{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:01:20Z","timestamp":1787022080857,"version":"build-2736575974"},"reference-count":58,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T00:00:00Z","timestamp":1614211200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004515","name":"Universiti Kebangsaan Malaysia","doi-asserted-by":"publisher","award":["GGP-2019-023"],"award-info":[{"award-number":["GGP-2019-023"]}],"id":[{"id":"10.13039\/501100004515","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004515","name":"Universiti Kebangsaan Malaysia","doi-asserted-by":"publisher","award":["GP-2019-K005539"],"award-info":[{"award-number":["GP-2019-K005539"]}],"id":[{"id":"10.13039\/501100004515","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>\n                    Achieving biologically interpretable neural-biomarkers and features from neuroimaging datasets is a challenging task in an MRI-based dyslexia study. This challenge becomes more pronounced when the needed MRI datasets are collected from multiple heterogeneous sources with inconsistent scanner settings. This study presents a method of improving the biological interpretation of dyslexia\u2019s neural-biomarkers from MRI datasets sourced from publicly available open databases. The proposed system utilized a modified histogram normalization (MHN) method to improve dyslexia neural-biomarker interpretations by mapping the pixels\u2019 intensities of low-quality input neuroimages to range between the low-intensity region of interest (\n                    <jats:italic>ROI<\/jats:italic>\n                    <jats:sub>low<\/jats:sub>\n                    ) and high-intensity region of interest (\n                    <jats:italic>ROI<\/jats:italic>\n                    <jats:sub>high<\/jats:sub>\n                    ) of the high-quality image. This was achieved after initial image smoothing using the Gaussian filter method with an isotropic kernel of size 4mm. The performance of the proposed smoothing and normalization methods was evaluated based on three image post-processing experiments: ROI segmentation, gray matter (GM) tissues volume estimations, and deep learning (DL) classifications using Computational Anatomy Toolbox (CAT12) and pre-trained models in a MATLAB working environment. The three experiments were preceded by some pre-processing tasks such as image resizing, labelling, patching, and non-rigid registration. Our results showed that the best smoothing was achieved at a scale value,\n                    <jats:italic>\u03c3<\/jats:italic>\n                    = 1.25 with a 0.9% increment in the peak-signal-to-noise ratio (PSNR). Results from the three image post-processing experiments confirmed the efficacy of the proposed methods. Evidence emanating from our analysis showed that using the proposed MHN and Gaussian smoothing methods can improve comparability of image features and neural-biomarkers of dyslexia with a statistically significantly high disc similarity coefficient (DSC) index, low mean square error (MSE), and improved tissue volume estimations. After 10 repeated 10-fold cross-validation, the highest accuracy achieved by DL models is 94.7% at a 95% confidence interval (CI) level. Finally, our finding confirmed that the proposed MHN method significantly outperformed the normalization method of the state-of-the-art histogram matching.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0245579","type":"journal-article","created":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T13:53:34Z","timestamp":1614261214000},"page":"e0245579","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":27,"title":["Gaussian smoothing and modified histogram normalization methods to improve neural-biomarker interpretations for dyslexia classification mechanism"],"prefix":"10.1371","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0788-5927","authenticated-orcid":true,"given":"Opeyemi Lateef","family":"Usman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8999-9548","authenticated-orcid":true,"given":"Ravie Chandren","family":"Muniyandi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khairuddin","family":"Omar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mazlyfarina","family":"Mohamad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"pone.0245579.ref001","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2020.105726","article-title":"Dyslexia detection using 3D convolutional neural networks and functional magnetic resonance imaging","volume":"197","author":"S Zahia","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0245579.ref002","doi-asserted-by":"crossref","DOI":"10.1016\/j.dcn.2019.100717","article-title":"Simultaneous EEG and fMRI reveals stronger sensitivity to orthographic strings in the left occipito-temporal cortex of typical versus poor beginning readers","volume":"40","author":"G Pleisch","year":"2019","journal-title":"Dev Cogn Neurosci."