TSNet:A Multi-modal Deep Learning Framework for Subtyping Appendicitis: Integrating Ultrasound Images, Handcrafted Features, and Clinical Data

TSNet:A Multi-modal Deep Learning Framework for Subtyping Appendicitis: Integrating Ultrasound Images, Handcrafted Features, and Clinical Data | 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 TSNet:A Multi-modal Deep Learning Framework for Subtyping Appendicitis: Integrating Ultrasound Images, Handcrafted Features, and Clinical Data Zhuanghe He, Rong Ma, Xinyi Huang, Liren Yang, Erqing Liao, Yang Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8526906/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Mar, 2026 Read the published version in Abdominal Radiology → Version 1 posted 15 You are reading this latest preprint version Abstract Purpose Preoperative differentiation of Acute Appendicitis (AA), Chronic Appendicitis (CA), and the clinically challenging Acute Exacerbation of Chronic Appendicitis (AEC) remains a significant diagnostic dilemma. We developed a multi-modal deep learning framework integrating ultrasound (US) images with domain-specific features to enhance diagnostic precision. Methods This retrospective study included 605 pathology-confirmed patients (392 AA, 150 CA, 63 AEC). The dataset comprised preoperative US images and a 19-dimensional feature vector encompassing clinical metrics and handcrafted sonographic markers guided by clinical protocols. We developed a multi-modal Two-Stream fusion framework ( TSNet ) utilizing a ResNet-50 backbone with Spatial Attention Modules (SAM) for visual extraction, fused with tabular data. Class imbalance was addressed using Focal Loss. Performance was evaluated via 5-fold stratified cross-validation. Results The optimal image-only model ( ResNet-SAM ) achieved an accuracy of 0.8612, whereas the best machine learning baseline ( RF-Sel ) attained 0.7570. The proposed TSNet achieved a robust patient-level accuracy of 0.8529. Notably, for the difficult-to-diagnose AEC subtype, TSNet achieved an AUC of 0.8031 and an F1-score of 0.4800. This represents a 17.1% improvement over the best machine learning baseline, confirming its superior capability in capturing acute-on-chronic pathology. Conclusion TSNet effectively differentiates appendicitis subtypes by leveraging the complementary strengths of deep visual representations and expert clinical knowledge. By significantly improving the identification of the elusive AEC subtype, the framework offers a robust tool for optimizing surgical decision-making and reducing the risk of mismanagement in complex clinical cases. Appendicitis Subtyping Deep Learning Multi-modal Fusion Ultrasound Chronic Appendicitis Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 03 Mar, 2026 Read the published version in Abdominal Radiology → Version 1 posted Editorial decision: Revision requested 27 Jan, 2026 Reviews received at journal 27 Jan, 2026 Reviews received at journal 23 Jan, 2026 Reviews received at journal 16 Jan, 2026 Reviewers agreed at journal 14 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 12 Jan, 2026 Reviewers agreed at journal 08 Jan, 2026 Reviewers agreed at journal 08 Jan, 2026 Reviewers agreed at journal 08 Jan, 2026 Reviewers agreed at journal 08 Jan, 2026 Reviewers invited by journal 08 Jan, 2026 Editor assigned by journal 07 Jan, 2026 Submission checks completed at journal 07 Jan, 2026 First submitted to journal 06 Jan, 2026 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-8526906","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":571478832,"identity":"9d1069f6-9e3c-47e7-ab8d-ba3b6fd5a52b","order_by":0,"name":"Zhuanghe He","email":"","orcid":"","institution":"Department of Medical Ultrasound, West China Hospital, Sichuan University, Chengdu, 610041, China","correspondingAuthor":false,"prefix":"","firstName":"Zhuanghe","middleName":"","lastName":"He","suffix":""},{"id":571478834,"identity":"e1f39f5a-c802-4ec3-9a00-520ca34fee44","order_by":1,"name":"Rong Ma","email":"","orcid":"","institution":"Department of Medical Ultrasound, West China Hospital, Sichuan University, Chengdu, 610041, China","correspondingAuthor":false,"prefix":"","firstName":"Rong","middleName":"","lastName":"Ma","suffix":""},{"id":571478836,"identity":"2be429c7-ecbb-4bbe-bf1f-6a22b448884f","order_by":2,"name":"Xinyi Huang","email":"","orcid":"","institution":"Department of Medical Ultrasound, West China Hospital, Sichuan University, Chengdu, 610041, China","correspondingAuthor":false,"prefix":"","firstName":"Xinyi","middleName":"","lastName":"Huang","suffix":""},{"id":571478837,"identity":"a2601d38-c368-4588-93c0-443f02d4116f","order_by":3,"name":"Liren Yang","email":"","orcid":"","institution":"Department of West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, 610041, China.","correspondingAuthor":false,"prefix":"","firstName":"Liren","middleName":"","lastName":"Yang","suffix":""},{"id":571478840,"identity":"fad4ba0a-a381-4a15-b347-3a827b5db550","order_by":4,"name":"Erqing Liao","email":"","orcid":"","institution":"Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China.","correspondingAuthor":false,"prefix":"","firstName":"Erqing","middleName":"","lastName":"Liao","suffix":""},{"id":571478842,"identity":"a8830edf-72dc-400a-a73b-0c5f593120e4","order_by":5,"name":"Yang Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIie3RMQuCQBTA8RfCuQiuJ4R+hQPBz3O32FLQ6OCgEDqktPYx3KpNCG66nB2vvcXNqbpoDPTGhvttN/y59+4ADOMPBRkgoACOax8GSZN0PiHtN/G9qg2JFFwjAZUoITnSyLvvLI3ErrmUCbAGaJywDIFb7un0LlW3IlQAO0HLe3ZeAha3Zvqafh1hVrzYJc+LngkEBG90kqca7GqhLSss3SRT63OEQCshoosx5Z9HdixMBXdmdwnKmntjqr4yeCyGMUl9t6xnBgNn8qiTGIZhGD/e+ghJ9+intPQAAAAASUVORK5CYII=","orcid":"","institution":"Department