Harnessing the Power of Multiple-Instance Learning for Conversion Therapy Outcome Prediction from Pretreatment CT images of Patients with Gastric Cancer

Harnessing the Power of Multiple-Instance Learning for Conversion Therapy Outcome Prediction from Pretreatment CT images of Patients with Gastric Cancer | 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 Harnessing the Power of Multiple-Instance Learning for Conversion Therapy Outcome Prediction from Pretreatment CT images of Patients with Gastric Cancer Wenzhuo Deng, Saiyi Han, Tong Zhang, Shaoliang Han, Beier Jiang, and 7 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6343089/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Background: Gastric cancer is a leading cause of cancer-related death worldwide. Conversion therapy for gastric cancer is a treatment strategy that aims to convert unresectable gastric cancer into resectable ones. Early noninvasive evaluation of patients who would benefit from conversion therapy remains a challenge but is essential for personalized treatment in the setting of locally advanced gastric cancer (LAGC). In this study, we aim to develop a reliable deep learning prediction model based on CT images for conversion therapy outcome in patients with LAGC. Methods: Data from LAGC patients, who had CT scans within two weeks prior to conversion therapy, were retrospectively analyzed. We propose a novel approach to predict the conversion therapy outcome using multiple-instance learning (MIL), which is a deep learning framework that can handle data with ambiguous labels, where only bag level labels are given but labels of instances within the bag are unknown. We first used contrastive learning to train a feature extractor, which was then used to extract features from each image. The extracted features were used to train the MIL model that can predict scan-level outcome. We evaluated the performance of the model on a dataset of 124 patients, and compare it with several baseline methods. Results: All 124 patients were recruited from one Chinese hospital between September 2017 and September 2023. The training cohort (TC, n=99) and validation cohort (VC, n=25) were randomly selected, with the data in VC remaining balanced. Performance metrics included accuracy (ACC), area under the curve (AUC), sensitivity and specificity. The results shown that our method achieves higher ACC, AUC and a better balance between sensitivity and specificity than the baseline methods, with an accuracy of 0.88 and an AUC of 0.92 on VC. We also analyzed the features learned by our model using several visualization approaches to verify efficacy. Conclusion: Our method may provide a new perspective and a useful tool for predicting the conversion therapy outcome of LAGC patients using CT images. Moreover, we believe that our method can be applied to various medical image analysis scenarios due to case-based characteristics and common absence of image-level labels. Deep learning Multiple instance learning Gastric cancer Conversion therapy Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 05 May, 2025 Editor invited by journal 09 Apr, 2025 Editor assigned by journal 08 Apr, 2025 Submission checks completed at journal 08 Apr, 2025 First submitted to journal 31 Mar, 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-6343089","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":452603246,"identity":"2eca51bb-cb95-40dd-98b9-24468387672a","order_by":0,"name":"Wenzhuo Deng","email":"","orcid":"","institution":"Quzhou People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Wenzhuo","middleName":"","lastName":"Deng","suffix":""},{"id":452603247,"identity":"9238f9de-1091-4b56-9e71-3076b098f9cf","order_by":1,"name":"Saiyi Han","email":"","orcid":"","institution":"Quzhou People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Saiyi","middleName":"","lastName":"Han","suffix":""},{"id":452603248,"identity":"5e23e60a-17f5-44cd-bcfd-0c98e5fed588","order_by":2,"name":"Tong Zhang","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Tong","middleName":"","lastName":"Zhang","suffix":""},{"id":452603249,"identity":"75fdfcc7-9cdd-41c8-992c-243f61fc8625","order_by":3,"name":"Shaoliang Han","email":"","orcid":"","institution":"First Affiliated Hospital of Wenzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Shaoliang","middleName":"","lastName":"Han","suffix":""},{"id":452603250,"identity":"c96d102c-688d-4321-91e3-14f22ad86906","order_by":4,"name":"Beier Jiang","email":"","orcid":"","institution":"Quzhou People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Beier","middleName":"","lastName":"Jiang","suffix":""},{"id":452603251,"identity":"0ae261af-e714-434c-b831-7cc67fd5f173","order_by":5,"name":"Honghao Wu","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Honghao","middleName":"","lastName":"Wu","suffix":""},{"id":452603252,"identity":"0e3e493a-8316-4417-98d3-f65626ae351b","order_by":6,"name":"Weidong Xie","email":"","orcid":"","institution":"First Affiliated Hospital of Wenzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Weidong","middleName":"","lastName":"Xie","suffix":""},{"id":452603253,"identity":"4bf0cadd-3464-4c67-a344-19effaae6cd1","order_by":7,"name":"Yide Chen","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Yide","middleName":"","lastName":"Chen","suffix":""},{"id":452603254,"identity":"0b26bb89-cefd-4d35-86e5-6273c307a8aa","order_by":8,"name":"Tao Deng","email":"","orcid":"","institution":"First Affiliated Hospital of Wenzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Deng","suffix":""},{"id":452603255,"identity":"dcb2a3df-6ba4-48b4-b3d1-1a4f88ea903a","order_by":9,"name":"Xuewen