},{"key":"pone.0245579.ref003","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1016\/j.cortex.2019.09.010","article-title":"Atypical gray matter in children with dyslexia before the onset of reading instruction","volume":"121","author":"C Beelen","year":"2019","journal-title":"Cortex"},{"issue":"10","key":"pone.0245579.ref004","doi-asserted-by":"crossref","first-page":"948","DOI":"10.1016\/j.jaac.2018.11.007","article-title":"Reading Acquisition in Children: Developmental Processes and Dyslexia-Specific Effects","volume":"58","author":"K Chyl","year":"2019","journal-title":"J Am Acad Child Adolesc Psychiatry"},{"key":"pone.0245579.ref005","doi-asserted-by":"crossref","DOI":"10.1016\/j.neuroimage.2020.116633","article-title":"The emergence of dyslexia in the developing brain","volume":"211","author":"U Kuhl","year":"2020","journal-title":"Neuroimage"},{"issue":"2","key":"pone.0245579.ref006","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1109\/42.836373","article-title":"New Variants of a Method of MRI Scale Standardization","volume":"19","author":"LG Nyul","year":"2000","journal-title":"IEEE Trans Med Imaging"},{"issue":"1","key":"pone.0245579.ref007","article-title":"Brain MR image normalization in texture analysis of multiple sclerosis","volume":"3","author":"CP Loizou","year":"2013","journal-title":"J Biomed Graph Comput"},{"issue":"73","key":"pone.0245579.ref008","first-page":"1","article-title":"Histogram \u2011 based normalization technique on human brain magnetic resonance images from different acquisitions","volume":"14","author":"X Sun","year":"2015","journal-title":"Biomed Eng Online"},{"key":"pone.0245579.ref009","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.nicl.2014.08.008","article-title":"Statistical normalization techniques for magnetic resonance imaging","volume":"6","author":"RT Shinohara","year":"2014","journal-title":"NeuroImage Clin"},{"issue":"2","key":"pone.0245579.ref010","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1002\/hbm.23426","article-title":"Multi-parameter machine learning approach to the neuroanatomical basis of developmental dyslexia","volume":"38","author":"P P\u0142o\u0144ski","year":"2017","journal-title":"Hum Brain Mapp"},{"key":"pone.0245579.ref011","first-page":"471","article-title":"Dealing with the heterogeneous multi-site neuroimaging data sets: A discrimination study of children dyslexia","author":"P P\u0142o\u0144ski","year":"2014","journal-title":"Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics)"},{"issue":"5","key":"pone.0245579.ref012","doi-asserted-by":"crossref","first-page":"1741","DOI":"10.1002\/hbm.22734","article-title":"How reliable are gray matter disruptions in specific reading disability across multiple countries and languages? Insights from a large-scale voxel-based morphometry study","volume":"36","author":"K Jednor\u00f3g","year":"2015","journal-title":"Hum Brain Mapp"},{"key":"pone.0245579.ref013","first-page":"1","article-title":"MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data","author":"Q Liu","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"issue":"2","key":"pone.0245579.ref014","doi-asserted-by":"crossref","first-page":"1193","DOI":"10.1016\/S1053-8119(03)00354-9","article-title":"Time-series analysis of MRI intensity patterns in multiple sclerosis","volume":"20","author":"DS Meier","year":"2003","journal-title":"Neuroimage"},{"issue":"6","key":"pone.0245579.ref015","doi-asserted-by":"crossref","first-page":"1072","DOI":"10.1002\/(SICI)1522-2594(199912)42:6<1072::AID-MRM11>3.0.CO;2-M","article-title":"On standardizing the MR image intensity scale","volume":"42","author":"LG Ny\u00fal","year":"1999","journal-title":"Magn Reson Med"},{"issue":"2","key":"pone.0245579.ref016","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/j.media.2010.12.003","article-title":"Evaluating intensity normalization on MRIs of human brain with multiple sclerosis","volume":"15","author":"M Shah","year":"2011","journal-title":"Med Image Anal"},{"issue":"1","key":"pone.0245579.ref017","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.mri.2003.09.001","article-title":"Influence of MRI acquisition protocols and image intensity normalization methods on texture classification","volume":"22","author":"G Collewet","year":"2004","journal-title":"Magn Reson Imaging"},{"key":"pone.0245579.ref018","volume-title":"Digital Image Processing","author":"RC Gonzalez","year":"2002","edition":"3"},{"key":"pone.0245579.ref019","article-title":"Contrast Stretch and Normalization","author":"S Koptenko","year":"2020","journal-title":"MATLAB Central File Exchange"},{"issue":"7","key":"pone.0245579.ref020","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1016\/S0730-725X(03)00102-4","article-title":"Normalization of brain magnetic resonance images using histogram even-order derivative analysis","volume":"21","author":"JD Christensen","year":"2003","journal-title":"Magn Reson Imaging"},{"issue":"2","key":"pone.0245579.ref021","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1002\/mrm.1910390222","article-title":"Correction for variations in MRI scanner sensitivity in brain studies with histogram matching","volume":"39","author":"L Wang","year":"1998","journal-title":"Magn Reson Med"},{"issue":"9","key":"pone.0245579.ref022","doi-asserted-by":"crossref","first-page":"3426","DOI":"10.1118\/1.2335487","article-title":"New methods of MR image intensity standardization via generalized scale","volume":"33","author":"A Madabhushi","year":"2006","journal-title":"Med Phys"},{"issue":"2","key":"pone.0245579.ref023","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.cviu.2005.07.010","article-title":"Generalized