An Explainable SSL-Based Model for Robust Multi-Class Brain Tumor Classification from MRI Images

preprint OA: closed
Full text JSON View at publisher
AI-generated deep summary by claude@2026-07, 2026-07-06 · read from full text

This preprint describes an explainable self-supervised learning framework for robust multi-class brain tumor classification from MRI using a SimCLR approach with an EfficientNetB3 backbone, fine-tuned for four classes (glioma, meningioma, pituitary tumor, and no-tumor). The authors report that SSL pre-training on unlabeled data improves generalization with minimal dependence on large-scale human annotation, and they report test accuracy of 98.32% with per-class precision, recall, and F1 all above 96% and best performance for no-tumor and pituitary classes. Explainability is addressed via Grad-CAM, with visualization and validation that the model’s attention aligns with radiological tumor regions. This paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Abstract

Abstract Accurate and interpretable brain tumor classification from magnetiSSc resonance imaging (MRI) is important for timely detection and effective treatment planning. Deep supervised learning methods, though strong, are limited by their reliance on vast labeled datasets and their lack of explainability in clinical decision-making. In this work, we introduce a self-supervised learning (SSL) approach based on SimCLR with EfficientNetB3 backbone for four-class brain tumor segmentation: glioma, meningioma, pituitary tumor, and no-tumor. The method employs SSL-based model pre-training on large amounts of unlabeled data to learn salient feature representations prior to performing supervised fine-tuning with an optimal classifier head. The technique effectively enhances generalization with minimal dependence on large-scale human annotation. The envisioned framework has a test accuracy of 98.32%, per-class precision, recall, and F1-measures over 96%, and best classification performance in no-tumor and pituitary classes. For improving interpretability and clinical confidence, Gradient-weighted Class Activation Mapping (Grad-CAM) was used with discriminative tumor region visualization and validation that model attention is in agreement with radiological features. To the best knowledge of the authors, it is the first work that combines an optimized SimCLR-based SSL with brain tumor classification using MRI and explainability. The results show that SSL-driven and interpretable models can have the capability of producing highly accurate, reliable, and clinically relevant decision support for neuro-oncology.
Full text 27,598 characters · extracted from preprint-html · click to expand
An Explainable SSL-Based Model for Robust Multi-Class Brain Tumor Classification from MRI Images | 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 Research Article An Explainable SSL-Based Model for Robust Multi-Class Brain Tumor Classification from MRI Images Md.Faishal Ahmed Rudro, Shajedul Hasan Arman, Omar faruque siyam, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7725530/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Accurate and interpretable brain tumor classification from magnetiSSc resonance imaging (MRI) is important for timely detection and effective treatment planning. Deep supervised learning methods, though strong, are limited by their reliance on vast labeled datasets and their lack of explainability in clinical decision-making. In this work, we introduce a self-supervised learning (SSL) approach based on SimCLR with EfficientNetB3 backbone for four-class brain tumor segmentation: glioma, meningioma, pituitary tumor, and no-tumor. The method employs SSL-based model pre-training on large amounts of unlabeled data to learn salient feature representations prior to performing supervised fine-tuning with an optimal classifier head. The technique effectively enhances generalization with minimal dependence on large-scale human annotation. The envisioned framework has a test accuracy of 98.32%, per-class precision, recall, and F1-measures over 96%, and best classification performance in no-tumor and pituitary classes. For improving interpretability and clinical confidence, Gradient-weighted Class Activation Mapping (Grad-CAM) was used with discriminative tumor region visualization and validation that model attention is in agreement with radiological features. To the best knowledge of the authors, it is the first work that combines an optimized SimCLR-based SSL with brain tumor classification using MRI and explainability. The results show that SSL-driven and interpretable models can have the capability of producing highly accurate, reliable, and clinically relevant decision support for neuro-oncology. Brain Tumor Classification Self-Supervised Learning SimCLR EfficientNet Medical Imaging Explainable AI Grad-CAM Clinical Decision