Irregular Feature Enhancer for Low-dose CT Denoising

Irregular Feature Enhancer for Low-dose CT Denoising | 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 Irregular Feature Enhancer for Low-dose CT Denoising Jiehang Deng, Zihang Hu, Jinwen He, Jiaxin Liu, Guoqing Qiao, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4198593/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 25 Nov, 2024 Read the published version in Multimedia Systems → Version 1 posted 11 You are reading this latest preprint version Abstract So far, deep learning based networks have been wildly applied in Low-Dose Computed Tomography (LDCT) image denoising. However, they usually adopt symmetric convolution to achieve regular feature extraction, but cannot effectively extract irregular features. Therefore, in this paper, an Irregular Feature Enhancer (IFE) focusing on effectively extracting irregular features is proposed by combining Symmetric-Asymmetric-Synergy Convolution Module (SASCM) with a hybrid loss module. Rather than simply stacking symmetric convolution layers used in traditional deep learning based networks, SASCM jointly utilizes symmetric and asymmetric convolution layers so as to effectively extract irregular tissue information of the image. In addition, the hybrid loss module is proposed to guide IFE to further mine the intrinsic feature information of the image from three perspectives: pixel point, high-level feature space, and gradient. The ablation experiments demonstrate the effectiveness and feasibility of SASCM and the hybrid loss. The quantitative experimental results also show that compared with several related LDCT denoising methods, the proposed IFE performs the best in terms of PSNR and SSIM. Furthermore, it can be observed from the qualitative visualization that the proposed IFE can recover the best image detail structure information among the compared methods. Low-dose Denoising SASCM Hybrid loss Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 25 Nov, 2024 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 29 May, 2024 Reviews received at journal 11 May, 2024 Reviews received at journal 09 May, 2024 Reviewers agreed at journal 09 May, 2024 Reviews received at journal 06 May, 2024 Reviewers agreed at journal 16 Apr, 2024 Reviewers agreed at journal 16 Apr, 2024 Reviewers invited by journal 16 Apr, 2024 Editor assigned by journal 14 Apr, 2024 Submission checks completed at journal 04 Apr, 2024 First submitted to journal 01 Apr, 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-4198593","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":290945185,"identity":"67b0430d-caa3-4e17-a9a9-8a0144dfb675","order_by":0,"name":"Jiehang Deng","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jiehang","middleName":"","lastName":"Deng","suffix":""},{"id":290945186,"identity":"0a681aa8-551e-4208-888c-3b4cec4a9392","order_by":1,"name":"Zihang Hu","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Zihang","middleName":"","lastName":"Hu","suffix":""},{"id":290945187,"identity":"33a3ee42-66f5-45ee-96d8-aad8ce379e55","order_by":2,"name":"Jinwen He","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jinwen","middleName":"","lastName":"He","suffix":""},{"id":290945188,"identity":"91816387-6983-4e47-a5d6-1302c79b84c7","order_by":3,"name":"Jiaxin Liu","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jiaxin","middleName":"","lastName":"Liu","suffix":""},{"id":290945189,"identity":"8551ca53-6106-4c0f-be49-ebe38dc09734","order_by":4,"name":"Guoqing Qiao","email":"","orcid":"","institution":"General Hospital of the Southern Theater of Operations","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Guoqing","middleName":"","lastName":"Qiao","suffix":""},{"id":290945190,"identity":"2f982606-8992-4f14-9a88-b732d9a788dc","order_by":5,"name":"Guosheng Gu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwUlEQVRIiWNgGAWjYLCCDwzMYFqCaB2MM4BaeEjSwsxDkhZ5/+PXpG1+WSfuZ2A+eJuHwS6PoBbDGzll0rl96Yk9DGzJ1jwMycWEtczgSZPO7TkM1MJjJs3DcCCxgaCW/jNp0pZgLfzfiNMiz5B+TJrhB9gWNuK0GEjkMFv2NqQb9xxmM7acY5BMhC39xx/e+PHHWra9vfnhjTcVdkTYcoDHgIGxDcgCJwADQupBtjSwP2Bg+EOEylEwCkbBKBi5AADCpjhDvtuzmgAAAABJRU5ErkJggg==","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Guosheng","middleName":"","lastName":"Gu","suffix":""},{"id":290945191,"identity":"5d5d04ff-6824-43cf-9385-00c3f94e9511","order_by":6,"name":"Shaowei Weng","email":"","orcid":"","institution":"Fujian