{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T02:08:43Z","timestamp":1791166123871,"version":"4.1.0"},"reference-count":42,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T00:00:00Z","timestamp":1765411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T00:00:00Z","timestamp":1765411200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Central Guidance on Local Science and Technology Development Fund of Hebei Provinc","award":["236Z1705G"],"award-info":[{"award-number":["236Z1705G"]}]},{"name":"Science Research Project of Hebei Education Department","award":["BJ2025057"],"award-info":[{"award-number":["BJ2025057"]}]},{"name":"Open Fund of State Key Laboratory of Information Photonics and Optical Communications (Beijing University of Posts and Telecommunications), P. R. China","award":["IPOC2021B06"],"award-info":[{"award-number":["IPOC2021B06"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>To enable efficient and accurate retinal lesion segmentation on resource-constrained point-of-care Optical Coherence Tomography (OCT) systems, we propose OCTSeg-UNeXt, an ultralight hybrid Convolution-Multilayer Perceptron (Conv-MLP) network optimized for OCT image analysis. Built upon the UNeXt architecture, our model integrates a Depthwise-Augmented Scale Context (DASC) module for adaptive multi-scale feature aggregation, and a Group Fusion Bridge (GFB) to enhance information interaction between the encoder and decoder. Additionally, we employ a deep supervision strategy during training to improve structural learning and accelerate convergence. We evaluated our model using three publicly available OCT datasets. The results of the comparative experiments and ablation experiments show that our method achieves powerful performance in multiple key indicators. Importantly, our method achieves this high performance with only 0.187 million parameters (Params) and 0.053 G Floating-Point Operations Per second (FLOPs), which is significantly lower than UNeXt (0.246M, 0.086G) and UNet (17M, 30.8G). These findings demonstrate the proposed method\u2019s strong potential for deployment in Point-of-Care Imaging (POCI) systems, where computational efficiency and model compactness are crucial.<\/jats:p>","DOI":"10.1088\/2057-1976\/ae2127","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T22:47:43Z","timestamp":1763592463000},"page":"015020","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["OCTSeg-UNeXt: an ultralight hybrid Conv-MLP network for retinal pathology segmentation in point-of-care OCT imaging"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3281-3799","authenticated-orcid":true,"given":"Shujun","family":"Men","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1697-4578","authenticated-orcid":true,"given":"Jiamin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6673-4463","authenticated-orcid":true,"given":"Yanke","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuntian","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1160-3133","authenticated-orcid":true,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Huo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2025,12,11]]},"reference":[{"key":"bpexae2127bib1","doi-asserted-by":"publisher","first-page":"60","DOI":"10.5114\/ko.2020.96492","type":"journal-article","article-title":"Eye health risks associated with the use of electronic devices and awareness of youth","volume":"122","author":"Skoblina","year":"2020","journal-title":"Klinika Oczna\/Acta Ophthalmologica Polonica"},{"key":"bpexae2127bib2","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1001\/jama.2023.26074","type":"journal-article","article-title":"Age-related macular degeneration: a review","volume":"331","author":"Fleckenstein","year":"2024","journal-title":"JAMA"},{"key":"bpexae2127bib3","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1159\/000458539","type":"journal-article","article-title":"Guidelines for the management of diabetic macular edema by the european society of retina specialists (EURETINA)","volume":"237","author":"Schmidt-Erfurth","year":"2017","journal-title":"Ophthalmologica"},{"key":"bpexae2127bib4","doi-asserted-by":"publisher","first-page":"28","DOI":"10.3390\/biomedicines12071405","type":"journal-article","article-title":"Advances in structural and functional retinal imaging and biomarkers for early detection of diabetic retinopathy","volume":"12","author":"Zhang","year":"2024","journal-title":"Biomedicines"},{"key":"bpexae2127bib5","first-page":"1","type":"journal-article","article-title":"LiDeOCTNet: a lightweight OCT-aware framework for segmentation of irregularly layered tissue structures","volume":"70","author":"Abaxi","year":"2023","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae2127bib6","first-page":"roceedings,art III 234","type":"conference-proceedings","article-title":"U-net: convolutional networks for biomedical image segmentation","volume":"2015","author":"Ronneberger","year":"2015"},{"key":"bpexae2127bib7","article-title":"Attention u-net: learning where to look for the