Wen","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Xuewen","middleName":"","lastName":"Wen","suffix":""},{"id":452603256,"identity":"fd3e49b1-232b-41f1-899d-56dcfc1a5d60","order_by":10,"name":"Jianping Fan","email":"","orcid":"","institution":"Quzhou People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jianping","middleName":"","lastName":"Fan","suffix":""},{"id":452603257,"identity":"0569bfe1-e000-4c4d-a3ae-367188371b3b","order_by":11,"name":"Jiajun Xian","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIiWNgGAWjYDACZiCWMABRzAcffABy2NiJ18KWbDgDpIWZePt4zKR5YIbgAwbHmZ89sCiwYze43WAgbfNrmzwfMwPjh485uLVINrOZG0gYJDMb3DmQYJzbd9uwjZmBWXLmNtxa+JkZzCQkDJiZDW4kHEjO7bnNCNTCxsyLRwsbM/s3oJZ6oJbEhsOWPbftCWrhZ+YB2XIYqCWZsZnhx+1Eglokm3nKgFqOM0veSGNm7G24ndzGzNiM1y8G549vk5b4U53MdyP/+48ff27bzm9vPvjhIx4tIMAswcCQDGYxtoHJBvzqQUqA6cQOwvxDUPEoGAWjYBSMQAAAYs5H7qfjd98AAAAASUVORK5CYII=","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":true,"prefix":"","firstName":"Jiajun","middleName":"","lastName":"Xian","suffix":""}],"badges":[],"createdAt":"2025-03-31 08:43:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6343089/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6343089/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":82227481,"identity":"1679d2f6-2ce6-4373-9412-005e039f662d","added_by":"auto","created_at":"2025-05-08 05:04:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2149726,"visible":true,"origin":"","legend":"","description":"","filename":"BMCpaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6343089/v1_covered_cad23d54-b9ae-44e1-a6b8-d498ad8c6dd9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Harnessing the Power of Multiple-Instance Learning for Conversion Therapy Outcome Prediction from Pretreatment CT images of Patients with Gastric Cancer","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Deep learning, Multiple instance learning, Gastric cancer, Conversion therapy","lastPublishedDoi":"10.21203/rs.3.rs-6343089/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6343089/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBackground: Gastric cancer is a leading cause of cancer-related death worldwide. Conversion therapy for gastric cancer is a treatment strategy that aims to convert unresectable gastric cancer into resectable ones. Early noninvasive evaluation of patients who would benefit from conversion therapy remains a challenge but is essential for personalized treatment in the setting of locally advanced gastric cancer (LAGC). In this study, we aim to develop a reliable deep learning prediction model based on CT images for conversion therapy outcome in patients with LAGC.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eMethods: Data from LAGC patients, who had CT scans within two weeks prior to conversion therapy, were retrospectively analyzed. We propose a novel approach to predict the conversion therapy outcome using multiple-instance learning (MIL), which is a deep learning framework that can handle data with ambiguous labels, where only bag level labels are given but labels of instances within the bag are unknown. We first used contrastive learning to train a feature extractor, which was then used to extract features from each image. The extracted features were used to train the MIL model that can predict scan-level outcome. We evaluated the performance of the model on a dataset of 124 patients, and compare it with several baseline methods.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eResults: All 124 patients were recruited from one Chinese hospital between September 2017 and September 2023. The training cohort (TC, n=99) and validation cohort (VC, n=25) were randomly selected, with the data in VC remaining balanced. Performance metrics included accuracy (ACC), area under the curve (AUC), sensitivity and specificity. The results shown that our method achieves higher ACC, AUC and a better balance between sensitivity and specificity than the baseline methods, with an accuracy of 0.88 and an AUC of 0.92 on VC. We also analyzed the features learned by our model using several visualization approaches to verify efficacy.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConclusion: Our method may provide a new perspective and a useful tool for predicting the conversion therapy outcome of LAGC patients using CT images. Moreover, we believe that our method can be applied to various medical image analysis scenarios due to case-based characteristics and common absence of image-level labels.\u003c/p\u003e","manuscriptTitle":"Harnessing the Power of Multiple-Instance Learning for Conversion Therapy Outcome Prediction from Pretreatment CT images of Patients with Gastric Cancer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-08 04:56:39","doi":"10.21203/rs.3.rs-6343089/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2025-05-06T02:03:10+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-04-09T04:24:33+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-04-08T13:56:30+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-08T13:55:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Imaging","date":"2025-03-31T08:22:07+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"17a8dd9a-1825-4124-9eaf-839db893b945","owner":[],"postedDate":"May 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-05-08T04:56:39+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-08 04:56:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6343089","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6343089","identity":"rs-6343089","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}