SEFormer:A new method for Medical Image Segmentation

SEFormer:A new method for Medical Image Segmentation | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article SEFormer:A new method for Medical Image Segmentation Chen Ge, Haoze Pan, Yihua Song, Xia Zhang, Zuojian Zhou This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6535669/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 24 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Medical image segmentation is a fundamental task in medical image analysis, playing a crucial role in disease diagnosis, treatment planning, and clinical decision-making. Accurate segmentation of anatomical structures, such as blood vessels, organs, and lesions, is essential for reliable medical interpretations. However, existing segmentation models often face challenges in effectively capturing both local and global features within medical images. Traditional convolutional neural networks (CNNs) excel at extracting fine-grained local features but struggle to model long-range dependencies due to their limited receptive fields. Conversely, transformer-based models can capture global contextual relationships but often fail to preserve detailed local structures, leading to suboptimal segmentation performance. The purpose of this study is to develop SEFormer, a novel hybrid network that integrates SENet, ResNet, and Transformer to enhance medical image segmentation. SEFormer aims to effectively capture both local and global features, addressing the limitations of traditional CNNs and transformer-based models.SENet is incorporated to recalibrate feature maps by adaptively emphasizing informative features, thereby compensating for the global representation limitations of CNNs. Meanwhile, the ResNet backbone ensures deep feature extraction while maintaining computational efficiency. Additionally, the Transformer module is introduced to capture long-range dependencies and enhance contextual awareness, complementing the local feature extraction capabilities of CNNs. This hybrid approach allows SEFormer to balance fine-grained spatial details with broader contextual information, leading to more precise segmentation results.Furthermore, to mitigate information loss during feature extraction and ensure a more complete and hierarchical representation of image information, we introduce a feature pyramid structure inspired by multi-scale image pyramid models. By progressively increasing the receptive field across different scales and employing skip connections, SEFormer effectively fuses multi-scale local and global features at each stage of the pyramid. This hierarchical fusion mechanism ensures a richer and more robust feature representation, which is particularly beneficial for segmenting complex medical structures such as blood vessels. We evaluate SEFormer on the CHASE_DB1 dataset, a widely used benchmark for retinal vessel segmentation. Experimental results demonstrate that SEFormer outperforms existing state-of-the-art segmentation methods, achieving a 3.25% improvement in segmentation accuracy. Additionally, we conduct ablation studies to verify the contributions of different components within SEFormer. The results show that incorporating SENet enhances feature recalibration and channel attention, while the Transformer module significantly improves global context awareness. The feature pyramid structure further contributes to performance gains by ensuring a multi-scale representation of vascular structures. Compared to conventional CNN-based methods, our approach achieves better segmentation accuracy with improved robustness to variations in vessel thickness, noise, and image contrast. Furthermore, SEFormer maintains computational efficiency, making it suitable for real-world clinical applications where both accuracy and processing speed are critical. SEFormer provides an efficient and accurate approach for medical image segmentation by leveraging the complementary strengths of CNNs, SENet, and Transformers while integrating a feature pyramid structure to maximize feature representation. Future research directions include extending SEFormer to other medical imaging modalities, such as CT and MRI scans, as well as exploring further optimization techniques to reduce computational costs while maintaining high segmentation performance. Additionally, integrating SEFormer with active learning frameworks could further improve segmentation performance by leveraging expert-annotated data more efficiently. Biological sciences/Computational biology and bioinformatics Health sciences/Medical research Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 24 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 26 Jun, 2025 Reviews received at journal 24 Jun, 2025 Reviewers agreed at journal 08 Jun, 2025 Reviews received at journal 07 Jun, 2025 Reviewers agreed at journal 07 Jun, 2025 Reviewers invited by journal 06 Jun, 2025 Editor assigned by journal 06 Jun, 2025 Editor invited by journal 12 May, 2025 Submission checks completed at journal 10 May, 2025 First submitted to journal 26 Apr, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6535669","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":468159264,"identity":"48e74778-eb53-4228-a217-3eccce8188ab","order_by":0,"name":"Chen Ge","email":"","orcid":"","institution":"Shandong Vocational and Technical University of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Chen","middleName":"","lastName":"Ge","suffix":""},{"id":468159265,"identity":"e1b79d5e-365d-4747-a2af-241e8d6778aa","order_by":1,"name":"Haoze Pan","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Haoze","middleName":"","lastName":"Pan","suffix":""},{"id":468159266,"identity":"9a1f2917-b676-4073-aff3-d8b6d80dcd92","order_by":2,"name":"Yihua Song","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+0lEQVRIiWNgGAWjYDACZh446wCDBIRlQKwWtgQitTDAtfDAVeLXYnCc95jED4Y6OXP+Nd8eWLbZRTOwN2+TYKi5g1vLYb40yR6Gw8aWM95uN5BsS85t4DlWJsFw7BkeLTxmEjwMBxI33Di7TUKy7UBug0SOmQRjw2G8WiT/MNQBtZx5BtEi/4awFmkeBubEDed72KC28ODXInmYx9haxuCwscENNjMJiXPJuW08acUWCcdwa+E7f8bw5puKOjmD84efSUuU2eX2sx/eeONDDW4tCgfAzgNiiQQGZlBUsoEEEnBqYGCQb4Cx+A8wMH7Ao3IUjIJRMApGLgAAN0hP5IL40t0AAAAASUVORK5CYII=","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":true,"prefix":"","firstName":"Yihua","middleName":"","lastName":"Song","suffix":""},{"id":468159268,"identity":"1e6d463d-bb47-45fc-9d6f-403211424349","order_by":3,"name":"Xia Zhang","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xia","middleName":"","lastName":"Zhang","suffix":""},{"id":468159270,"identity":"75fd23bf-093e-4a13-961d-cca561976ee2","order_by":4,"name":"Zuojian Zhou","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Zuojian","middleName":"","lastName":"Zhou","suffix":""}],"badges":[],"createdAt":"2025-04-26 14:38:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6535669/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6535669/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-25450-1","type":"published","date":"2025-11-24T15:57:56+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":97178435,"identity":"806f4924-c2f7-4a63-90fb-3912418e56a8","added_by":"auto","created_at":"2025-12-01 16:10:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":476799,"visible":true,"origin":"","legend":"","description":"","filename":"SEFormerAnewmethodforMedicalImageSegmentation0509.