Deep Learning for Decision Support in Ovarian Cancer Treatment Planning

Deep Learning for Decision Support in Ovarian Cancer Treatment Planning | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Deep Learning for Decision Support in Ovarian Cancer Treatment Planning Francesca Fati, Marina Rosanu, Luigi De Vitis, Alberto Rota, Alice Traversa, and 13 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7434368/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Ovarian cancer is the deadliest gynecologic malignancy worldwide, with a 5-year overall survival rate of approximately 49%. Although complete resection is associated with the most favorable prognosis following primary debulking surgery, accurately assessing tumor resectability at diagnosis remains a major clinical challenge. We propose a decision support system (DSS) designed to predict residual tumor after primary debulking surgery, based on clinical and imaging data available at diagnosis. The system was developed and validated using a retrospective cohort of 465 patients with high-grade serous ovarian cancer, collected at the European Institute of Oncology in Milan, Italy. We developed a deep learning (DL) model that combines pre-trained Vision Transformer encoders with an attention mechanism and a classification head. When evaluated on an independent test cohort of 75 cases, our best-performing model achieved an area under the curve (AUC) of 0.80 (95% CI: 0.68–0.89) and a recall of 0.86 (95% CI: 0.71–0.97), demonstrating discriminatory ability with a particularly low rate of false negatives. Clinically, the model correctly identified 24 out of 28 patients (86%) with non-resectable disease, who would not have benefited from primary debulking surgery. Notably, within this subgroup, the model accurately predicted 93% (13 out of 14) of cases in which surgery was aborted intraoperatively due to unforeseen unresectable disease. These findings suggest that the model could have potential in preventing unnecessary and inappropriate surgical interventions. The proposed DSS is a fully automated, DL–based system for predicting tumor resectability at diagnosis, without the need for manual segmentation or expert evaluation of radiological features and structured clinical parameters. This approach could facilitate and accelerate personalized treatment planning in ovarian cancer. The work is part of the project Under-XAI: understanding ovarian cancer initiation and progression through explainable AI. Project code: PNRR-MAD-2022-12376574. Biological sciences/Cancer Health sciences/Medical research Health sciences/Oncology Ovarian Cancer Tumor Resecability Deep Learning Precision Medicine Vision Transformer Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 21 May, 2026 Reviewers agreed at journal 29 Apr, 2026 Reviews received at journal 04 Oct, 2025 Reviewers agreed at journal 19 Sep, 2025 Reviewers agreed at journal 11 Sep, 2025 Reviewers invited by journal 10 Sep, 2025 Editor assigned by journal 27 Aug, 2025 Submission checks completed at journal 27 Aug, 2025 First submitted to journal 22 Aug, 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-7434368","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":515579895,"identity":"f5704f0c-526a-4076-a25b-a3b2580e8e25","order_by":0,"name":"Francesca Fati","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9UlEQVRIiWNgGAWjYBAC9gY4k/EBA4OBDVCIsYEhgUECpxaeA3AmswHDAYM0IA3RglMPmhaGw0AawsWtRfrwswc/Kurk+RuYGT9/KDifx8/M3LrhAYNFHU4tfGnmhj1nDhvOOMDMLHHA4HaxZDNj2w18DrPnYTCTZmw7kMBwgP8ASEvihsMEtPDwsH+TZvxXlyAPtOXHAYNzxGjhAdrSwJxgcICZDWjLAaK0lEn2HDtsuPEwM5vFGYNkqF8MJCQbcDtsm8SPmjp5uePNzDcq/tjl8bO3P7sJDEN+XLYgADQ6EiCUAWENcJBAgtpRMApGwSgYIQAA3jRQNypuijQAAAAASUVORK5CYII=","orcid":"","institution":"European Institute of Oncology","correspondingAuthor":true,"prefix":"","firstName":"Francesca","middleName":"","lastName":"Fati","suffix":""},{"id":515579896,"identity":"2a955d85-5cf3-450b-8899-1c74d0244dcd","order_by":1,"name":"Marina Rosanu","email":"","orcid":"","institution":"European Institute of Oncology","correspondingAuthor":false,"prefix":"","firstName":"Marina","middleName":"","lastName":"Rosanu","suffix":""},{"id":515579897,"identity":"f053c69b-5309-46e7-94e3-f87897c40f2b","order_by":2,"name":"Luigi De Vitis","email":"","orcid":"","institution":"Mayo Clinic","correspondingAuthor":false,"prefix":"","firstName":"Luigi","middleName":"","lastName":"De Vitis","suffix":""},{"id":515579898,"identity":"a0cfd161-3bd4-4613-be66-693a038f13d8","order_by":3,"name":"Alberto Rota","email":"","orcid":"","institution":"Politecnico di Milano","correspondingAuthor":false,"prefix":"","firstName":"Alberto","middleName":"","lastName":"Rota","suffix":""},{"id":515579899,"identity":"2a796ca3-9af6-4e7b-8129-93039a825a24","order_by":4,"name":"Alice