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SAM2-RFANet: a multi-receptive-field aware attention network for enhanced polyp segmentation in colonoscopy imagery"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0091-8625","authenticated-orcid":true,"given":"Guangcheng","family":"Li","sequence":"first","affiliation":[{"name":"Hengyang Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6202-3158","authenticated-orcid":true,"given":"Ge","family":"Jiao","sequence":"additional","affiliation":[{"name":"Hengyang Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Hengyang Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenpeng","family":"Zhong","sequence":"additional","affiliation":[{"name":"Hengyang Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,6,2]]},"reference":[{"key":"bpexae71d7bib1","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","type":"journal-article","article-title":"Global cancer statistics 2020 GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clinicians"},{"key":"bpexae71d7bib2","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1056\/NEJMoa1100370","type":"journal-article","article-title":"Colonoscopic polypectomy and long-term prevention of colorectal-cancer deaths","volume":"366","author":"Zauber","year":"2012","journal-title":"New Engl. J. Med."},{"key":"bpexae71d7bib3","article-title":"Colorectal polyp segmentation in the deep learning era: a comprehensive survey","author":"Wu","year":"2024","type":"preprint"},{"key":"bpexae71d7bib4","first-page":"1762","type":"conference-proceedings","article-title":"Cnn based u-net with modified skip connections for colon polyp segmentation","author":"Sushma","year":"2021"},{"key":"bpexae71d7bib5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s44267-024-00071-w","type":"journal-article","article-title":"A survey on deep learning for polyp segmentation: techniques, challenges and future trends","volume":"3","author":"Mei","year":"2025","journal-title":"Vis. Intell."},{"key":"bpexae71d7bib6","first-page":"234","type":"conference-proceedings","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"bpexae71d7bib7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109555","type":"journal-article","article-title":"Cross-level feature aggregation network for polyp segmentation","volume":"140","author":"Zhou","year":"2023","journal-title":"Pattern Recognit."},{"key":"bpexae71d7bib8","article-title":"Polyp-pvt: polyp segmentation with pyramid vision transformers","author":"Dong","year":"2021","type":"preprint"},{"key":"bpexae71d7bib9","first-page":"263","type":"conference-proceedings","article-title":"Pranet: parallel reverse attention network for polyp segmentation","author":"Fan","year":"2020"},{"key":"bpexae71d7bib10","first-page":"699","type":"conference-proceedings","article-title":"Shallow attention network for polyp segmentation","author":"Wei","year":"2021"},{"key":"bpexae71d7bib11","first-page":"7985","type":"conference-proceedings","article-title":"Meganet: multi-scale edge-guided attention network for weak boundary polyp segmentation","author":"Bui","year":"2024"},{"key":"bpexae71d7bib12","first-page":"302","type":"conference-proceedings","article-title":"Selective feature aggregation network with area-boundary constraints for polyp segmentation","author":"Fang","year":"2019"},{"key":"bpexae71d7bib13","first-page":"4015","type":"conference-proceedings","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"bpexae71d7bib14","article-title":"Sam 2: segment anything in images and videos","author":"Ravi","year":"2024","type":"preprint"},{"key":"bpexae71d7bib15","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1109\/TMI.2015.2487997","type":"journal-article","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":"bpexae71d7bib16","doi-asserted-by":"publisher","first-page":"1488","DOI":"10.1109\/TMI.2014.2314959","type":"journal-article","article-title":"Automated polyp detection in colon capsule endoscopy","volume":"33","author":"Mamonov","year":"2014","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae71d7bib17","doi-asserted-by":"publisher","first-page":"1408","DOI":"10.1109\/TBME.2012.2188397","type":"journal-article","article-title":"A colon video analysis framework for polyp detection","volume":"59","author":"Park","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae71d7bib18","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1109\/TMI.2009.2031323","type":"journal-article","article-title":"Detection and segmentation of colonic polyps on implicit isosurfaces by second principal curvature flow","volume":"29","author":"Van Wijk","year":"2010","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae71d7bib19","doi-asserted-by":"publisher","first-page":"4090","DOI":"10.1109\/JBHI.2022.3173948","type":"journal-article","article-title":"Boundary constraint network with cross layer feature integration for polyp segmentation","volume":"26","author":"Yue","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"bpexae71d7bib20","doi-asserted-by":"publisher","first-page":"2610","DOI":"10.1109\/TCYB.2022.3162873","type":"journal-article","article-title":"Polypseg+: A lightweight context-aware network for real-time polyp segmentation","volume":"53","author":"Wu","year":"2022","journal-title":"IEEE Trans. Cybern."