Zone-Aware Pneumonia Classification Using Automated Lung Region Detection and Multi-Branch Feature Learning

preprint OA: closed
Full text JSON View at publisher
Full text 27,336 characters · extracted from preprint-html · click to expand
Zone-Aware Pneumonia Classification Using Automated Lung Region Detection and Multi-Branch Feature Learning | 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 Zone-Aware Pneumonia Classification Using Automated Lung Region Detection and Multi-Branch Feature Learning Fadl Dahan, Jamal Hussain Shah, Maira Afzal, Mohammed Aloqaily, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8100727/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Pneumonia is a major lung infection and remains one of the leading causes of death, especially among children under five and older adults. Early and accurate diagnosis often depends on chest X-rays, yet manual interpretation is challenging due to overlapping structures and low-contrast opacities. In this context, computer-based techniques have been proposed to assist radiologists in detecting pneumonia symptoms. Most existing techniques rely on deep learning models that extract features from the entire image to make classification decisions. While these approaches achieve high accuracy, they lack explainability, offering no clear information on where features are localized or how decisions are made. In this paper, we address two main limitations: (1) the localization of pneumonia-related features, and (2) the interpretability of deep features used for decision-making. This research presents a robust framework that integrates lung zone detection with multi-branch feature learning to classify pneumonia types and predict zone-specific findings. The proposed system consists of three phases. First, lung zone localization is performed to automatically focus on disease-relevant regions. Second, intra-zone CoT reasoning is introduced for zone-specific feature extraction, where lung zones detected by YOLOv8 are processed by ResNet-18 to capture local features. Third, attention-based inter-zone CoT fusion and classification is applied to predict pneumonia type and zone-level findings such as opacities and ground-glass patterns, aligning with radiology reporting standards. The proposed framework is evaluated on the Chest X-Ray Images (Pneumonia) dataset. It achieved an average accuracy of 94.4% and demonstrated notable improvements in detecting early-stage pneumonia. These results highlight the potential of the model as a decision-support tool for radiologists, enabling accurate diagnosis and standardized reporting in clinical practice. Pneumonia Detection Deep Learning YOLOv8 Lobe Detection Lung disease Chain-of-Thought (CoT) Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 27 Dec, 2025 Reviews received at journal 27 Dec, 2025 Reviews received at journal 23 Dec, 2025 Reviews received at journal 21 Dec, 2025 Reviewers agreed at journal 20 Dec, 2025 Reviewers agreed at journal 16 Dec, 2025 Reviewers agreed at journal 13 Dec, 2025 Reviewers agreed at journal 11 Dec, 2025 Reviewers agreed at journal 11 Dec, 2025 Reviewers invited by journal 30 Nov, 2025 Editor assigned by journal 21 Nov, 2025 Submission checks completed at journal 20 Nov, 2025 First submitted to journal 12 Nov, 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-8100727","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":553270872,"identity":"5c63d6f3-8c2f-48e1-a1c9-5080da245d33","order_by":0,"name":"Fadl Dahan","email":"","orcid":"","institution":"Prince Sattam bin Abdulaziz University","correspondingAuthor":false,"prefix":"","firstName":"Fadl","middleName":"","lastName":"Dahan","suffix":""},{"id":553270873,"identity":"c73bd3eb-ad9c-44d3-a97b-78a84143e5c8","order_by":1,"name":"Jamal Hussain Shah","email":"","orcid":"","institution":"COMSATS University Islamabad","correspondingAuthor":false,"prefix":"","firstName":"Jamal","middleName":"Hussain","lastName":"Shah","suffix":""},{"id":553270875,"identity":"732fa13f-8dda-45ad-a298-59b6c7200d11","order_by":2,"name":"Maira Afzal","email":"","orcid":"","institution":"COMSATS University Islamabad","correspondingAuthor":false,"prefix":"","firstName":"Maira","middleName":"","lastName":"Afzal","suffix":""},{"id":553270884,"identity":"7120091b-d401-4e5a-9428-ef797a515b19","order_by":3,"name":"Mohammed Aloqaily","email":"","orcid":"","institution":"Prince Sattam bin Abdulaziz University","correspondingAuthor":false,"prefix":"","firstName":"Mohammed","middleName":"","lastName":"Aloqaily","suffix":""},{"id":553270885,"identity":"2e04c40f-c16e-4394-940c-5cb109169d24","order_by":4,"name":"Refan Almohamedh","email":"","orcid":"","institution":"Prince Sattam bin Abdulaziz