QXRNet: A Hybrid CNN–QNN Model with Dynamic Feature Extraction and Variational Quantum Circuit

QXRNet: A Hybrid CNN–QNN Model with Dynamic Feature Extraction and Variational Quantum Circuit | 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 QXRNet: A Hybrid CNN–QNN Model with Dynamic Feature Extraction and Variational Quantum Circuit Neha Vinayak, Shandar Ahmad This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7779759/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Apr, 2026 Read the published version in Quantum Machine Intelligence → Version 1 posted 11 You are reading this latest preprint version Abstract Hybrid Quantum Neural Networks (QNNs) have emerged as a new direction in the domain of medical image analysis, especially for low dimension images with less expressive power. In this work, we propose QXRNet, a hybrid architecture that employs a dynamic feature extraction pipeline using pretrained CNNs integrated with the high expressive power of a quantum processor. Experiments with multiple image sizes from 16 px to 512 px show that QXRNet achieves AUC scores that are on par with or better than their classical counterparts, while saving on the trainable parameters by an order of magnitude. With this performance, a 6-qubit QNN block contributes only 18 parameters, highlighting the efficiency of the hybrid design. Between the various hybrid frameworks employed, we find that ResNet-QNN performs better at smaller image sizes, while EfficientNet-QNN works at higher dimensions. Motivated by this, QXRNet uses their complementary strengths by creating a dynamic feature extraction pipeline. Additional experiments suggest that \((R_y)\) encoding results in better performance with minimal circuit overhead, while qubit scaling identifies 6 qubits as the optimal balance between stability, performance, and complexity. The hybrid QXRNet architecture is trained using classical gradient descent by unifying the gradient propagation using the chain rule and integrating the quantum parameter shift rules. This work combines parameter-efficient hybrid design and systematic benchmarking and demonstrates the potential of QXRNet as a compact and scalable alternative in medical image analysis. Quantum Neural Network (QNN) Convolutional Neural Network (CNN) Medical Image Analysis Dynamic feature extractor Backpropagation Parameter Efficient Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 16 Apr, 2026 Read the published version in Quantum Machine Intelligence → Version 1 posted Editorial decision: Revision requested 07 Jan, 2026 Reviews received at journal 03 Dec, 2025 Reviews received at journal 21 Nov, 2025 Reviews received at journal 08 Nov, 2025 Reviewers agreed at journal 07 Nov, 2025 Reviewers agreed at journal 07 Nov, 2025 Reviewers agreed at journal 07 Nov, 2025 Reviewers invited by journal 07 Nov, 2025 Editor assigned by journal 07 Nov, 2025 Submission checks completed at journal 06 Oct, 2025 First submitted to journal 04 Oct, 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-7779759","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":546350961,"identity":"51efa68e-1b47-41f5-baf6-265c0ee93282","order_by":0,"name":"Neha Vinayak","email":"","orcid":"","institution":"Jawaharlal Nehru University","correspondingAuthor":false,"prefix":"","firstName":"Neha","middleName":"","lastName":"Vinayak","suffix":""},{"id":546350962,"identity":"3ba37940-13a1-48c5-ba02-ea59aaee3875","order_by":1,"name":"Shandar Ahmad","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxElEQVRIiWNgGAWjYDACCSDmYWCQY2yA8HmI1mJMupbEBqLdJT+7+dmDNzX30ptn9xgw/KhhkDEnpMXgzjFzwznHinMb55wxYOw5xsBjScg+A4kEM2ketoTcxhk5Bgy8DQw8BgcIOWxG+jdpnn8J6YxALYx/idHCcCPHTJq3LSEBpIWZKFsMbuSUSc7tSzBsnJFWcFjmmARRDtsm8eZbgrzhjOSND9/U2NgTdhgMGDYwMByARBOxQJ4EtaNgFIyCUTDCAABbRDsSTk0rlwAAAABJRU5ErkJggg==","orcid":"","institution":"Jawaharlal Nehru University","correspondingAuthor":true,"prefix":"","firstName":"Shandar","middleName":"","lastName":"Ahmad","suffix":""}],"badges":[],"createdAt":"2025-10-04 12:08:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7779759/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7779759/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s42484-026-00377-6","type":"published","date":"2026-04-16T15:57:24+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":96145220,"identity":"52e57f8d-15ec-47bc-8612-2f683414ad14","added_by":"auto","created_at":"2025-11-18 06:30:12","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4367,"visible":true,"origin":"","legend":"","description":"","filename":"bd79b33426ae4dd7a09fd648f786d3f4.json","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/2518aede69113c2ff7d080eb.json"},{"id":96145222,"identity":"2bf8e319-816d-407c-a69d-39fc61d2b2a4","added_by":"auto","created_at":"2025-11-18 06:30:12","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":102601,"visible":true,"origin":"","legend":"","description":"","filename":"bd79b33426ae4dd7a09fd648f786d3f41enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/34589725a7aa7ee876bbc077.xml"},{"id":96145226,"identity":"cb1f3f8d-f306-41d8-b695-e6b0a96eff57","added_by":"auto","created_at":"2025-11-18 06:30:12","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":462642,"visible":true,"origin":"","legend":"","description":"","filename":"QMICoverletter.