Texture Feature Analysis of MRI-ADC Images to Differentiate Glioma Grades Using Machine Learning Techniques.

Texture Feature Analysis of MRI-ADC Images to Differentiate Glioma Grades Using Machine Learning Techniques. | 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 Texture Feature Analysis of MRI-ADC Images to Differentiate Glioma Grades Using Machine Learning Techniques. Sahan M. Vijithananda, Mohan Mohan L. Jayatilake, Teresa C. Gonçalves, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2193959/v2 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 22 Sep, 2023 Read the published version in Scientific Reports → Version 2 posted 9 You are reading this latest preprint version Show more versions Abstract Background : Apparent Diffusion Coefficient (ADC) of Magnetic Resonance Imaging (MRI) is an indispensable imaging technique in clinical neuroimaging that quantitatively assesses the diffusivity of water molecules within tissues using Diffusion-weighted imaging (DWI). This study focuses on developing a robust Machine Learning (ML) model to predict the aggressiveness of gliomas according to World Health Organization (WHO) grading by analyzing patients’ demographics, higher-order moments, and Grey Level Co-occurrence Matrix (GLCM) texture features of ADC. Methods : A population of 722 labeled MRI-ADC brain image slices from 88 human subjects was selected, where gliomas are labeled as glioblastoma multiforme (WHO-IV), high-grade glioma (WHO-III), and low-grade glioma (WHO I-II). Images were acquired using 3T-MR systems and a region of interest (ROI) was delineated over tumor areas. Skewness, kurtosis, and statistical texture features of GLCM (mean, variance, energy, entropy, contrast, homogeneity, correlation, prominence, and shade) were calculated using ADC values within ROI. The ANOVA f-test was utilized to select the best features to train an ML model. The data set was split into training (70%) and testing (30%) sets. The train set was fed into several ML algorithms and selected most promising ML algorithm using K-fold cross-validation. The hyper-parameters of the selected algorithm were optimized using random grid search technique. Finally, the performance of the developed model was assessed by calculating accuracy, precision, recall, and F1 values reported for the test set. Results : According to the ANOVA f-test, three attributes; patient gender (1.48), GLCM energy (9.48), and correlation (13.86) that performed minimum scores were excluded from the dataset. Among the tested algorithms, the random forest classifier(0.8772±0.0237) performed the highest score and selected to build the ML model which was able to predict tumor categories with an accuracy of 88.14% over the test set. Conclusion: The study concludes that the developed ML model using the above features except for patient gender, GLCM energy, and correlation, has high prediction accuracy in glioma grading. Therefore, the outcomes of this study enable to development of advanced tumor classification applications that assist in the decision-making process in a real-time clinical environment. Biological sciences/Cancer Biological sciences/Computational biology and bioinformatics Health sciences/Neurology Physical sciences/Engineering Magnetic Resonance Imaging Diffusion Weighted Imaging Apparent Diffusion Coefficient Glioma grading Machine Learning Grey Level Co-occurrence Matrix Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 22 Sep, 2023 Read the published version in Scientific Reports → Version 2 posted Editorial decision: Major revision 09 Mar, 2023 Reviews received at journal 07 Feb, 2023 Reviewers agreed at journal 23 Jan, 2023 Reviewers agreed at journal 16 Jan, 2023 Reviewers invited by journal 09 Jan, 2023 Editor assigned by journal 09 Jan, 2023 Editor invited by journal 30 Nov, 2022 Submission checks completed at journal 30 Nov, 2022 First submitted to journal 21 Nov, 2022 You are reading this latest preprint version Show more versions 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-2193959","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[{"code":1,"date":"2022-11-15 07:14:57","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"articleType":"Article","associatedPublications":[],"authors":[{"id":166727814,"identity":"7a03d413-cea3-42c8-aadf-875ca705f598","order_by":0,"name":"Sahan