University","correspondingAuthor":false,"prefix":"","firstName":"Refan","middleName":"","lastName":"Almohamedh","suffix":""},{"id":553270891,"identity":"6fa31490-3914-49f3-9b3f-c51cb03070fa","order_by":5,"name":"Taha M. Alfakih","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA90lEQVRIie3QsWoCQRDG8REhWixcO4K+w4WF0yIkr+IiWKYRglXY4Yo0ou35FgYh9RwH2uwDXHn2KRZsLIRkz0KsNtoF3H+3xY9vWIBQ6F/W1BYYhxHw6dnQfwEBDcpq0tGO8A0EhnE9chV5aeWkD2bwKnMj9xaeeisWj5V3RSiiWYmThE2CDGPpiIz9h6mPSlhUX464wwrlSIJeEu2Ijo6stZGW4acm/YOXoKJUlKhWYGJ3GJ9WfAJEuaO0a1BlvHlDE4/ksniYeA9rLUY5fW/e1SIr1nY6fe7Nt+mn9c6cc1cB1F/VbHs/7KJIn5erK0koFArdSb9LbFlyjL1kdwAAAABJRU5ErkJggg==","orcid":"","institution":"Aljanad University for Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Taha","middleName":"M.","lastName":"Alfakih","suffix":""}],"badges":[],"createdAt":"2025-11-13 02:38:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8100727/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8100727/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97257983,"identity":"6cc1d450-1979-45fc-a739-9f0c58f8b767","added_by":"auto","created_at":"2025-12-02 13:43:27","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1498335,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/4e2ea779af60742267af1105.docx"},{"id":97366923,"identity":"3d4cbaa2-1867-4c16-9853-4a37a274bd17","added_by":"auto","created_at":"2025-12-03 16:13:43","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8320,"visible":true,"origin":"","legend":"","description":"","filename":"07c210f3499f4d338107ffee52ec05cc.json","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/8964b9a757eba293675ee4c6.json"},{"id":97367482,"identity":"c8cbd57d-e03b-4668-91fe-cad4678b9c4d","added_by":"auto","created_at":"2025-12-03 16:18:56","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":154396,"visible":true,"origin":"","legend":"","description":"","filename":"07c210f3499f4d338107ffee52ec05cc1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/231b3f41651199dc5d7a93b4.xml"},{"id":97257982,"identity":"d9632e9c-7382-4297-9c31-eccabcce6a4c","added_by":"auto","created_at":"2025-12-02 13:43:27","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86129,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/e90ee558856bee54dfe9fe50.jpeg"},{"id":97257980,"identity":"2a5c27a5-ef0c-40c3-a62c-817469974ad6","added_by":"auto","created_at":"2025-12-02 13:43:27","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49923,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/a6e9fca9af3f3344e6fc355b.jpeg"},{"id":97257984,"identity":"c97f0d46-9f2c-43d8-99f8-6250b05d2459","added_by":"auto","created_at":"2025-12-02 13:43:27","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49039,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/338661568478c8ac55c68a61.jpeg"},{"id":97368069,"identity":"db945f32-3ba4-4bda-9de0-71eb3558e56f","added_by":"auto","created_at":"2025-12-03 16:21:29","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48167,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/ccc438dfa3ef3f7105a5797a.jpeg"},{"id":97257987,"identity":"eee50a00-6492-42f2-b41a-bf548bc30fb3","added_by":"auto","created_at":"2025-12-02 13:43:27","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110796,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/1fd4f89f912e4a501f9f28a3.png"},{"id":97366677,"identity":"eb498ab4-a129-4c5e-a602-b64ae76ba897","added_by":"auto","created_at":"2025-12-03 15:57:23","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":272541,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/695f930e3d774bee4735847c.png"},{"id":97257996,"identity":"57ea8add-51b8-45b8-96e4-cd38b9e21804","added_by":"auto","created_at":"2025-12-02 13:43:27","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103605,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/b587a88c03beb2ba776a1800.png"},{"id":97367028,"identity":"b77c6625-900e-4879-82d1-756ffef6bde4","added_by":"auto","created_at":"2025-12-03 16:15:39","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124763,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/20e29fcb1c128bcd0ab50e8e.png"},{"id":97257988,"identity":"54866b67-7571-490b-a069-6751e9e596aa","added_by":"auto","created_at":"2025-12-02 13:43:27","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":123638,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/9831eec79ee47708b82cc58a.png"},{"id":97366921,"identity":"2389bc70-2a22-4889-afb1-ce8011b31afe","added_by":"auto","created_at":"2025-12-03 16:13:39","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":147976,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/d9129f69dd188476de85a38e.png"},{"id":97366856,"identity":"5f47332c-8937-4494-b60a-ed15c38ad701","added_by":"auto","created_at":"2025-12-03 