Traversa","email":"","orcid":"","institution":"European Institute of Oncology","correspondingAuthor":false,"prefix":"","firstName":"Alice","middleName":"","lastName":"Traversa","suffix":""},{"id":515579900,"identity":"282f722f-1273-4eb0-a891-1cc4f6686465","order_by":5,"name":"Lucia Ribero","email":"","orcid":"","institution":"European Institute of Oncology","correspondingAuthor":false,"prefix":"","firstName":"Lucia","middleName":"","lastName":"Ribero","suffix":""},{"id":515579902,"identity":"1bc00ceb-37a0-43c5-b0f9-acff7d612395","order_by":6,"name":"Gabriella Schivardi","email":"","orcid":"","institution":"European Institute of Oncology","correspondingAuthor":false,"prefix":"","firstName":"Gabriella","middleName":"","lastName":"Schivardi","suffix":""},{"id":515579903,"identity":"5ea9e0be-a59b-4aa0-8559-f46c504dab1f","order_by":7,"name":"Giuseppe Petralia","email":"","orcid":"","institution":"European Institute of Oncology","correspondingAuthor":false,"prefix":"","firstName":"Giuseppe","middleName":"","lastName":"Petralia","suffix":""},{"id":515579904,"identity":"7bea70e9-2aab-4ddd-9241-ba9a3138561d","order_by":8,"name":"Giovanni Damiano Aletti","email":"","orcid":"","institution":"European Institute of Oncology","correspondingAuthor":false,"prefix":"","firstName":"Giovanni","middleName":"Damiano","lastName":"Aletti","suffix":""},{"id":515579905,"identity":"013329cf-8595-49a1-b7fd-5412fae117e9","order_by":9,"name":"Nicoletta Colombo","email":"","orcid":"","institution":"European Institute of Oncology","correspondingAuthor":false,"prefix":"","firstName":"Nicoletta","middleName":"","lastName":"Colombo","suffix":""},{"id":515579906,"identity":"45b4686f-3753-4315-b09e-f0a5a41ce929","order_by":10,"name":"Michele Peiretti","email":"","orcid":"","institution":"Azienda Ospedaliero-Universitaria Cagliari","correspondingAuthor":false,"prefix":"","firstName":"Michele","middleName":"","lastName":"Peiretti","suffix":""},{"id":515579907,"identity":"5b6e1c97-3923-4b8a-8a40-835998ffd9ad","order_by":11,"name":"Stefano Angioni","email":"","orcid":"","institution":"Azienda Ospedaliero-Universitaria Cagliari","correspondingAuthor":false,"prefix":"","firstName":"Stefano","middleName":"","lastName":"Angioni","suffix":""},{"id":515579908,"identity":"d16703f6-9bf7-4adb-abab-56152ce667d1","order_by":12,"name":"Jvan Casarin","email":"","orcid":"","institution":"University of Insubria","correspondingAuthor":false,"prefix":"","firstName":"Jvan","middleName":"","lastName":"Casarin","suffix":""},{"id":515579909,"identity":"33d9c152-781e-40cd-8777-e802e66b3e0b","order_by":13,"name":"Roberto Veraldi","email":"","orcid":"","institution":"Magna Graecia University","correspondingAuthor":false,"prefix":"","firstName":"Roberto","middleName":"","lastName":"Veraldi","suffix":""},{"id":515579910,"identity":"2ac1686d-4304-4ca1-a55b-5abe0ebb0235","order_by":14,"name":"Paolo Zaffino","email":"","orcid":"","institution":"Magna Graecia University","correspondingAuthor":false,"prefix":"","firstName":"Paolo","middleName":"","lastName":"Zaffino","suffix":""},{"id":515579911,"identity":"ab73323a-39a4-4578-bddc-34940e8b47bd","order_by":15,"name":"Maria Francesca Spadea","email":"","orcid":"","institution":"Karlsruhe Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Maria","middleName":"Francesca","lastName":"Spadea","suffix":""},{"id":515579912,"identity":"a1210d03-7a13-477e-bb53-df6810b74ff1","order_by":16,"name":"Francesco Multinu","email":"","orcid":"","institution":"European Institute of Oncology","correspondingAuthor":false,"prefix":"","firstName":"Francesco","middleName":"","lastName":"Multinu","suffix":""},{"id":515579913,"identity":"5cdaf538-bcf3-4079-91fa-fef30041b887","order_by":17,"name":"Elena De Momi","email":"","orcid":"","institution":"European Institute of Oncology","correspondingAuthor":false,"prefix":"","firstName":"Elena","middleName":"","lastName":"De Momi","suffix":""}],"badges":[],"createdAt":"2025-08-22 12:08:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7434368/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7434368/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91484629,"identity":"a551da46-ae8e-4859-8595-ed9f68cf9891","added_by":"auto","created_at":"2025-09-17 04:29:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3212471,"visible":true,"origin":"","legend":"","description":"","filename":"Fati2025DeepLearningforDecisionSupportinOvarianCancerTreatmentPlanning.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7434368/v1_covered_d6d8205c-c8bb-4fe8-b720-38454e43d2ba.