},{"key":"bpexae71d7bib21","first-page":"142","type":"conference-proceedings","article-title":"Progressively normalized self-attention network for video polyp segmentation","author":"Ji","year":"2021"},{"key":"bpexae71d7bib22","first-page":"302","type":"conference-proceedings","article-title":"Multi-frame collaboration for effective endoscopic video polyp detection via spatial-temporal feature transformation","author":"Wu","year":"2021"},{"key":"bpexae71d7bib23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3293880","type":"journal-article","article-title":"Ftmf-net: a fourier transform-multiscale feature fusion network for segmentation of small polyp objects","volume":"72","author":"Liu","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"bpexae71d7bib24","first-page":"14","type":"conference-proceedings","article-title":"Transfuse: fusing transformers and CNNs for medical image segmentation","author":"Zhang","year":"2021"},{"key":"bpexae71d7bib25","doi-asserted-by":"publisher","first-page":"80575","DOI":"10.1109\/ACCESS.2022.3195241","type":"journal-article","article-title":"Colonformer: an efficient transformer based method for colon polyp segmentation","volume":"10","author":"Duc","year":"2022","journal-title":"IEEE Access"},{"key":"bpexae71d7bib26","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102195","type":"journal-article","article-title":"Multi-level feature fusion network combining attention mechanisms for polyp segmentation","volume":"104","author":"Liu","year":"2024","journal-title":"Inf. Fusion"},{"key":"bpexae71d7bib27","first-page":"3","type":"conference-proceedings","article-title":"Cbam: convolutional block attention module","author":"Woo","year":"2018"},{"key":"bpexae71d7bib28","first-page":"7132","type":"conference-proceedings","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"bpexae71d7bib29","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111211","type":"journal-article","article-title":"Optimal features driven hybrid attention network for effective video summarization","volume":"158","author":"Khan","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"bpexae71d7bib30","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103165","type":"journal-article","article-title":"Bilateral feature fusion with hexagonal attention for robust saliency detection under uncertain environments","volume":"121","author":"Khan","year":"2025","journal-title":"Inf. Fusion"},{"key":"bpexae71d7bib31","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2022.102072","type":"journal-article","article-title":"Polyp segmentation network with hybrid channel-spatial attention and pyramid global context guided feature fusion","volume":"98","author":"Huang","year":"2022","journal-title":"Comput. Med. Imaging Graph."},{"key":"bpexae71d7bib32","first-page":"6222","type":"conference-proceedings","article-title":"Medical image segmentation via cascaded attention decoding","author":"Rahman","year":"2023"},{"key":"bpexae71d7bib33","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.108483","type":"journal-article","article-title":"Cbam\u2013smk: Integrating convolution block attention module with separable multi-resolution kernels in deep neural networks for brain tumor classification","volume":"112","author":"Binish","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae71d7bib34","doi-asserted-by":"publisher","first-page":"184709","DOI":"10.1109\/ACCESS.2025.3621157","type":"journal-article","article-title":"A multimodal deep learning framework using resnet-101 and firefly-based feature selection for early diagnosis of dementia and Alzheimer\u2019s disease","volume":"13","author":"Bansal","year":"2025","journal-title":"IEEE Access"},{"key":"bpexae71d7bib35","first-page":"3367","type":"conference-proceedings","article-title":"Sam-adapter: adapting segment anything in underperformed scenes","author":"Chen","year":"2023"},{"key":"bpexae71d7bib36","first-page":"4989","type":"conference-proceedings","article-title":"Pp-sam: perturbed prompts for robust adaption of segment anything model for polyp segmentation","author":"Rahman","year":"2024"},{"key":"bpexae71d7bib37","article-title":"The sam-med2d","author":"Cheng","year":"2023","type":"preprint"},{"key":"bpexae71d7bib38","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1117\/12.3006809","type":"journal-article","article-title":"Polyp-sam: transfer SAM for polyp segmentation","volume":"12927","author":"Li","year":"2024","journal-title":"Proc. SPIE"},{"key":"bpexae71d7bib39","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s00371-025-04252-6","type":"journal-article","article-title":"Sam2-degnet: dual-stage edge guidance network for camouflaged object detection using sam2","volume":"42","author":"Zhong","year":"2026","journal-title":"The Visual Comput."},{"key":"bpexae71d7bib40","doi-asserted-by":"publisher","first-page":"2923","DOI":"10.1109\/LSP.2025.3589944","type":"journal-article","article-title":"Hfs-sam2: Segment anything model 2 with high-frequency feature supplementation for camouflaged object detection","volume":"32","author":"Wu","year":"2025","journal-title":"IEEE Signal Process. Lett."},{"key":"bpexae71d7bib41","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105308","type":"journal-article","article-title":"Attention enhanced machine instinctive vision with human-inspired saliency detection","volume":"152","author":"Khan","year":"2024","journal-title":"Image Vis. Comput."},{"key":"bpexae71d7bib42","first-page":"12321","type":"conference-proceedings","article-title":"F 3net: fusion, feedback and focus for salient object detection","volume":"vol 34","author":"Wei","year":"2020"},{"key":"bpexae71d7bib43","first-page":"451","type":"conference-proceedings","article-title":"Kvasir-seg: a segmented polyp dataset","author":"Jha","year":"2019"},{"key":"bpexae71d7bib44","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.compmedimag.2015.02.007","type":"journal-article","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":"bpexae71d7bib45","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/4037190","type":"journal-article","article-title":"A benchmark for endoluminal scene segmentation of colonoscopy images","volume":"2017","author":"V\u00e1zquez","year":"2017","journal-title":"J. Healthc. Eng."