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/d3f8883c052b9f247a01b32c.pdf"},{"id":96248754,"identity":"ca3bbb86-9974-4583-b389-d37e7008724f","added_by":"auto","created_at":"2025-11-19 07:29:08","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1352404,"visible":true,"origin":"","legend":"","description":"","filename":"QNNxrayNehaShandar.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/282b11f7070c4eaf7bad217b.pdf"},{"id":96249996,"identity":"9e721aa7-cf54-4da5-a511-029dc5786781","added_by":"auto","created_at":"2025-11-19 07:37:01","extension":"eps","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2890,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/4f9e101315b2050c062ae7cd.eps"},{"id":96145223,"identity":"eea66c33-d133-43e0-86a6-e8b47f005f15","added_by":"auto","created_at":"2025-11-18 06:30:12","extension":"eps","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91593,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/7996bc36cf3c5ce00360a83b.eps"},{"id":96145225,"identity":"464cc9ad-ef8b-4448-86bb-d17b7d96962e","added_by":"auto","created_at":"2025-11-18 06:30:12","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":174110,"visible":true,"origin":"","legend":"","description":"","filename":"fig1.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/e8e56b7f1703a71e82b1f791.png"},{"id":96145228,"identity":"0fbbb21b-d513-467f-9633-d808c644c5f3","added_by":"auto","created_at":"2025-11-18 06:30:12","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":173403,"visible":true,"origin":"","legend":"","description":"","filename":"fig2.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/314a7019de1c71e4a648a9e6.png"},{"id":96145233,"identity":"cc17b47f-6f94-404b-ab98-490c5e2fe24d","added_by":"auto","created_at":"2025-11-18 06:30:12","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32366,"visible":true,"origin":"","legend":"","description":"","filename":"fig3.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/93c42fbfcfde2a452b94aab3.png"},{"id":96250233,"identity":"8225632f-6ed7-4db2-be43-f1ad4da65bdf","added_by":"auto","created_at":"2025-11-19 07:37:46","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":137071,"visible":true,"origin":"","legend":"","description":"","filename":"fig41.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/ca486908aaa982cf64334f2a.png"},{"id":96145240,"identity":"9c86a393-ba0e-4c63-968e-18cffb1faa39","added_by":"auto","created_at":"2025-11-18 06:30:13","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":136906,"visible":true,"origin":"","legend":"","description":"","filename":"fig42.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/61f5aeefcb9f2d63fa8e4994.png"},{"id":96251292,"identity":"3ac8ac51-8e89-4601-a721-92e7c3f21025","added_by":"auto","created_at":"2025-11-19 07:39:36","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":155376,"visible":true,"origin":"","legend":"","description":"","filename":"fig43.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/b244d3df3c7b7b3b4d149dcc.png"},{"id":96145234,"identity":"4605eebf-185c-47ee-98a6-4512f3da110b","added_by":"auto","created_at":"2025-11-18 06:30:12","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93455,"visible":true,"origin":"","legend":"","description":"","filename":"fig51.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/4b3c179509ed8ab0e8c5db7f.png"},{"id":96145245,"identity":"7989a01a-5dfb-44c3-a320-6a27d82ddc2d","added_by":"auto","created_at":"2025-11-18 06:30:13","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":88218,"visible":true,"origin":"","legend":"","description":"","filename":"fig52.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/285162f6f52d4e8a2f9308ec.png"},{"id":96248385,"identity":"a3d1c6ff-ba33-4f06-9b19-6ba163c00dcd","added_by":"auto","created_at":"2025-11-19 07:28:24","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":138687,"visible":true,"origin":"","legend":"","description":"","filename":"fig6.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/72ff2514016a3e864c9b29f3.png"},{"id":96250126,"identity":"841d82ae-4a09-497d-a887-1876e3d0919d","added_by":"auto","created_at":"2025-11-19 07:37:34","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109310,"visible":true,"origin":"","legend":"","description":"","filename":"fig7.