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep Learning for Decision Support in Ovarian Cancer Treatment Planning","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":"npj-womens-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [npj Women's Health](https://www.nature.com/npjwomenshealth/)","snPcode":"44294","submissionUrl":"https://submission.springernature.com/new-submission/44294/3","title":"npj Women's Health","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Ovarian Cancer, Tumor Resecability, Deep Learning, Precision Medicine, Vision Transformer","lastPublishedDoi":"10.21203/rs.3.rs-7434368/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7434368/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eOvarian cancer is the deadliest gynecologic malignancy worldwide, with a 5-year overall survival rate of approximately 49%. Although complete resection is associated with the most favorable prognosis following primary debulking surgery, accurately assessing tumor resectability at diagnosis remains a major clinical challenge. We propose a decision support system (DSS) designed to predict residual tumor after primary debulking surgery, based on clinical and imaging data available at diagnosis. The system was developed and validated using a retrospective cohort of 465 patients with high-grade serous ovarian cancer, collected at the European Institute of Oncology in Milan, Italy. We developed a deep learning (DL) model that combines pre-trained Vision Transformer encoders with an attention mechanism and a classification head. When evaluated on an independent test cohort of 75 cases, our best-performing model achieved an area under the curve (AUC) of 0.80 (95% CI: 0.68–0.89) and a recall of 0.86 (95% CI: 0.71–0.97), demonstrating discriminatory ability with a particularly low rate of false negatives. Clinically, the model correctly identified 24 out of 28 patients (86%) with non-resectable disease, who would not have benefited from primary debulking surgery. Notably, within this subgroup, the model accurately predicted 93% (13 out of 14) of cases in which surgery was aborted intraoperatively due to unforeseen unresectable disease. These findings suggest that the model could have potential in preventing unnecessary and inappropriate surgical interventions. The proposed DSS is a fully automated, DL–based system for predicting tumor resectability at diagnosis, without the need for manual segmentation or expert evaluation of radiological features and structured clinical parameters. This approach could facilitate and accelerate personalized treatment planning in ovarian cancer. \u0026nbsp;\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe work is part of the project Under-XAI: understanding ovarian cancer initiation and progression through explainable AI. Project code: PNRR-MAD-2022-12376574.\u003c/p\u003e","manuscriptTitle":"Deep Learning for Decision Support in Ovarian Cancer Treatment Planning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-17 04:21:33","doi":"10.21203/rs.3.rs-7434368/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-21T06:52:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"198776725978119672835797101129195423884","date":"2026-04-29T17:51:43+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-04T13:31:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"50840338759038490663780523215370060820","date":"2025-09-19T08:59:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"69122269266589888744342528912858005897","date":"2025-09-11T07:14:23+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-10T11:27:23+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-28T00:04:52+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-27T12:05:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Women's Health","date":"2025-08-22T12:00:00+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-womens-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [npj Women's Health](https://www.nature.com/npjwomenshealth/)","snPcode":"44294","submissionUrl":"https://submission.springernature.com/new-submission/44294/3","title":"npj Women's Health","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"aeee53d4-21ff-4e3f-b64e-73b996ffbcbf","owner":[],"postedDate":"September 17th, 2025","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-21T06:52:09+00:00","index":51,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":54768393,"name":"Biological sciences/Cancer"},{"id":54768394,"name":"Health sciences/Medical research"},{"id":54768395,"name":"Health sciences/Oncology"}],"tags":[],"updatedAt":"2025-09-17T04:21:33+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-17 04:21:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7434368","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7434368","identity":"rs-7434368","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}