},{"key":"bpexae71d7bib46","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s11548-013-0926-3","type":"journal-article","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":"bpexae71d7bib47","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","type":"preprint"},{"key":"bpexae71d7bib48","first-page":"248","type":"conference-proceedings","article-title":"How to evaluate foreground maps?","author":"Margolin","year":"2014"},{"key":"bpexae71d7bib49","first-page":"4548","type":"conference-proceedings","article-title":"Structure-measure: a new way to evaluate foreground maps","author":"Fan","year":"2017"},{"key":"bpexae71d7bib50","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1360\/SSI-2020-0370","type":"journal-article","article-title":"Cognitive vision inspired object segmentation metric and loss function","volume":"6","author":"Fan","year":"2021","journal-title":"Sci. Sin. Informationis"},{"key":"bpexae71d7bib51","first-page":"733","type":"conference-proceedings","article-title":"Saliency filters: contrast based filtering for salient region detection","author":"Perazzi","year":"2012"},{"key":"bpexae71d7bib52","first-page":"3","type":"conference-proceedings","article-title":"Unet++: A nested u-net architecture for medical image segmentation","author":"Zhou","year":"2018"},{"key":"bpexae71d7bib53","article-title":"Transunet: transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","type":"preprint"},{"key":"bpexae71d7bib54","first-page":"2167","type":"conference-proceedings","article-title":"Uacanet: uncertainty augmented context attention for polyp segmentation","author":"Kim","year":"2021"},{"key":"bpexae71d7bib55","article-title":"M 2SNet: multi-scale in multi-scale subtraction network for medical image segmentation","author":"Zhao","year":"2023","type":"preprint"},{"key":"bpexae71d7bib56","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1109\/JBHI.2023.3273728","type":"journal-article","article-title":"An efficient multi-task synergetic network for polyp segmentation and classification","volume":"28","author":"Wang","year":"2023","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"bpexae71d7bib57","article-title":"Sam2-unet: segment anything 2 makes strong encoder for natural and medical image segmentation","author":"Xiong","year":"2024","type":"preprint"},{"key":"bpexae71d7bib58","doi-asserted-by":"publisher","first-page":"7440","DOI":"10.1109\/TCSVT.2024.3370685","type":"journal-article","article-title":"Uncertainty-aware hierarchical aggregation network for medical image segmentation","volume":"34","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"bpexae71d7bib59","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102759","type":"journal-article","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"},{"key":"bpexae71d7bib60","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2025.104396","type":"journal-article","article-title":"Manet: multi-attention network for polyp segmentation","volume":"143","author":"Jian","year":"2025","journal-title":"Med. Eng. Phys."},{"key":"bpexae71d7bib61","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106906","type":"journal-article","article-title":"Safe-net: shape-aware and feature enhancement network for polyp segmentation","volume":"99","author":"Yu","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae71d7bib62","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2025.105777","type":"journal-article","article-title":"HMPFormer: hierarchical vision transformer with multi-perspective feature learning for precise polyp segmentation","volume":"164","author":"Usman","year":"2025","journal-title":"Image Vis. Comput."},{"key":"bpexae71d7bib63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112101","type":"journal-article","article-title":"MSBP-Net: a multi-scale boundary prediction network for automated polyp segmentation","volume":"170","author":"Pan","year":"2026","journal-title":"Pattern Recognit."}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae71d7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae71d7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae71d7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae71d7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae71d7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae71d7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae71d7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae71d7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T06:33:57Z","timestamp":1780382037000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae71d7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":63,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,6,2]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae71d7","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,1]]},"assertion":[{"value":"SAM2-RFANet: a multi-receptive-field aware attention network for enhanced polyp segmentation in colonoscopy imagery","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-02-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-05-22","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-06-02","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}