Support Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-7725530","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":525136014,"identity":"8a01a2fe-094c-4711-ba9a-65d9c9515e1b","order_by":0,"name":"Md.Faishal Ahmed Rudro","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCElEQVRIiWNgGAWjYFCCBIYPDAZAkh3I5mFgkAOJHXiAXwvjDLAWZogWY7CWBIJaGBBaEhsgVuMGuu0JjA0/Cury+Jt5n0m83WOTPj/s8EOgLXZyug3YtZidecDY2GNwuFjiMLuZ5Jxnabkbb6cZALUkG5sdwKHlRgL7Ax6DA4kNh9nYpHkOHM7dODsBpOVA4jbcWhgb/xjUJc6Hakk3nJ3+gaCWZh4D5sQNUC0J8tI5BGw587CxWcbgcOLGw2zMlnMOpBlukM4pOJBggMcvx5MPNr75U5c473gb4403B2zk5Wenb/7wocJODpcWBgbGBlS+AVilAS7l2IB8A0Elo2AUjIJRMMIAAIdUZaAP6LLtAAAAAElFTkSuQmCC","orcid":"","institution":"East West University","correspondingAuthor":true,"prefix":"","firstName":"Md.Faishal","middleName":"Ahmed","lastName":"Rudro","suffix":""},{"id":525136015,"identity":"66f38b26-e227-4ad5-8483-261f0f8819a8","order_by":1,"name":"Shajedul Hasan Arman","email":"","orcid":"","institution":"University of Central Florida","correspondingAuthor":false,"prefix":"","firstName":"Shajedul","middleName":"Hasan","lastName":"Arman","suffix":""},{"id":525136016,"identity":"1510395f-822b-4f55-b92a-f3da0068f3ed","order_by":2,"name":"Omar faruque siyam","email":"","orcid":"","institution":"University of Central Florida","correspondingAuthor":false,"prefix":"","firstName":"Omar","middleName":"faruque","lastName":"siyam","suffix":""},{"id":525136017,"identity":"e9f328a7-9120-4447-99a5-343109bd0bb6","order_by":3,"name":"Nur Nabi Rahman","email":"","orcid":"","institution":"Jagannath University","correspondingAuthor":false,"prefix":"","firstName":"Nur","middleName":"Nabi","lastName":"Rahman","suffix":""},{"id":525136018,"identity":"ba510ef5-01e8-4c18-8700-7149e5244fd3","order_by":4,"name":"Anzim Hasan Nabil","email":"","orcid":"","institution":"Govt. Science College, Tejgaon, Dhaka","correspondingAuthor":false,"prefix":"","firstName":"Anzim","middleName":"Hasan","lastName":"Nabil","suffix":""},{"id":525136019,"identity":"d199329e-e1d2-4075-b0b5-5cd898b4ae6f","order_by":5,"name":"Afiah Rahman","email":"","orcid":"","institution":"University of Asia Pacific","correspondingAuthor":false,"prefix":"","firstName":"Afiah","middleName":"","lastName":"Rahman","suffix":""},{"id":525136020,"identity":"bd15274f-343f-4700-b908-9bc6750557e3","order_by":6,"name":"Zannatul Ferdus","email":"","orcid":"","institution":"Ahsanullah University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zannatul","middleName":"","lastName":"Ferdus","suffix":""}],"badges":[],"createdAt":"2025-09-27 03:23:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7725530/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7725530/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93035580,"identity":"6f824f9c-bc4f-409d-963b-6023de379da0","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2380653,"visible":true,"origin":"","legend":"","description":"","filename":"BraintumorSimCLR.docx","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/ae1b722f4e08c5012732d795.docx"},{"id":93035571,"identity":"5e40e278-2375-4121-8a64-665d3da59bd4","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8335,"visible":true,"origin":"","legend":"","description":"","filename":"153c6a4919654ecd8a0ac36d391fbe1c.json","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/2113381dd7140041293f49ab.json"},{"id":93035572,"identity":"ca58aa56-666b-4302-9d57-b609f32431e7","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110533,"visible":true,"origin":"","legend":"","description":"","filename":"153c6a4919654ecd8a0ac36d391fbe1c1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/fd950204e224e75276f4bc9c.xml"},{"id":93035579,"identity":"0abaa0d3-348c-464a-8bb6-532607a751eb","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":545591,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/74c2384585024b55c8ed04c5.png"},{"id":93035573,"identity":"0eec6126-a78c-4db4-aeb8-2fda8524a186","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27556,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/5d90a242e8a6c249c403aaee.png"},{"id":93036310,"identity":"e0439b08-a199-47ba-a059-fa4cd35b2a64","added_by":"auto","created_at":"2025-10-08 11:13:25","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20357,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/eecd6eecd65392ea0e27fe26.png"},{"id":93035596,"identity":"30d69415-e926-43d0-8c1e-434d74b0b0bf","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16613,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/3cfecf1eba44fcae8afbddaf.png"},{"id":93035603,"identity":"26080425-4600-47ab-9c7e-0be0473662cc","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":101911,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/0376af3698f9f1f0958a904b.png"},{"id":93035574,"identity":"cc211320-ff3b-4086-bca1-d7c397c5ac6f","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41139,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/9010a4826fba699febcccb7a.png"},{"id":93035593,"identity":"792452d2-bba5-4b8d-b207-36765c3e9397","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":171142,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/641ae567a17b1af73cfba42d.png"},{"id":93035585,"identity":"604150da-3036-44f8-9bc6-939969c6c882","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"jpeg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":61939,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage16.