{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T08:39:20Z","timestamp":1769848760862,"version":"3.49.0"},"reference-count":44,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Fundamental Research Program of Shanxi Province","award":["202403021221141"],"award-info":[{"award-number":["202403021221141"]}]}],"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>\n                    Research on deep learning for medical image segmentation has shifted from single-modality networks to multimodal data fusion. Updating the parameters of such deep learning models is crucial for accurate segmentation predictions. Although existing optimizers can perform global parameter updates, the fine-grained initialization of learning rates across different network hierarchies and its influence on segmentation performance has not been sufficiently explored. To address this, we conducted a series of experiments showing that the initialization of a differentiated learning rate across network layers directly affected the performance of medical image segmentation models. To determine the optimal initial learning rate for each network level, we summarized a general statistical relationship between early-stage training results and the model\u2019s final optimal performance. In this paper, we proposed a fine-grained learning rate configuration algorithm. To verify the effectiveness of the proposed algorithm, we evaluated 10 segmentation models on three benchmark datasets: the colon polyp segmentation dataset CVC-ClinicDB, the gastrointestinal polyp dataset Kvasir-SEG, and the breast tumor segmentation dataset BUSI. The models that achieved the most significant improvement in mIoU on these three datasets were H-vmunet, MSRUNet, and H-vmunet, with increases of 3.87%, 4.67%, and 6.22%, respectively. Additionally, we validated the generalization and transferability of the proposed algorithm using a thyroid nodule segmentation dataset and a skin lesion segmentation dataset. Finally, a series of analyses, including segmentation result analysis, feature map visualization, training process analysis, computational overhead analysis, and clinical relevance analysis, confirmed the effectiveness of the proposed method. The core code is publicly available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Lambda-Wave\/PaperCoreCode\">https:\/\/github.com\/Lambda-Wave\/PaperCoreCode<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/ae3830","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T22:47:55Z","timestamp":1768430875000},"page":"015060","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Impact of fine-grained learning rate configuration on the performance of medical image segmentation models"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5876-423X","authenticated-orcid":true,"given":"Fang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0470-2352","authenticated-orcid":true,"given":"Jing","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaimei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"bpexae3830bib1","doi-asserted-by":"publisher","first-page":"111225","DOI":"10.1016\/j.engappai.2025.111225","type":"journal-article","article-title":"A survey on state-of-the-art deep learning applications and challenges","volume":"159","author":"Mohd Noor","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"bpexae3830bib2","doi-asserted-by":"publisher","first-page":"108270","DOI":"10.1016\/j.bspc.2025.108270","type":"journal-article","article-title":"VM-SwinUNet: attention-guided deep placental vessel network with mixture-of-experts for medical image segmentation","volume":"110","author":"Memon","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae3830bib3","doi-asserted-by":"publisher","first-page":"195016","DOI":"10.1088\/1361-6560\/ae0976","type":"journal-article","article-title":"Hybrid-MedNet: a hybrid cnn-transformer network with multi-dimensional feature fusion for medical image segmentation","volume":"70","author":"Memon","year":"2025","journal-title":"Phys. Med. Biol."},{"key":"bpexae3830bib4","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1109\/TMI.2023.3290356","type":"journal-article","article-title":"Multi-ConDoS: multimodal contrastive domain sharing generative adversarial networks for self-supervised medical image segmentation","volume":"43","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae3830bib5","doi-asserted-by":"publisher","first-page":"5242","DOI":"10.21037\/qims-22-1367","type":"journal-article","article-title":"Modality preserving U-Net for segmentation of multimodal medical images","volume":"13","author":"Wu","year":"2023","journal-title":"Quant. Imaging Med. Surg."