University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Shaowei","middleName":"","lastName":"Weng","suffix":""}],"badges":[],"createdAt":"2024-04-01 06:33:55","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4198593/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4198593/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-024-01575-7","type":"published","date":"2024-11-25T15:57:37+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":70391337,"identity":"2bec18e0-f27a-4dd7-a14e-19c0432f8476","added_by":"auto","created_at":"2024-12-02 17:30:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":921581,"visible":true,"origin":"","legend":"","description":"","filename":"IrregularFeatureEnhancerforLowdoseCTDenoising.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4198593/v1_covered_8813848f-0c7f-4893-9ab0-0b21f0b9b3eb.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Irregular Feature Enhancer for Low-dose CT Denoising","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":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Low-dose, Denoising, SASCM, Hybrid loss","lastPublishedDoi":"10.21203/rs.3.rs-4198593/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4198593/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSo far, deep learning based networks have been wildly applied in Low-Dose Computed Tomography (LDCT) image denoising. However, they usually adopt symmetric convolution to achieve regular feature extraction, but cannot effectively extract irregular features. Therefore, in this paper, an Irregular Feature Enhancer (IFE) focusing on effectively extracting irregular features is proposed by combining Symmetric-Asymmetric-Synergy Convolution Module (SASCM) with a hybrid loss module. Rather than simply stacking symmetric convolution layers used in traditional deep learning based networks, SASCM jointly utilizes symmetric and asymmetric convolution layers so as to effectively extract irregular tissue information of the image. In addition, the hybrid loss module is proposed to guide IFE to further mine the intrinsic feature information of the image from three perspectives: pixel point, high-level feature space, and gradient. The ablation experiments demonstrate the effectiveness and feasibility of SASCM and the hybrid loss. The quantitative experimental results also show that compared with several related LDCT denoising methods, the proposed IFE performs the best in terms of PSNR and SSIM. Furthermore, it can be observed from the qualitative visualization that the proposed IFE can recover the best image detail structure information among the compared methods.\u003c/p\u003e","manuscriptTitle":"Irregular Feature Enhancer for Low-dose CT Denoising","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-17 01:49:50","doi":"10.21203/rs.3.rs-4198593/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-05-29T15:40:07+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-11T14:16:03+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-09T12:20:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"306960773244060515404454976190500860899","date":"2024-05-09T07:04:28+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-06T14:59:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"86c25545-b01f-4308-b697-151fd6b2d148","date":"2024-04-17T02:48:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"b98818e0-ee1a-41e6-9df9-c901d0077e51","date":"2024-04-17T02:43:50+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-04-17T02:38:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-04-14T07:27:06+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-04-04T08:06:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2024-04-01T06:32:33+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"412b34db-907c-45a0-97b0-cf61444dbfe6","owner":[],"postedDate":"April 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-12-02T17:28:55+00:00","versionOfRecord":{"articleIdentity":"rs-4198593","link":"https://doi.org/10.1007/s00530-024-01575-7","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2024-11-25 15:57:37","publishedOnDateReadable":"November 25th, 2024"},"versionCreatedAt":"2024-04-17 01:49:50","video":"","vorDoi":"10.1007/s00530-024-01575-7","vorDoiUrl":"https://doi.org/10.1007/s00530-024-01575-7","workflowStages":[]},"version":"v1","identity":"rs-4198593","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4198593","identity":"rs-4198593","version":["v1"]},"buildId":"rHA-KDH7Qsr4HCuvH75dn","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}