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/a63f2e9850247b5915e9657b.png"},{"id":96145250,"identity":"e3c0a2b4-8980-41c9-92a5-9a8e791ea37a","added_by":"auto","created_at":"2025-11-18 06:30:13","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/287f149cf582e246bea71d9c.bst"},{"id":96145244,"identity":"6a754c49-da58-4be0-a541-703d5e5328a5","added_by":"auto","created_at":"2025-11-18 06:30:13","extension":"bst","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/d8223143bf37343ee4414f3b.bst"},{"id":96250282,"identity":"7e37165f-7dc7-4bbc-be6f-f477627c8235","added_by":"auto","created_at":"2025-11-19 07:37:57","extension":"pdf","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":421391,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/2da79bf89bd523d6b61264ea.pdf"},{"id":96250095,"identity":"02ea054c-9e0f-480a-ac4a-73044c8ee2c1","added_by":"auto","created_at":"2025-11-19 07:37:26","extension":"bst","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/4a0a863b21d30612bee25b73.bst"},{"id":96145237,"identity":"2f9adf21-a478-466f-9da5-8fdd135819d2","added_by":"auto","created_at":"2025-11-18 06:30:13","extension":"bst","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/b00d3bc035736f000053a29b.bst"},{"id":96145236,"identity":"2e0793da-c6b4-4434-bcba-7c139e0cbb0f","added_by":"auto","created_at":"2025-11-18 06:30:12","extension":"cls","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/8d7a09f26334ea0cec1cdafb.cls"},{"id":96250107,"identity":"2b126e24-e089-4bac-bd84-e81384481fcb","added_by":"auto","created_at":"2025-11-19 07:37:28","extension":"bst","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/4e9d4a05ac28283634655c54.bst"},{"id":96250084,"identity":"876e8c81-6465-4553-8e8d-98a7613c8aef","added_by":"auto","created_at":"2025-11-19 07:37:25","extension":"bst","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/893188ac1bb74e6d1bf1007d.bst"},{"id":96250110,"identity":"7b89cd7a-29bd-4ad3-b55f-d483d8205efc","added_by":"auto","created_at":"2025-11-19 07:37:29","extension":"bst","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/82c91d61ba3d7ecbf3c5cd5b.bst"},{"id":96145243,"identity":"a54d3cdb-5c1a-4ac3-8168-6341d79a54df","added_by":"auto","created_at":"2025-11-18 06:30:13","extension":"bst","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/ab55b4b76783965a4d431901.bst"},{"id":96250008,"identity":"4e2bb854-a7a3-4019-94eb-5b1689f8b7ad","added_by":"auto","created_at":"2025-11-19 07:37:07","extension":"bst","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/757acf426450904c5b468f66.bst"},{"id":96145249,"identity":"334d8e14-71de-48b2-8c95-ce0361e4a091","added_by":"auto","created_at":"2025-11-18 06:30:13","extension":"pdf","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":418495,"visible":true,"origin":"","legend":"","description":"","filename":"usermanual.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/31d70f04fd5116288e0b3f6e.pdf"},{"id":96145238,"identity":"319085fa-9c72-410e-a318-d58023b001a8","added_by":"auto","created_at":"2025-11-18 06:30:13","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":120644,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefig42.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/2206694f25fd0cc0c227c939.png"},{"id":96145256,"identity":"9363d1c4-a383-4671-9fb7-35cd4f60e83b","added_by":"auto","created_at":"2025-11-18 06:30:13","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":138835,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefig43.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/908cd202962cf28beec9e3a8.png"},{"id":96145251,"identity":"96be6a57-b355-4c1e-b99b-93b2c76ab59e","added_by":"auto","created_at":"2025-11-18 06:30:13","extension":"png","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":75392,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefig52.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/ce4b7dd5768f26e6bb8f1874.png"},{"id":96145246,"identity":"473ca0b8-b372-4565-96df-dad3d28743ee","added_by":"auto","created_at":"2025-11-18 06:30:13","extension":"png","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":85231,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefig7.png","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/d9f6e6bc6573ca0f82922e4d.png"},{"id":96251349,"identity":"1370a28a-7345-4c2f-909f-79ac6c2ec807","added_by":"auto","created_at":"2025-11-19 07:39:39","extension":"xml","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":107851,"visible":true,"origin":"","legend":"","description":"","filename":"bd79b33426ae4dd7a09fd648f786d3f41structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/1f58d177effd937351531bd3.xml"},{"id":96251362,"identity":"ebd3d5e2-79e4-4b5f-ae40-0ef40550fffe","added_by":"auto","created_at":"2025-11-19 07:39:40","extension":"html","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":129368,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1/cdd2b5e817d43208700f88bf.html"},{"id":107350992,"identity":"efb38024-ed59-419c-8d02-274d2bf4d60e","added_by":"auto","created_at":"2026-04-20 16:07:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1201919,"visible":true,"origin":"","legend":"","description":"","filename":"QNNxrayNehaShandar.