},{"key":"bpexae3830bib6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3500067","type":"journal-article","article-title":"Prototype-driven and multi-expert integrated multi-modal MR brain tumor image segmentation","volume":"74","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"bpexae3830bib7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2025.3527526","type":"journal-article","article-title":"Frequency-enhanced lightweight vision mamba network for medical image segmentation","volume":"74","author":"Liu","year":"2025","journal-title":"IEEE Trans. Instrum. Meas"},{"key":"bpexae3830bib8","doi-asserted-by":"publisher","first-page":"676","DOI":"10.3390\/electronics14040676","type":"journal-article","article-title":"Lightweight denoising diffusion implicit model for medical segmentation","volume":"14","author":"Oh","year":"2025","journal-title":"Electronics"},{"key":"bpexae3830bib9","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/s10044-025-01424-x","type":"journal-article","article-title":"LMFR-Net: lightweight multi-scale feature refinement network for retinal vessel segmentation","volume":"28","author":"Zhang","year":"2025","journal-title":"Pattern Anal. Appl."},{"key":"bpexae3830bib10","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1109\/TMI.2022.3143371","type":"journal-article","article-title":"Data-driven deep supervision for medical image segmentation","volume":"41","author":"Mishra","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae3830bib11","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1109\/LSP.2024.3356414","type":"journal-article","article-title":"Adaptive multiphase liver tumor segmentation with multiscale supervision","volume":"31","author":"Kuang","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"key":"bpexae3830bib12","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1109\/JAS.2023.123813","type":"journal-article","article-title":"Dendritic deep learning for medical segmentation","volume":"11","author":"Liu","year":"2024","journal-title":"IEEE\/CAA J. Autom. Sinica"},{"key":"bpexae3830bib13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10586-025-05707-0","type":"journal-article","article-title":"DUC-Net: a deep unified cross-modal architecture with cascaded feature learning for medical image segmentation","volume":"28","author":"Memon","year":"2025","journal-title":"Cluster Comput"},{"key":"bpexae3830bib14","doi-asserted-by":"publisher","first-page":"129147","DOI":"10.1016\/j.neucom.2024.129147","type":"journal-article","article-title":"Cluster fusion based cross teaching for semi-supervised medical image segmentation","volume":"618","author":"Zhang","year":"2025","journal-title":"Neurocomputing"},{"key":"bpexae3830bib15","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/TMI.2023.3291719","type":"journal-article","article-title":"Lvit: language meets vision transformer in medical image segmentation","volume":"43","author":"Li","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae3830bib16","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s00530-024-01263-6","type":"journal-article","article-title":"RKSeg+: make full use of Runge\u2013Kutta methods in medical image segmentation","volume":"30","author":"Zhu","year":"2024","journal-title":"Multimedia Syst"},{"key":"bpexae3830bib17","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/TMI.2023.3317088","type":"journal-article","article-title":"MTANet: multi-task attention network for automatic medical image segmentation and classification","volume":"43","author":"Ling","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae3830bib18","doi-asserted-by":"publisher","first-page":"2665","DOI":"10.1109\/LSP.2024.3466608","type":"journal-article","article-title":"Edge-and-mask integration-driven diffusion models for medical image segmentation","volume":"31","author":"Tang","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"key":"bpexae3830bib19","doi-asserted-by":"publisher","first-page":"6543","DOI":"10.1007\/s10489-024-05496-w","type":"journal-article","article-title":"TransDiff: medical image segmentation method based on Swin transformer with diffusion probabilistic model","volume":"54","author":"Liu","year":"2024","journal-title":"Appl. Intell."},{"key":"bpexae3830bib20","first-page":"10012","type":"book","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"bpexae3830bib21","doi-asserted-by":"publisher","first-page":"2510","DOI":"10.1109\/TAI.2025.3550458","type":"journal-article","article-title":"Ensuring reliable learning in graph convolutional networks: convergence analysis and training methodology","volume":"6","author":"Zhao","year":"2025","journal-title":"IEEE Trans. Artif. Intell."},{"key":"bpexae3830bib22","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/j.ins.2022.12.039","type":"journal-article","article-title":"Leader population learning rate schedule","volume":"623","author":"Wei","year":"2023","journal-title":"Inf. Sci."},{"key":"bpexae3830bib23","doi-asserted-by":"publisher","first-page":"121607","DOI":"10.1016\/j.ins.2024.121607","type":"journal-article","article-title":"AdaLo: adaptive learning rate optimizer with loss for classification","volume":"690","author":"Jeong","year":"2025","journal-title":"Inf. Sci."