16:10:15","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":125128,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/83a3ac96bcda994d3ded5d10.png"},{"id":97257993,"identity":"f1920183-5e7b-4e98-b76a-a9be37b10880","added_by":"auto","created_at":"2025-12-02 13:43:27","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142868,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/70fc90c1fa05321c3cda20a1.png"},{"id":97257989,"identity":"5e1400a1-3713-4c6e-8d80-b751a5ca32ca","added_by":"auto","created_at":"2025-12-02 13:43:27","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28417,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/513a521502483eba61fc6ca6.png"},{"id":97367550,"identity":"4531d69b-a3a6-4fd2-b6df-333187141657","added_by":"auto","created_at":"2025-12-03 16:19:20","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28592,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/42dde2d674a5d4b5e3902e21.png"},{"id":97366694,"identity":"d96c027e-8662-40ff-87da-e5e84802ff31","added_by":"auto","created_at":"2025-12-03 16:00:04","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30784,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/b2b033c765ffb1c83430dc10.png"},{"id":97367297,"identity":"e0f43c6e-29b9-4f0b-8e0f-b74fe37823ac","added_by":"auto","created_at":"2025-12-03 16:18:03","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28770,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/08b43e78f569fc5cc3df7c0a.png"},{"id":97366915,"identity":"7d26759e-cb8c-4f13-b509-e1a1286179ed","added_by":"auto","created_at":"2025-12-03 16:13:26","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":107400,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/99ce3d3c8b57168c015c50f5.png"},{"id":97258008,"identity":"8ec887a4-b0c6-4cef-a3b4-f7528b0afc7b","added_by":"auto","created_at":"2025-12-02 13:43:28","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29166,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/95307930323beeb5a1f50e52.png"},{"id":97366766,"identity":"3e8abe9d-378c-4503-982c-60153a36f94d","added_by":"auto","created_at":"2025-12-03 16:07:56","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":100812,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/3c51f88d705c8e416e8bc6d3.png"},{"id":97367870,"identity":"732fb744-528e-426f-8f68-4f8bf2e30707","added_by":"auto","created_at":"2025-12-03 16:20:56","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14156,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/782afaa85386d614e58d67c5.png"},{"id":97258009,"identity":"0ddbb8f5-16e9-4488-8fbb-d4df768c1233","added_by":"auto","created_at":"2025-12-02 13:43:28","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":119680,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/71fb2fb41173e626d5d24abd.png"},{"id":97366872,"identity":"ba4f6863-f0ef-4662-a2f1-9bfbc16d5baf","added_by":"auto","created_at":"2025-12-03 16:11:41","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18010,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/ba7ed1e95c752b8286388dea.png"},{"id":97258001,"identity":"c8d44802-7a1c-4843-9442-60a62e5d87d1","added_by":"auto","created_at":"2025-12-02 13:43:28","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":121723,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/13084b871e13656733008633.png"},{"id":97367566,"identity":"0dbf3965-c299-4b2b-8985-6f3b4a28fe85","added_by":"auto","created_at":"2025-12-03 16:19:30","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17708,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/96cfb6a41e2fb4e9243ecaa6.png"},{"id":97258006,"identity":"0f19c5b6-01bf-499a-bb67-73d134b27295","added_by":"auto","created_at":"2025-12-02 13:43:28","extension":"xml","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":154589,"visible":true,"origin":"","legend":"","description":"","filename":"07c210f3499f4d338107ffee52ec05cc1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/38d677a3c2c7d17d7cc56a89.xml"},{"id":97258004,"identity":"a020365b-bd36-4a1e-a12b-95633279b1d5","added_by":"auto","created_at":"2025-12-02 13:43:28","extension":"html","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":172267,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1/c44336b98dc5f749ec097111.html"},{"id":97372923,"identity":"8d0025f1-5a5f-4a7d-9f97-e635c53be7bb","added_by":"auto","created_at":"2025-12-03 16:33:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":830826,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8100727/v1_covered_2a7be056-9c9b-45fa-a6e3-73b429e8a53e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Zone-Aware Pneumonia Classification Using Automated Lung Region Detection and Multi-Branch Feature Learning","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":"international-journal-of-computational-intelligence-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [International