Fourier PD and PDUNet: Complex-valued networks to speed-up MR Thermometry during Hyperthermia

Fourier PD and PDUNet: Complex-valued networks to speed-up MR Thermometry during Hyperthermia | 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 Fourier PD and PDUNet: Complex-valued networks to speed-up MR Thermometry during Hyperthermia Rupali Khatun, Soumick Chatterjee, Christoph Bert, Martin Wadepohl, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4491570/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 06 Apr, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Hyperthermia (HT) in combination with radio-and/or chemotherapy has become an accepted cancer treatment for distinct solid tumour entities. In HT, tumour tissue is exogenously heated to temperatures of 39 to 43 °C for 60 minutes. Temperature monitoring can be performed noninvasively using dynamic magnetic resonance imaging (MRI). However, the slow nature of MRI leads to motion artefacts in the images due to the movements of patients during image acquisition time. By discarding parts of the data, the speed of the acquisition can be increased-known as Undersampling. However, due to the invalidation of the Nyquist criterion, the acquired images have lower resolution and can also produce artefacts. The aim of this work was, therefore, to reconstruct highly undersampled MR thermometry acquisitions with better resolution and with less artefacts compared to conventional techniques like compressed sensing. The use of deep learning in the medical field has emerged in recent times, and various studies have shown that deep learning has the potential to solve inverse problems such as MR image reconstruction. However, most of the published work only focusses on the magnitude images, while the phase images are ignored, which are fundamental requirements for MR thermometry. This work, for the first time ever, presents deep learning based solutions for reconstructing undersampled MR thermometry data. Two different deep learning models have been employed here, the Fourier Primal-Dual network and Fourier Primal-Dual UNet, to reconstruct highly undersampled complex images of MR thermometry. MR images of 44 patients with different sarcoma cancers who have received the HT treatment in a combination of radiotherapy/chemotherapy were used in this study. It was observed that the method was able to reduce the temperature difference between the undersampled MRIs and the fully sampled MRIs from 1.5 °C to 0.5°C. Health sciences/Health care/Medical imaging/Magnetic resonance imaging Physical sciences/Mathematics and computing/Computer science Physical sciences/Physics/Applied physics Physical sciences/Engineering/Biomedical engineering Hyperthermia MRI MR Image Reconstruction Deep Learning Undersampled MRI Undersampled MR Reconstruction Complex Image MR Thermometry Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 06 Apr, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 04 Jul, 2024 Reviews received at journal 24 Jun, 2024 Reviews received at journal 16 Jun, 2024 Reviewers agreed at journal 13 Jun, 2024 Reviewers agreed at journal 07 Jun, 2024 Reviewers invited by journal 07 Jun, 2024 Editor assigned by journal 29 May, 2024 Editor invited by journal 29 May, 2024 Submission checks completed at journal 29 May, 2024 First submitted to journal 28 May, 2024 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-4491570","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":312782830,"identity":"9a12abd5-6f7c-4ff2-9c36-f4c3748a986d","order_by":0,"name":"Rupali Khatun","email":"","orcid":"","institution":"Universitätsklinikum Erlangen, Friedrich-Alexnder-Universität Erlangen-Nürnberg Erlangen","correspondingAuthor":false,"prefix":"","firstName":"Rupali","middleName":"","lastName":"Khatun","suffix":""},{"id":312782831,"identity":"82f71c1d-29ee-4584-b9ac-3c59792e187e","order_by":1,"name":"Soumick Chatterjee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuklEQVRIiWNgGAWjYBADOTCZAITEAMYGBgYDY9K1JDYwQDURBPztvccf/Kj5kz6/vcd0w4OaNKBIN359EmfOJTb2HDPI3XDmjNmNhGM5QJGzG/BqMZDIMWzgbQBqkcgxu5HYUAEUySWspfFvg0G6/AxStDQDbUlguAHWkkNYi8SZM4azZY4ZG244c6wM6Jc0HoJ+4W/vMfj4pkZOXr69edvNHzXJcsAwxK8FA/CQpnwUjIJRMApGAVYAAEfbSPxCDuc9AAAAAElFTkSuQmCC","orcid":"","institution":"Human Technopole","correspondingAuthor":true,"prefix":"","firstName":"Soumick","middleName":"","lastName":"Chatterjee","suffix":""},{"id":312782832,"identity":"574134d4-6840-48b6-afd0-738a7e72e891","order_by":2,"name":"Christoph Bert","email":"","orcid":"","institution":"Universitätsklinikum Erlangen, Friedrich-Alexnder-Universität Erlangen-Nürnberg Erlangen","correspondingAuthor":false,"prefix":"","firstName":"Christoph","middleName":"","lastName":"Bert","suffix":""},{"id":312782833,"identity":"fe05bfef-9f94-486d-8bd4-956e9a593ca6","order_by":3,"name":"Martin Wadepohl","email":"","orcid":"","institution":"Dr Sennewald Medizintechnik GmbH","correspondingAuthor":false,"prefix":"","firstName":"Martin","middleName":"","lastName":"Wadepohl","suffix":""},{"id":312782834,"identity":"2061ae37-1340-4c30-be7e-54dbb5d78297","order_by":4,"name":"Oliver J. Ott","email":"","orcid":"","institution":"Universitätsklinikum Erlangen, Friedrich-Alexnder-Universität Erlangen-Nürnberg Erlangen","correspondingAuthor":false,"prefix":"","firstName":"Oliver","middleName":"J.","lastName":"Ott","suffix":""},{"id":312782835,"identity":"528bf699-3224-450f-987e-cf2e3b23afd0","order_by":5,"name":"Sabine Semrau","email":"","orcid":"","institution":"Universitätsklinikum Erlangen, Friedrich-Alexnder-Universität Erlangen-Nürnberg Erlangen","correspondingAuthor":false,"prefix":"","firstName":"Sabine","middleName":"","lastName":"Semrau","suffix":""},{"id":312782836,"identity":"824ee400-7f8d-45e7-9fa7-cc86ee1911ff","order_by":6,"name":"Rainer Fietkau","email":"","orcid":"","institution":"Universitätsklinikum Erlangen, Friedrich-Alexnder-Universität Erlangen-Nürnberg Erlangen","correspondingAuthor":false,"prefix":"","firstName":"Rainer","middleName":"","lastName":"Fietkau","suffix":""},{"id":312782837,"identity":"14c01c14-e9a4-4c4b-9ebb-75488e6eabcc","order_by":7,"name":"Andreas