pancreas","author":"Oktay","year":"2018","type":"preprint"},{"key":"bpexae2127bib8","article-title":"nnu-net: self-adapting framework for u-net-based medical image segmentation","author":"Isensee","year":"2018","type":"preprint"},{"key":"bpexae2127bib9","article-title":"Attention is all you need","author":"Vaswani","year":"2017","type":"conference-proceedings"},{"key":"bpexae2127bib10","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","type":"preprint"},{"key":"bpexae2127bib11","article-title":"TransUNet: transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","type":"preprint"},{"key":"bpexae2127bib12","first-page":"205","type":"conference-proceedings","article-title":"Swin-unet: unet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"key":"bpexae2127bib13","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/TIM.2022.3178991","type":"journal-article","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":"bpexae2127bib14","article-title":"MLP-Mixer: an all-MLP architecture for Vision","author":"Tolstikhin","year":"2021","type":"conference-proceedings"},{"key":"bpexae2127bib15","doi-asserted-by":"publisher","first-page":"5314","DOI":"10.1109\/TPAMI.2022.3206148","type":"journal-article","article-title":"ResMLP: feedforward networks for image classification with data-efficient training","volume":"45","author":"Touvron","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"bpexae2127bib16","first-page":"262","type":"conference-proceedings","article-title":"MedMLP: an efficient MLP-like network for zero-shot retinal image classification","author":"Zhou","year":"2024"},{"key":"bpexae2127bib17","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.compbiomed.2023.107460","type":"journal-article","article-title":"U-MLP: MLP-based ultralight refinement network for medical image segmentation","volume":"165","author":"Gao","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"bpexae2127bib18","first-page":"23","type":"conference-proceedings","article-title":"Unext: Mlp-based rapid medical image segmentation network","author":"Valanarasu","year":"2022"},{"key":"bpexae2127bib19","doi-asserted-by":"publisher","first-page":"3295","DOI":"10.1364\/BOE.456435","type":"journal-article","article-title":"Portable boom-type ultrahigh-resolution OCT with an integrated imaging probe for supine position retinal imaging","volume":"13","author":"Duan","year":"2022","journal-title":"Biomed. Opt. Express"},{"key":"bpexae2127bib20","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1167\/tvst.14.1.14","type":"journal-article","article-title":"New directions for ophthalmic OCT - handhelds, surgery, and robotics","volume":"14","author":"Foust","year":"2025","journal-title":"Translational Vision Science & Technology."},{"key":"bpexae2127bib21","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1007\/s00592-023-02105-z","type":"journal-article","article-title":"Clinical validation of a smartphone-based retinal camera for diabetic retinopathy screening","volume":"60","author":"de Oliveira","year":"2023","journal-title":"Acta Diabetologica."},{"key":"bpexae2127bib22","first-page":"562","type":"journal-article","article-title":"Deeply-supervised nets","author":"Lee","year":"2015","journal-title":"Artificial intelligence and statistics: Pmlr"},{"key":"bpexae2127bib23","first-page":"1279","type":"conference-proceedings","article-title":"1M parameters are enough? a lightweight CNN-based model for medical image segmentation","author":"Dinh","year":"2023"},{"key":"bpexae2127bib24","first-page":"481","type":"book","article-title":"EGE-UNet: an efficient group enhanced UNet for skin lesion segmentation","author":"Ruan","year":"2023"},{"key":"bpexae2127bib25","doi-asserted-by":"publisher","first-page":"35932","DOI":"10.1109\/ACCESS.2022.3163711","type":"journal-article","article-title":"ELU-Net: an efficient and lightweight U-Net for medical image segmentation","volume":"10","author":"Deng","year":"2022","journal-title":"IEEE Access."},{"key":"bpexae2127bib26","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1002\/acm2.14584","type":"journal-article","article-title":"LightAWNet: lightweight adaptive weighting network based on dynamic convolutions for medical image segmentation","volume":"26","author":"Wang","year":"2025","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"bpexae2127bib27","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.bspc.2025.107773","type":"journal-article","article-title":"LiteNeXt: a novel lightweight convmixer-based model with self-embedding representation parallel for medical image segmentation","volume":"107","author":"Tran","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae2127bib28","doi-asserted-by":"publisher","first-page":"5723","DOI":"10.1364\/BOE.529662","type":"journal-article","article-title":"LS-Net: lightweight segmentation network for dermatological epidermal segmentation in optical coherence tomography imaging","volume":"15","author":"Liao","year":"2024","journal-title":"Biomed. Opt. Express"},{"key":"bpexae2127bib29","doi-asserted-by":"publisher","first-page":"2958","DOI":"10.1364\/BOE.521453","type":"journal-article","article-title":"PSCAT: a lightweight transformer for simultaneous denoising and super-resolution of OCT images","volume":"15","author":"Yao","year":"2024","journal-title":"Biomed. Opt. Express"},{"key":"bpexae2127bib30","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1016\/j.ajo.2020.07.020","type":"journal-article","article-title":"Lightweight learning-based automatic segmentation of subretinal blebs on microscope-integrated optical coherence tomography images","volume":"221","author":"Song","year":"2021","journal-title":"Am. J. Ophthalmol."