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/1b507e77fa0fc89e19f0603f.jpeg"},{"id":93036311,"identity":"a10f915a-f504-453b-9c25-09ef8be634e5","added_by":"auto","created_at":"2025-10-08 11:13:25","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":387102,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/6f94f67f581363fb58c130c5.png"},{"id":93036313,"identity":"d00ff916-dea2-40e9-8c94-8b123f542d1c","added_by":"auto","created_at":"2025-10-08 11:13:26","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":136297,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/c1a719581f65de692f3a4e82.png"},{"id":93035586,"identity":"aeaf853c-8a0d-49f8-9b0c-b732421dfc6a","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":203046,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/4a954d31a0fae066fe764288.png"},{"id":93036308,"identity":"6e876921-b54b-45d0-bc3c-2baec18c806c","added_by":"auto","created_at":"2025-10-08 11:13:23","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":320535,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/5f22fe50b111e9e20f5a4555.png"},{"id":93035582,"identity":"d5457287-321f-439a-8596-ed55862ceeb6","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":363852,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/eec46a59208d1c750695c5d7.png"},{"id":93035589,"identity":"91355b0a-6da2-4f56-b4b5-f89a7869afe5","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17842,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/a18595d39294cafc04e71241.png"},{"id":93035595,"identity":"921e5f70-3498-4dfa-881f-b6e859b56b5a","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13312,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/614f44379d6a67e5f2cc16ae.png"},{"id":93035594,"identity":"527b9835-64b6-4d30-a7de-1856c3d72906","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13013,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/9fac46e031aa7aae617beddc.png"},{"id":93035598,"identity":"ab0f9fae-c8ed-4796-b608-e234a787ef89","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91961,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/a24dfef4e2bcc469c05cc100.png"},{"id":93035591,"identity":"2f46f734-b74c-4012-81bb-03bf5d945932","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6116,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/08b5fc9f68cb41968a66261d.png"},{"id":93035618,"identity":"7edd8b88-99a0-4e40-9034-c0d48dcb816a","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4937,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/e292a8c5a95f575f29f54eab.png"},{"id":93036309,"identity":"c7a339a4-b4db-46be-818f-c03702b6cb70","added_by":"auto","created_at":"2025-10-08 11:13:24","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4400,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/1fab2c2b21cb7dbf7167564d.png"},{"id":93036312,"identity":"3fdac9d4-5939-4d3d-9586-0598359e967f","added_by":"auto","created_at":"2025-10-08 11:13:26","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23702,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/ddf02b75e4f24a199c4f3ec1.png"},{"id":93035604,"identity":"16b53765-8d43-435a-8b59-fc4cb858ce7f","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10827,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/0a6b191d506a191d4dc2a51b.png"},{"id":93035608,"identity":"07bb15d2-c130-431a-ab86-724df1a78526","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29301,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/8d27a7ab756253a3445762a6.png"},{"id":93035577,"identity":"5fa73674-eb23-4ece-afdd-d922e0fff65b","added_by":"auto","created_at":"2025-10-08 11:05:22","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":59736,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/b7897c4b5065fe0c1ba49d22.png"},{"id":93035617,"identity":"226ef5d4-922b-4abe-b441-6771ca8ceabe","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":89578,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/43112a0660021e8b6dcf0501.png"},{"id":93036314,"identity":"b80d84db-9e15-4068-984b-1330928bfaed","added_by":"auto","created_at":"2025-10-08 