M. Vijithananda","email":"","orcid":"","institution":"University of Peradeniya","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Sahan","middleName":"M.","lastName":"Vijithananda","suffix":""},{"id":166727815,"identity":"bf522942-313d-454b-97f5-a7c127a05176","order_by":1,"name":"Mohan Mohan L. Jayatilake","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2ElEQVRIiWNgGAWjYBACxgYQacAgww8iQYCPhxgtBwwYeCQboFrYCGkBgwMMDDwGB4jVwtx+xvDzh4JtPMa3m7c9YKixA2o5QMBhPTnGEgcMbvOY3TlWbsBwLJmBjbeBgJaGHAOIlhs5ZhIMbAcY2PgJOIyx/43xD5AW4xkgLf+I0QJSCdJiIAFkMLYdIMJhM56VWZwBapG4c6xMIrEvmYeg9w37kzffqPhzW45/dvM2iQ/f7OT4eRIIaGnggEQHgwQQAxUTjkh5BvYHCC2jYBSMglEwCrABACwpPpP0UhBEAAAAAElFTkSuQmCC","orcid":"","institution":"University of Peradeniya","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Mohan","middleName":"Mohan L.","lastName":"Jayatilake","suffix":""},{"id":166727816,"identity":"57162f6c-6fd9-4a28-a25a-30a403ee493f","order_by":2,"name":"Teresa C. Gonçalves","email":"","orcid":"","institution":"University of Évora","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Teresa","middleName":"C.","lastName":"Gonçalves","suffix":""},{"id":166727817,"identity":"48a7c818-5721-4749-afa3-bb87432915cf","order_by":3,"name":"Badra Hewavithana","email":"","orcid":"","institution":"University of Peradeniya","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Badra","middleName":"","lastName":"Hewavithana","suffix":""},{"id":166727818,"identity":"9b070ef4-bb57-4e7f-8dd9-8b054da0dc2d","order_by":4,"name":"Luis M. Rato","email":"","orcid":"","institution":"University of Évora","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Luis","middleName":"M.","lastName":"Rato","suffix":""},{"id":166727819,"identity":"800c6ac8-0510-46e6-ade4-4585a5346d3d","order_by":5,"name":"Bimali S. Weerakoon","email":"","orcid":"","institution":"University of Peradeniya","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Bimali","middleName":"S.","lastName":"Weerakoon","suffix":""},{"id":166727820,"identity":"d85eaed1-a071-48ae-ac47-02f924015758","order_by":6,"name":"Tharindu D. Kalupahana","email":"","orcid":"","institution":"University of Sri Jayewardenepura","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Tharindu","middleName":"D.","lastName":"Kalupahana","suffix":""},{"id":166727821,"identity":"58e70801-ba48-4910-be9c-6b9f40fd99bf","order_by":7,"name":"Anil D. Silva","email":"","orcid":"","institution":"National Hospital of Sri Lanka","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Anil","middleName":"D.","lastName":"Silva","suffix":""},{"id":166727822,"identity":"5d87d78a-254e-41dd-ad0a-8ed12af64e43","order_by":8,"name":"Karuna Dissanayake","email":"","orcid":"","institution":"National Hospital of Sri Lanka","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Karuna","middleName":"","lastName":"Dissanayake","suffix":""}],"badges":[],"createdAt":"2022-10-22 16:29:19","currentVersionCode":2,"declarations":"","doi":"10.21203/rs.3.rs-2193959/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-2193959/v2","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-023-41353-5","type":"published","date":"2023-09-22T15:01:52+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":43640874,"identity":"dda3ba81-4c51-4202-81e3-93322175b101","added_by":"auto","created_at":"2023-09-25 15:09:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":631566,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptLaTeXsourcefile.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2193959/v2_covered_672f6862-ec6a-4ced-a09d-4f0f86c1edd4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Texture Feature Analysis of MRI-ADC Images to Differentiate Glioma Grades Using Machine Learning Techniques.","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":"Magnetic Resonance Imaging, Diffusion Weighted Imaging,Apparent Diffusion Coefficient, Glioma grading, Machine Learning, Grey Level Co-occurrence Matrix","lastPublishedDoi":"10.21203/rs.3.rs-2193959/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2193959/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground\u003c/strong\u003e: Apparent Diffusion Coefficient (ADC) of Magnetic Resonance Imaging (MRI) is an indispensable imaging technique in clinical neuroimaging that quantitatively assesses the diffusivity of water molecules within tissues using Diffusion-weighted imaging (DWI). This study focuses on developing a robust Machine Learning (ML) model to predict the aggressiveness of gliomas according to World Health Organization (WHO) grading by analyzing patients’ demographics, higher-order moments, and Grey Level Co-occurrence Matrix (GLCM) texture features of ADC.