of Medical Ultrasound, West China Hospital, Sichuan University, Chengdu, 610041, China","correspondingAuthor":true,"prefix":"","firstName":"Yang","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2026-01-06 05:38:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8526906/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8526906/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00261-026-05446-9","type":"published","date":"2026-03-03T15:58:35+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100011561,"identity":"67cedc1c-d518-47a1-ad6c-72a98a7d461e","added_by":"auto","created_at":"2026-01-12 06:10:40","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":360219,"visible":true,"origin":"","legend":"","description":"","filename":"blank6.docx","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/51b1d7a502a4bc341abd3f5b.docx"},{"id":100011559,"identity":"39e0aec8-551c-4fac-aa19-c56389616417","added_by":"auto","created_at":"2026-01-12 06:10:40","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7957,"visible":true,"origin":"","legend":"","description":"","filename":"e79ad47b6f79476483bc0f0cfbf0e743.json","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/f0c7db1e0bd57bef0df6c684.json"},{"id":100011541,"identity":"b351cdb0-9ecf-480e-a2e7-dc37e7607aa8","added_by":"auto","created_at":"2026-01-12 06:10:37","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":131859,"visible":true,"origin":"","legend":"","description":"","filename":"e79ad47b6f79476483bc0f0cfbf0e7431enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/67d96420bf4cf58557ee6721.xml"},{"id":100011553,"identity":"57f47aa2-4977-4164-bdad-d34f0c4215fd","added_by":"auto","created_at":"2026-01-12 06:10:39","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":113102,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/db4c6128a4e340a08e4ffa26.jpeg"},{"id":100011557,"identity":"b23b5a0f-4c81-4aa5-80d1-097fcd04950b","added_by":"auto","created_at":"2026-01-12 06:10:40","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":143746,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/aefeee2f496fb5310f211aaf.jpeg"},{"id":100011560,"identity":"02b00e97-1162-470c-bfe7-236510fb2805","added_by":"auto","created_at":"2026-01-12 06:10:40","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":90318,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/5847dc8b50bb65a103113f00.jpeg"},{"id":100011542,"identity":"646d9284-60c3-4a72-9d14-f1a977fa91b3","added_by":"auto","created_at":"2026-01-12 06:10:37","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67941,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/258181c3e7d5fc1a30ea55e3.jpeg"},{"id":100011550,"identity":"a405ac02-4a94-443a-9ea7-71c1a159dc74","added_by":"auto","created_at":"2026-01-12 06:10:39","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56614,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/057fb5b59a0ddda376d58032.png"},{"id":100362073,"identity":"9eb4a006-718e-458c-9630-8691be18a0ed","added_by":"auto","created_at":"2026-01-16 07:46:10","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":63467,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/59dee1e6618a5602fe097e0f.png"},{"id":100011545,"identity":"c20600c3-c479-45d7-9fe3-57676ab684e4","added_by":"auto","created_at":"2026-01-12 06:10:38","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29717,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/b35e5f081f4b16cccd5574f3.png"},{"id":100011544,"identity":"49d5db7a-0776-465c-a5e0-b8f5eac9c3c4","added_by":"auto","created_at":"2026-01-12 06:10:38","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25468,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/614f48903543138aa454aa28.png"},{"id":100011543,"identity":"d9a74fee-7d8b-424e-a9c2-d003a1bdb2fb","added_by":"auto","created_at":"2026-01-12 06:10:37","extension":"xml","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":126203,"visible":true,"origin":"","legend":"","description":"","filename":"e79ad47b6f79476483bc0f0cfbf0e7431structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/f5c2741494f8a5ed9e4f0f4a.xml"},{"id":100011549,"identity":"e8930e00-0c49-4708-8008-e4d2948411ed","added_by":"auto","created_at":"2026-01-12 06:10:39","extension":"html","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":145958,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1/7a8358377f0c8ba33923e68d.html"},{"id":104251877,"identity":"0be65c19-0ea6-43ed-bb20-b9d31887b2c5","added_by":"auto","created_at":"2026-03-09 16:15:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":781041,"visible":true,"origin":"","legend":"","description":"","filename":"blank6.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8526906/v1_covered_d7b97fdd-ff30-4c7a-988d-47de8d5905ec.