Journal of Computational Intelligence Systems](https://link.springer.com/journal/44196)","snPcode":"44196","submissionUrl":"https://submission.springernature.com/new-submission/44196/3","title":"International Journal of Computational Intelligence Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Pneumonia Detection, Deep Learning, YOLOv8, Lobe Detection, Lung disease, Chain-of-Thought (CoT)","lastPublishedDoi":"10.21203/rs.3.rs-8100727/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8100727/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePneumonia is a major lung infection and remains one of the leading causes of death, especially among children under five and older adults. Early and accurate diagnosis often depends on chest X-rays, yet manual interpretation is challenging due to overlapping structures and low-contrast opacities. In this context, computer-based techniques have been proposed to assist radiologists in detecting pneumonia symptoms. Most existing techniques rely on deep learning models that extract features from the entire image to make classification decisions. While these approaches achieve high accuracy, they lack explainability, offering no clear information on where features are localized or how decisions are made. In this paper, we address two main limitations: (1) the localization of pneumonia-related features, and (2) the interpretability of deep features used for decision-making. This research presents a robust framework that integrates lung zone detection with multi-branch feature learning to classify pneumonia types and predict zone-specific findings. The proposed system consists of three phases. First, lung zone localization is performed to automatically focus on disease-relevant regions. Second, intra-zone CoT reasoning is introduced for zone-specific feature extraction, where lung zones detected by YOLOv8 are processed by ResNet-18 to capture local features. Third, attention-based inter-zone CoT fusion and classification is applied to predict pneumonia type and zone-level findings such as opacities and ground-glass patterns, aligning with radiology reporting standards. The proposed framework is evaluated on the Chest X-Ray Images (Pneumonia) dataset. It achieved an average accuracy of 94.4% and demonstrated notable improvements in detecting early-stage pneumonia. These results highlight the potential of the model as a decision-support tool for radiologists, enabling accurate diagnosis and standardized reporting in clinical practice.\u003c/p\u003e","manuscriptTitle":"Zone-Aware Pneumonia Classification Using Automated Lung Region Detection and Multi-Branch Feature Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-02 13:43:23","doi":"10.21203/rs.3.rs-8100727/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-28T02:48:35+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-27T19:58:25+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-23T11:47:17+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-21T16:48:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"310683378791165957178274277323348045823","date":"2025-12-20T22:50:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"217866727817106379614422929601744103537","date":"2025-12-16T19:14:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"130948013240590277658301236105956991242","date":"2025-12-13T05:13:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"154421836034828383267841256501038003739","date":"2025-12-11T10:29:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"29692049150455466737547713060676026427","date":"2025-12-11T06:49:37+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-01T03:05:19+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-21T08:16:43+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-20T06:55:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Computational Intelligence Systems","date":"2025-11-13T02:28:30+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-computational-intelligence-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [International Journal of Computational Intelligence Systems](https://link.springer.com/journal/44196)","snPcode":"44196","submissionUrl":"https://submission.springernature.com/new-submission/44196/3","title":"International Journal of Computational Intelligence Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d1924862-6c28-4249-b058-46fac7a3c0bf","owner":[],"postedDate":"December 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-02-02T11:57:25+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-02 13:43:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8100727","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8100727","identity":"rs-8100727","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