11:13:26","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18706,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/84347c6103485672a256dcd2.png"},{"id":93035623,"identity":"ecb9b0fb-eae3-443f-b1a3-65a9cde4538e","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26238,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/2c1f0361cc701fb861688c96.png"},{"id":93035611,"identity":"61a9c034-83c3-4ad5-80e5-483c774d4126","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37121,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/3a63095e1b18eb3f1a39f381.png"},{"id":93035605,"identity":"c0b389cf-4948-44f6-9b58-3b8fed2220d4","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70773,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/fc5a370c7ffac8d07a0362e0.png"},{"id":93035615,"identity":"29d7691f-b214-493e-8598-d1bf288384b1","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4610,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/bf14a014beeef00d881a6c4a.png"},{"id":93035624,"identity":"867c0186-df1c-4fb1-a96f-e85c010576fe","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2996,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/2569a8205e34fc2ae78bc934.png"},{"id":93035602,"identity":"553a2fe0-d0c1-4126-b8da-968552afb7a8","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"png","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2884,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/923a4968f7d9bb360d6887ed.png"},{"id":93035613,"identity":"672ca4dc-2211-4c7c-9ebe-e39905fa6e73","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"xml","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110663,"visible":true,"origin":"","legend":"","description":"","filename":"153c6a4919654ecd8a0ac36d391fbe1c1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/7139bfc87d0c5dbc9b7a52f1.xml"},{"id":93035620,"identity":"612cce47-a533-4d32-88af-b48ff6e3332e","added_by":"auto","created_at":"2025-10-08 11:05:23","extension":"html","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":119228,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1/67a2a6b71e7f5eab9d7a2f86.html"},{"id":93808991,"identity":"65aab962-ad75-45d1-96e6-11cacd419e7d","added_by":"auto","created_at":"2025-10-17 19:01:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1107720,"visible":true,"origin":"","legend":"","description":"","filename":"BraintumorSimCLR2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7725530/v1_covered_0f7eb2bc-1271-44ba-97c4-2ec30af88dc7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Explainable SSL-Based Model for Robust Multi-Class Brain Tumor Classification from MRI Images","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Brain Tumor Classification, Self-Supervised Learning, SimCLR, EfficientNet, Medical Imaging, Explainable AI, Grad-CAM, Clinical Decision Support","lastPublishedDoi":"10.21203/rs.3.rs-7725530/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7725530/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate and interpretable brain tumor classification from magnetiSSc resonance imaging (MRI) is important for timely detection and effective treatment planning. Deep supervised learning methods, though strong, are limited by their reliance on vast labeled datasets and their lack of explainability in clinical decision-making. In this work, we introduce a self-supervised learning (SSL) approach based on SimCLR with EfficientNetB3 backbone for four-class brain tumor segmentation: glioma, meningioma, pituitary tumor, and no-tumor. The method employs SSL-based model pre-training on large amounts of unlabeled data to learn salient feature representations prior to performing supervised fine-tuning with an optimal classifier head. The technique effectively enhances generalization with minimal dependence on large-scale human annotation. The envisioned framework has a test accuracy of 98.32%, per-class precision, recall, and F1-measures over 96%, and best classification performance in no-tumor and pituitary classes. For improving interpretability and clinical confidence, Gradient-weighted Class Activation Mapping (Grad-CAM) was used with discriminative tumor region visualization and validation that model attention is in agreement with radiological features. To the best knowledge of the authors, it is the first work that combines an optimized SimCLR-based SSL with brain tumor classification using MRI and explainability. The results show that SSL-driven and interpretable models can have the capability of producing highly accurate, reliable, and clinically relevant decision support for neuro-oncology.\u003c/p\u003e","manuscriptTitle":"An Explainable SSL-Based Model for Robust Multi-Class Brain Tumor Classification from MRI Images","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-08 11:05:16","doi":"10.21203/rs.3.rs-7725530/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"adaf2cf4-093a-4083-8c37-faaec1024d03","owner":[],"postedDate":"October 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-22T15:55:47+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-08 11:05:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7725530","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7725530","identity":"rs-7725530","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00