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods\u003c/strong\u003e: A population of 722 labeled MRI-ADC brain image slices from 88 human subjects was selected, where gliomas are labeled as glioblastoma multiforme (WHO-IV), high-grade glioma (WHO-III), and low-grade glioma (WHO I-II). Images were acquired using 3T-MR systems and a region of interest (ROI) was delineated over tumor areas. Skewness, kurtosis, and statistical texture features of GLCM (mean, variance, energy, entropy, contrast, homogeneity, correlation, prominence, and shade) were calculated using ADC values within ROI. The ANOVA f-test was utilized to select the best features to train an ML model. The data set was split into training (70%) and testing (30%) sets. The train set was fed into several ML algorithms and selected most promising ML algorithm using K-fold cross-validation. The hyper-parameters of the selected algorithm were optimized using random grid search technique. Finally, the performance of the developed model was assessed by calculating accuracy, precision, recall, and F1 values reported for the test set.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e: According to the ANOVA f-test, three attributes; patient gender (1.48), GLCM energy (9.48), and correlation (13.86) that performed minimum scores were excluded from the dataset. Among the tested algorithms, the random forest classifier(0.8772±0.0237) performed the highest score and selected to build the ML model which was able to predict tumor categories with an accuracy of 88.14% over the test set.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion:\u003c/strong\u003e The study concludes that the developed ML model using the above features except for patient gender, GLCM energy, and correlation, has high prediction accuracy in glioma grading. Therefore, the outcomes of this study enable to development of advanced tumor classification applications that assist in the decision-making process in a real-time clinical environment.\u003c/p\u003e","manuscriptTitle":"Texture Feature Analysis of MRI-ADC Images to Differentiate Glioma Grades Using Machine Learning Techniques.","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2023-01-11 11:44:33","doi":"10.21203/rs.3.rs-2193959/v2","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2023-03-09T09:20:21+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-02-07T14:52:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"162aea5e-a4f4-446d-93de-b24e126fae95","date":"2023-01-23T14:01:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"2576c3f7-5a08-4483-a9db-76acb7e05d1c","date":"2023-01-16T09:03:06+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-01-09T16:59:55+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-01-09T16:51:15+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2022-11-30T16:21:17+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2022-11-30T16:19:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2022-11-22T04:14:48+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":"ec6b0a54-2130-496e-a43a-48c1fce8d7ab","owner":[],"postedDate":"January 11th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":18309416,"name":"Biological sciences/Cancer"},{"id":18309417,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":18309418,"name":"Health sciences/Neurology"},{"id":18309419,"name":"Physical sciences/Engineering"}],"tags":[],"updatedAt":"2023-09-25T15:07:58+00:00","versionOfRecord":{"articleIdentity":"rs-2193959","link":"https://doi.org/10.1038/s41598-023-41353-5","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2023-09-22 15:01:52","publishedOnDateReadable":"September 22nd, 2023"},"versionCreatedAt":"2023-01-11 11:44:33","video":"","vorDoi":"10.1038/s41598-023-41353-5","vorDoiUrl":"https://doi.org/10.1038/s41598-023-41353-5","workflowStages":[]},"version":"v2","identity":"rs-2193959","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2193959","identity":"rs-2193959","version":["v2"]},"buildId":"-HB7Z8yhvgn0wM9Nzuekk","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}