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"TSNet:A Multi-modal Deep Learning Framework for Subtyping Appendicitis: Integrating Ultrasound Images, Handcrafted Features, and Clinical Data","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":"abdominal-radiology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aima","sideBox":"Learn more about [Abdominal Radiology](http://link.springer.com/journal/261)","snPcode":"261","submissionUrl":"https://submission.springernature.com/new-submission/261/3","title":"Abdominal Radiology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Appendicitis Subtyping, Deep Learning, Multi-modal Fusion, Ultrasound, Chronic Appendicitis","lastPublishedDoi":"10.21203/rs.3.rs-8526906/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8526906/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003ePurpose\u003c/h2\u003e \u003cp\u003ePreoperative differentiation of Acute Appendicitis (AA), Chronic Appendicitis (CA), and the clinically challenging Acute Exacerbation of Chronic Appendicitis (AEC) remains a significant diagnostic dilemma. We developed a multi-modal deep learning framework integrating ultrasound (US) images with domain-specific features to enhance diagnostic precision.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThis retrospective study included 605 pathology-confirmed patients (392 AA, 150 CA, 63 AEC). The dataset comprised preoperative US images and a \u003cb\u003e19-dimensional\u003c/b\u003e feature vector encompassing clinical metrics and handcrafted sonographic markers guided by clinical protocols. We developed a multi-modal Two-Stream fusion framework (\u003cb\u003eTSNet\u003c/b\u003e) utilizing a ResNet-50 backbone with Spatial Attention Modules (SAM) for visual extraction, fused with tabular data. Class imbalance was addressed using Focal Loss. Performance was evaluated via 5-fold stratified cross-validation.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe optimal image-only model (\u003cb\u003eResNet-SAM\u003c/b\u003e) achieved an accuracy of 0.8612, whereas the best machine learning baseline (\u003cb\u003eRF-Sel\u003c/b\u003e) attained 0.7570. The proposed TSNet achieved a robust patient-level accuracy of 0.8529. Notably, for the difficult-to-diagnose AEC subtype, TSNet achieved an AUC of 0.8031 and an F1-score of 0.4800. This represents a \u003cb\u003e17.1% improvement\u003c/b\u003e over the best machine learning baseline, confirming its superior capability in capturing acute-on-chronic pathology.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eTSNet effectively differentiates appendicitis subtypes by leveraging the complementary strengths of deep visual representations and expert clinical knowledge. By significantly improving the identification of the elusive AEC subtype, the framework offers a robust tool for optimizing surgical decision-making and reducing the risk of mismanagement in complex clinical cases.\u003c/p\u003e","manuscriptTitle":"TSNet:A Multi-modal Deep Learning Framework for Subtyping Appendicitis: Integrating Ultrasound Images, Handcrafted Features, and Clinical Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-12 06:10:26","doi":"10.21203/rs.3.rs-8526906/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-27T14:59:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-27T11:24:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-23T07:49:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-16T05:54:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"329712096143203166046544910681808688695","date":"2026-01-14T15:38:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"152473930880511140706823245389208148674","date":"2026-01-13T11:00:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"288801809131941852316188815870360629713","date":"2026-01-12T06:19:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"232309210707116023637890615009825973046","date":"2026-01-08T11:21:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"153450313630069483273520847483229426684","date":"2026-01-08T11:10:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"65435204342894169802986425337475128335","date":"2026-01-08T11:07:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"293574218175111649052750926292083540162","date":"2026-01-08T11:03:46+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-08T10:43:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-07T13:50:09+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-07T10:19:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"Abdominal Radiology","date":"2026-01-06T05:23:04+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"abdominal-radiology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aima","sideBox":"Learn more about [Abdominal Radiology](http://link.springer.com/journal/261)","snPcode":"261","submissionUrl":"https://submission.springernature.com/new-submission/261/3","title":"Abdominal Radiology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f6680fa8-3b26-44e0-86e7-41220caef59e","owner":[],"postedDate":"January 12th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-03-09T16:10:52+00:00","versionOfRecord":{"articleIdentity":"rs-8526906","link":"https://doi.org/10.1007/s00261-026-05446-9","journal":{"identity":"abdominal-radiology","isVorOnly":false,"title":"Abdominal Radiology"},"publishedOn":"2026-03-03 15:58:35","publishedOnDateReadable":"March 3rd, 2026"},"versionCreatedAt":"2026-01-12 06:10:26","video":"","vorDoi":"10.1007/s00261-026-05446-9","vorDoiUrl":"https://doi.org/10.1007/s00261-026-05446-9","workflowStages":[]},"version":"v1","identity":"rs-8526906","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8526906","identity":"rs-8526906","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}