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7779759/v1_covered_ef3f39f9-d155-4af3-b2e4-2339f0b3f5dc.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"QXRNet: A Hybrid CNN–QNN Model with Dynamic Feature Extraction and Variational Quantum Circuit","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":"quantum-machine-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"qumi","sideBox":"Learn more about [Quantum Machine Intelligence](http://link.springer.com/journal/42484)","snPcode":"42484","submissionUrl":"https://submission.nature.com/new-submission/42484/3","title":"Quantum Machine Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Quantum Neural Network (QNN), Convolutional Neural Network (CNN), Medical Image Analysis, Dynamic feature extractor, Backpropagation, Parameter Efficient","lastPublishedDoi":"10.21203/rs.3.rs-7779759/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7779759/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHybrid Quantum Neural Networks (QNNs) have emerged as a new direction in the domain of medical image analysis, especially for low dimension images with less expressive power. In this work, we propose QXRNet, a hybrid architecture that employs a dynamic feature extraction pipeline using pretrained CNNs integrated with the high expressive power of a quantum processor. Experiments with multiple image sizes from 16 px to 512 px show that QXRNet achieves AUC scores that are on par with or better than their classical counterparts, while saving on the trainable parameters by an order of magnitude. With this performance, a 6-qubit QNN block contributes only 18 parameters, highlighting the efficiency of the hybrid design. Between the various hybrid frameworks employed, we find that ResNet-QNN performs better at smaller image sizes, while EfficientNet-QNN works at higher dimensions. Motivated by this, QXRNet uses their complementary strengths by creating a dynamic feature extraction pipeline. Additional experiments suggest that \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\((R_y)\\)\u003c/span\u003e\u003c/span\u003e encoding results in better performance with minimal circuit overhead, while qubit scaling identifies 6 qubits as the optimal balance between stability, performance, and complexity. The hybrid QXRNet architecture is trained using classical gradient descent by unifying the gradient propagation using the chain rule and integrating the quantum parameter shift rules. This work combines parameter-efficient hybrid design and systematic benchmarking and demonstrates the potential of QXRNet as a compact and scalable alternative in medical image analysis.\u003c/p\u003e","manuscriptTitle":"QXRNet: A Hybrid CNN–QNN Model with Dynamic Feature Extraction and Variational Quantum Circuit","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-18 06:30:07","doi":"10.21203/rs.3.rs-7779759/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-07T12:29:02+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-03T10:28:31+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-21T16:41:52+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-09T04:20:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"20849621020857259607635948268725693533","date":"2025-11-07T21:35:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"267497978212892132744729425612555899156","date":"2025-11-07T15:14:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"337359798318678103980607253454867606358","date":"2025-11-07T14:07:52+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-07T14:04:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-07T14:02:48+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-07T00:19:21+00:00","index":"","fulltext":""},{"type":"submitted","content":"Quantum Machine Intelligence","date":"2025-10-04T11:55:53+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"quantum-machine-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"qumi","sideBox":"Learn more about [Quantum Machine Intelligence](http://link.springer.com/journal/42484)","snPcode":"42484","submissionUrl":"https://submission.nature.com/new-submission/42484/3","title":"Quantum Machine Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"97c18b18-8a25-491d-82c6-fce44820aed5","owner":[],"postedDate":"November 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-04-20T16:05:06+00:00","versionOfRecord":{"articleIdentity":"rs-7779759","link":"https://doi.org/10.1007/s42484-026-00377-6","journal":{"identity":"quantum-machine-intelligence","isVorOnly":false,"title":"Quantum Machine Intelligence"},"publishedOn":"2026-04-16 15:57:24","publishedOnDateReadable":"April 16th, 2026"},"versionCreatedAt":"2025-11-18 06:30:07","video":"","vorDoi":"10.1007/s42484-026-00377-6","vorDoiUrl":"https://doi.org/10.1007/s42484-026-00377-6","workflowStages":[]},"version":"v1","identity":"rs-7779759","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7779759","identity":"rs-7779759","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}