},{"key":"bpexae3830bib24","author":"Naveen","year":"2024","type":"preprint"},{"key":"bpexae3830bib25","first-page":"234","type":"journal-article","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015","journal-title":"Med. Image Comput. Comput. Assist. Interv"},{"key":"bpexae3830bib26","doi-asserted-by":"publisher","first-page":"106274","DOI":"10.1016\/j.compbiomed.2022.106274","type":"journal-article","article-title":"MSRAformer: multiscale spatial reverse attention network for polyp segmentation","volume":"151","author":"Wu","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"bpexae3830bib27","doi-asserted-by":"publisher","first-page":"014005","DOI":"10.1117\/1.JMI.10.1.014005","type":"journal-article","article-title":"CaraNet: context axial reverse attention network for segmentation of small medical objects","volume":"10","author":"Lou","year":"2023","journal-title":"J. Med. Imaging"},{"key":"bpexae3830bib28","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1038\/s41598-023-50989-2","type":"journal-article","article-title":"UNet based on dynamic convolution decomposition and triplet attention","volume":"14","author":"Li","year":"2024","journal-title":"Sci. Rep"},{"key":"bpexae3830bib29","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":"bpexae3830bib30","doi-asserted-by":"publisher","first-page":"104863","DOI":"10.1016\/j.dib.2019.104863","type":"journal-article","article-title":"Dataset of breast ultrasound images","volume":"28","author":"Al-Dhabyani","year":"2020","journal-title":"Data Brief"},{"key":"bpexae3830bib31","first-page":"451","type":"book","article-title":"Kvasir-seg: a segmented polyp dataset","volume":"26","author":"Jha","year":"2020"},{"key":"bpexae3830bib32","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2563","type":"journal-article","article-title":"MSR-UNet: enhancing multi-scale and long-range dependencies in medical image segmentation","volume":"10","author":"Wang","year":"2024","journal-title":"PeerJ Comput. Sci"},{"key":"bpexae3830bib33","doi-asserted-by":"publisher","first-page":"8824","DOI":"10.21037\/qims-24-1229","type":"journal-article","article-title":"TAC-UNet: transformer-assisted convolutional neural network for medical image segmentation","volume":"14","author":"He","year":"2024","journal-title":"Quant. Imaging Med. Surg"},{"key":"bpexae3830bib34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00371-025-03832-w","type":"journal-article","article-title":"Dynamic neighbourhood-enhanced UNet with interwoven fusion for medical image segmentation","volume":"41","author":"Wan","year":"2025","journal-title":"Vis. Comput"},{"key":"bpexae3830bib35","doi-asserted-by":"publisher","first-page":"108526","DOI":"10.1016\/j.cmpb.2024.108526","type":"journal-article","article-title":"Laplacian-guided hierarchical transformer: a network for medical image segmentation","volume":"260","author":"Chen","year":"2025","journal-title":"Comput. Methods Programs Biomed"},{"key":"bpexae3830bib36","doi-asserted-by":"publisher","first-page":"107791","DOI":"10.1016\/j.bspc.2025.107791","type":"journal-article","article-title":"Dual-axis Generalized Cross Attention and Shape-aware Network for 2D medical image segmentation","volume":"107","author":"Zhang","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae3830bib37","doi-asserted-by":"publisher","first-page":"129447","DOI":"10.1016\/j.neucom.2025.129447","type":"journal-article","article-title":"H-vmunet: high-order vision Mamba UNet for medical image segmentation","volume":"624","author":"Wu","year":"2025","journal-title":"Neurocomput"},{"key":"bpexae3830bib38","first-page":"188","type":"journal-article","article-title":"An open access thyroid ultrasound image database","volume":"9287","author":"Pedraza","year":"2015","journal-title":"Proc. 10th Int. Symp. Med. Inf. Process. Anal"},{"key":"bpexae3830bib39","first-page":"168","type":"journal-article","article-title":"Skin lesion analysis toward melanoma detection: a challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC)","author":"Codella","year":"2018","journal-title":"Proc. IEEE Int. Symp. Biomed. Imaging"},{"key":"bpexae3830bib40","type":"other"},{"key":"bpexae3830bib41","type":"other"},{"key":"bpexae3830bib42","type":"other"},{"key":"bpexae3830bib43","type":"other"},{"key":"bpexae3830bib44","type":"other"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3830","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3830\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3830","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3830\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3830\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3830\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3830\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3830\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T18:24:21Z","timestamp":1769797461000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,30]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,30]]},"published-print":{"date-parts":[[2026,2,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae3830","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,30]]},"assertion":[{"value":"Impact of fine-grained learning rate configuration on the performance of medical image segmentation models","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":"2025-09-12","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-01-14","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-01-30","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}