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6535669/v1_covered_d8c49794-935e-41cb-a780-82a13e040b43.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"SEFormer:A new method for Medical Image Segmentation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6535669/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6535669/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMedical image segmentation is a fundamental task in medical image analysis, playing a crucial role in disease diagnosis, treatment planning, and clinical decision-making. Accurate segmentation of anatomical structures, such as blood vessels, organs, and lesions, is essential for reliable medical interpretations. However, existing segmentation models often face challenges in effectively capturing both local and global features within medical images. Traditional convolutional neural networks (CNNs) excel at extracting fine-grained local features but struggle to model long-range dependencies due to their limited receptive fields. Conversely, transformer-based models can capture global contextual relationships but often fail to preserve detailed local structures, leading to suboptimal segmentation performance.\u003cstrong\u003e \u003c/strong\u003eThe purpose of this study is to develop SEFormer, a novel hybrid network that integrates SENet, ResNet, and Transformer to enhance medical image segmentation. SEFormer aims to effectively capture both local and global features, addressing the limitations of traditional CNNs and transformer-based models.SENet is incorporated to recalibrate feature maps by adaptively emphasizing informative features, thereby compensating for the global representation limitations of CNNs. Meanwhile, the ResNet backbone ensures deep feature extraction while maintaining computational efficiency. Additionally, the Transformer module is introduced to capture long-range dependencies and enhance contextual awareness, complementing the local feature extraction capabilities of CNNs. This hybrid approach allows SEFormer to balance fine-grained spatial details with broader contextual information, leading to more precise segmentation results.Furthermore, to mitigate information loss during feature extraction and ensure a more complete and hierarchical representation of image information, we introduce a feature pyramid structure inspired by multi-scale image pyramid models. By progressively increasing the receptive field across different scales and employing skip connections, SEFormer effectively fuses multi-scale local and global features at each stage of the pyramid. This hierarchical fusion mechanism ensures a richer and more robust feature representation, which is particularly beneficial for segmenting complex medical structures such as blood vessels. We evaluate SEFormer on the CHASE_DB1 dataset, a widely used benchmark for retinal vessel segmentation. Experimental results demonstrate that SEFormer outperforms existing state-of-the-art segmentation methods, achieving a 3.25% improvement in segmentation accuracy. Additionally, we conduct ablation studies to verify the contributions of different components within SEFormer. The results show that incorporating SENet enhances feature recalibration and channel attention, while the Transformer module significantly improves global context awareness. The feature pyramid structure further contributes to performance gains by ensuring a multi-scale representation of vascular structures. Compared to conventional CNN-based methods, our approach achieves better segmentation accuracy with improved robustness to variations in vessel thickness, noise, and image contrast. Furthermore, SEFormer maintains computational efficiency, making it suitable for real-world clinical applications where both accuracy and processing speed are critical.\u003cstrong\u003e \u003c/strong\u003eSEFormer provides an efficient and accurate approach for medical image segmentation by leveraging the complementary strengths of CNNs, SENet, and Transformers while integrating a feature pyramid structure to maximize feature representation. Future research directions include extending SEFormer to other medical imaging modalities, such as CT and MRI scans, as well as exploring further optimization techniques to reduce computational costs while maintaining high segmentation performance. Additionally, integrating SEFormer with active learning frameworks could further improve segmentation performance by leveraging expert-annotated data more efficiently.\u003c/p\u003e","manuscriptTitle":"SEFormer:A new method for Medical Image Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-09 14:31:11","doi":"10.21203/rs.3.rs-6535669/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-26T17:32:46+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-24T20:20:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"24942606484773387188469246355309095621","date":"2025-06-08T13:55:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-07T10:08:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"214335683788599101672156332678598776812","date":"2025-06-07T04:34:52+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-06T10:58:02+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-06T10:53:20+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-05-13T03:59:35+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-10T17:24:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-04-26T14:29:46+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"72a5d9de-3f97-4d3c-af08-c9d082a55797","owner":[],"postedDate":"June 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":49704175,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":49704176,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2025-12-01T16:02:31+00:00","versionOfRecord":{"articleIdentity":"rs-6535669","link":"https://doi.org/10.1038/s41598-025-25450-1","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-11-24 15:57:56","publishedOnDateReadable":"November 24th, 2025"},"versionCreatedAt":"2025-06-09 14:31:11","video":"","vorDoi":"10.1038/s41598-025-25450-1","vorDoiUrl":"https://doi.org/10.1038/s41598-025-25450-1","workflowStages":[]},"version":"v1","identity":"rs-6535669","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6535669","identity":"rs-6535669","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}