},{"key":"bpexae2127bib31","first-page":"1","type":"journal-article","article-title":"Light-weight retinal layer segmentation with global reasoning","volume":"73","author":"He","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"bpexae2127bib32","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.compbiomed.2023.107120","type":"journal-article","article-title":"AMSUnet: a neural network using atrous multi-scale convolution for medical image segmentation","volume":"162","author":"Yin","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"bpexae2127bib33","doi-asserted-by":"publisher","first-page":"3860","DOI":"10.1109\/JBHI.2023.3331278","type":"journal-article","article-title":"LDMRes-Net: a lightweight neural network for efficient medical image segmentation on IoT and edge devices","volume":"28","author":"Iqbal","year":"2024","journal-title":"IEEE J Biomed Health Inform."},{"key":"bpexae2127bib34","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1371\/journal.pone.0186949","type":"journal-article","article-title":"Fully-automated segmentation of fluid regions in exudative age-related macular degeneration subjects: Kernel graph cut in neutrosophic domain","volume":"12","author":"Rashno","year":"2017","journal-title":"PLoS One"},{"key":"bpexae2127bib35","first-page":"989","type":"journal-article","article-title":"Fully automated segmentation of fluid\/cyst regions in optical coherence tomography images with diabetic macular edema using neutrosophic sets and graph algorithms","volume":"65","author":"Rashno","year":"2018","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae2127bib36","doi-asserted-by":"publisher","DOI":"10.21227\/55pk-8z03","type":"dataset","article-title":"PALM: Pathologic Myopia Challenge","author":"Fu","year":"2019","unstructured":"Fu H 2019 PALM: Pathologic Myopia Challenge IEEE Dataport 10.21227\/55pk-8z03"},{"key":"bpexae2127bib37","article-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019","type":"conference-proceedings"},{"key":"bpexae2127bib38","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","type":"preprint"},{"key":"bpexae2127bib39","first-page":"116","type":"conference-proceedings","article-title":"Shufflenet v2: practical guidelines for efficient cnn architecture design","author":"Ma","year":"2018"},{"key":"bpexae2127bib40","first-page":"1314","type":"conference-proceedings","article-title":"Searching for mobilenetv3","author":"Howard","year":"2019"},{"key":"bpexae2127bib41","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1117\/1.JRS.14.044512","type":"journal-article","article-title":"Improved U-Nets with inception blocks for building detection","volume":"14","author":"Delibasoglu","year":"2020","journal-title":"J. Appl. Remote Sens."},{"key":"bpexae2127bib42","doi-asserted-by":"publisher","first-page":"3205","DOI":"10.1109\/TNNLS.2022.3176493","type":"journal-article","article-title":"LMFFNet: a well-balanced lightweight network for fast and accurate semantic segmentation","volume":"34","author":"Shi","year":"2023","journal-title":"IEEE Trans Neural Netw. Learn. Syst."}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2127","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2127\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2127","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2127\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2127\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2127\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2127\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2127\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T10:56:37Z","timestamp":1765450597000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2127"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,11]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12,11]]},"published-print":{"date-parts":[[2026,2,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae2127","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,11]]},"assertion":[{"value":"OCTSeg-UNeXt: an ultralight hybrid Conv-MLP network for retinal pathology segmentation in point-of-care OCT imaging","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 2025 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":"2025-08-18","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-11-19","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-12-11","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}