Nürnberger","email":"","orcid":"","institution":"Otto von Guericke University Magdeburg","correspondingAuthor":false,"prefix":"","firstName":"Andreas","middleName":"","lastName":"Nürnberger","suffix":""},{"id":312782838,"identity":"26d718f4-9f75-4566-8054-d85f30d27153","order_by":8,"name":"Udo S. Gaipl","email":"","orcid":"","institution":"Universitätsklinikum Erlangen, Friedrich-Alexnder-Universität Erlangen-Nürnberg","correspondingAuthor":false,"prefix":"","firstName":"Udo","middleName":"S.","lastName":"Gaipl","suffix":""},{"id":312782839,"identity":"6d7cfa13-2d03-4037-a497-9023da0d7487","order_by":9,"name":"Benjamin Frey","email":"","orcid":"","institution":"Universitätsklinikum Erlangen, Friedrich-Alexnder-Universität Erlangen-Nürnberg","correspondingAuthor":false,"prefix":"","firstName":"Benjamin","middleName":"","lastName":"Frey","suffix":""}],"badges":[],"createdAt":"2024-05-28 14:21:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4491570/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4491570/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-96071-x","type":"published","date":"2025-04-06T15:57:40+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":80082248,"identity":"1d43e0ed-89a6-4ce4-988f-57fd88f5b803","added_by":"auto","created_at":"2025-04-07 16:07:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1171257,"visible":true,"origin":"","legend":"","description":"","filename":"ThermoRecon.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4491570/v1_covered_6f380b15-ea9b-49fc-8a14-4e54505c9da2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Fourier PD and PDUNet: Complex-valued networks to speed-up MR Thermometry during Hyperthermia","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Hyperthermia, MRI, MR Image Reconstruction, Deep Learning, Undersampled MRI, Undersampled, MR Reconstruction, Complex Image, MR Thermometry","lastPublishedDoi":"10.21203/rs.3.rs-4491570/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4491570/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Hyperthermia (HT) in combination with radio-and/or chemotherapy has become an accepted cancer treatment for distinct solid tumour entities. In HT, tumour tissue is exogenously heated to temperatures of 39 to 43 °C for 60 minutes. Temperature monitoring can be performed noninvasively using dynamic magnetic resonance imaging (MRI). However, the slow nature of MRI leads to motion artefacts in the images due to the movements of patients during image acquisition time. By discarding parts of the data, the speed of the acquisition can be increased-known as Undersampling. However, due to the invalidation of the Nyquist criterion, the acquired images have lower resolution and can also produce artefacts. The aim of this work was, therefore, to reconstruct highly undersampled MR thermometry acquisitions with better resolution and with less artefacts compared to conventional techniques like compressed sensing. The use of deep learning in the medical field has emerged in recent times, and various studies have shown that deep learning has the potential to solve inverse problems such as MR image reconstruction. However, most of the published work only focusses on the magnitude images, while the phase images are ignored, which are fundamental requirements for MR thermometry. This work, for the first time ever, presents deep learning based solutions for reconstructing undersampled MR thermometry data. Two different deep learning models have been employed here, the Fourier Primal-Dual network and Fourier Primal-Dual UNet, to reconstruct highly undersampled complex images of MR thermometry. MR images of 44 patients with different sarcoma cancers who have received the HT treatment in a combination of radiotherapy/chemotherapy were used in this study. It was observed that the method was able to reduce the temperature difference between the undersampled MRIs and the fully sampled MRIs from 1.5 °C to 0.5°C.","manuscriptTitle":"Fourier PD and PDUNet: Complex-valued networks to speed-up MR Thermometry during Hyperthermia","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-11 06:30:04","doi":"10.21203/rs.3.rs-4491570/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-07-04T15:58:54+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-25T03:41:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-17T01:36:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"317554601851983585615177770975688604318","date":"2024-06-13T04:22:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"206882790005047520344166429275396185697","date":"2024-06-07T17:43:47+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-06-07T12:59:02+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-05-29T11:29:58+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-05-29T08:51:54+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-05-29T08:50:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-05-28T14:19:59+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"197362b5-b6fd-4180-b444-de63265e9674","owner":[],"postedDate":"June 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":33065204,"name":"Health sciences/Health care/Medical imaging/Magnetic resonance imaging"},{"id":33065205,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":33065206,"name":"Physical sciences/Physics/Applied physics"},{"id":33065207,"name":"Physical sciences/Engineering/Biomedical engineering"}],"tags":[],"updatedAt":"2025-04-07T16:04:35+00:00","versionOfRecord":{"articleIdentity":"rs-4491570","link":"https://doi.org/10.1038/s41598-025-96071-x","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-04-06 15:57:40","publishedOnDateReadable":"April 6th, 2025"},"versionCreatedAt":"2024-06-11 06:30:04","video":"","vorDoi":"10.1038/s41598-025-96071-x","vorDoiUrl":"https://doi.org/10.1038/s41598-025-96071-x","workflowStages":[]},"version":"v1","identity":"rs-4491570","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4491570","identity":"rs-4491570","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}