scale: Theory, algorithms, and application to image inhomogeneity correction","volume":"101","author":"A Madabhushi","year":"2006","journal-title":"Comput Vis Image Underst"},{"issue":"10","key":"pone.0245579.ref024","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1109\/83.791966","article-title":"Wavelet-based Rician noise removal for magnetic resonance imaging","volume":"8","author":"RD Nowak","year":"1999","journal-title":"IEEE Trans Image Process"},{"issue":"12","key":"pone.0245579.ref025","doi-asserted-by":"crossref","first-page":"1579","DOI":"10.1109\/TIP.2003.819229","article-title":"Noise removal using fourth-order partial differential equation with applications to medical magnetic resonance images in space and time","volume":"12","author":"M Lysaker","year":"2003","journal-title":"IEEE Trans Image Process"},{"issue":"8","key":"pone.0245579.ref026","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.1109\/TIP.2008.925382","article-title":"Noise and signal estimation in magnitude MRI and Rician distributed images: A LMMSE approach","volume":"17","author":"S Aja-Fern\u00e1ndez","year":"2008","journal-title":"IEEE Trans Image Process"},{"issue":"2","key":"pone.0245579.ref027","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.media.2003.12.001","article-title":"DT-MRI denoising and neuronal fiber tracking","volume":"8","author":"T McGraw","year":"2004","journal-title":"Med Image Anal"},{"issue":"6","key":"pone.0245579.ref028","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1109\/42.781019","article-title":"Adaptive template filtering for signal-to-noise ratio enhancement in magnetic resonance imaging","volume":"18","author":"CB Ahn","year":"1999","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0245579.ref029","first-page":"677","volume-title":"IPIMI 2005, LNCS","author":"SP Awate","year":"2005"},{"key":"pone.0245579.ref030","first-page":"117","article-title":"Rician noise removal in diffusion tensor MRI","author":"S Basu","year":"2006","journal-title":"Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics)"},{"issue":"2","key":"pone.0245579.ref031","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.mri.2006.05.001","article-title":"Sequential anisotropic Wiener filtering applied to 3D MRI data","volume":"25","author":"M Martin-Fernandez","year":"2007","journal-title":"Magn Reson Imaging"},{"issue":"160044","key":"pone.0245579.ref032","first-page":"208","article-title":"The brain imaging data structure, a format for organizing and describing outputs of neuroimaging experimts","volume":"3","author":"KJ Gorgolewski","year":"2016","journal-title":"Sci Data"},{"issue":"105091","key":"pone.0245579.ref033","first-page":"1","article-title":"A neuroimaging dataset on orthographic, phonological and semantic word processing in school-aged children","volume":"28","author":"MN Lytle","year":"2020","journal-title":"Data Br"},{"issue":"5","key":"pone.0245579.ref034","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0096899","article-title":"Optimizing the Magnetization-Prepared Rapid Gradient-Echo (MP-RAGE) sequence","volume":"9","author":"J Wang","year":"2014","journal-title":"PLoS One"},{"issue":"3","key":"pone.0245579.ref035","doi-asserted-by":"crossref","first-page":"1116","DOI":"10.1016\/j.neuroimage.2006.01.015","article-title":"User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability","volume":"31","author":"PA Yushkevich","year":"2006","journal-title":"Neuroimage"},{"key":"pone.0245579.ref036","doi-asserted-by":"crossref","first-page":"91772","DOI":"10.1109\/ACCESS.2019.2927286","article-title":"Length Independent Writer Identification Based on the Fusion of Deep and Hand-Crafted Descriptors","volume":"7","author":"A Sulaiman","year":"2019","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0245579.ref037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/cseij.2016.6101","article-title":"Image Segmentation By Using Thresholding Techniques For Medical Images","volume":"6","author":"N Senthilkumaran","year":"2016","journal-title":"Comput Sci Eng An Int J."},{"issue":"6","key":"pone.0245579.ref038","first-page":"1","article-title":"Efficient Segmentation Method for ROI Detection in Mammography Images Using Morphological Operations","volume":"3","author":"J Denny","year":"2020","journal-title":"Int Adv J Eng Res"},{"issue":"1","key":"pone.0245579.ref039","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/42.906424","article-title":"Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm","volume":"20","author":"Y Zhang","year":"2001","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0245579.ref040","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/S1053-8119(01)91428-4","article-title":"Using the Talairach Atlas with the MNI template The Talairach atlas","volume":"13","author":"M Brett","year":"2001","journal-title":"Neuroimage"},{"key":"pone.0245579.ref041","unstructured":"Andersson JLR, Jenkinson M, Smith S. Non-linear registration, aka spatial normalization: FMRIB Technical Report TR07JA2. Oxford, United Kingdom; 2007."},{"key":"pone.0245579.ref042","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1016\/j.neuroimage.2017.04.041","article-title":"VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images","volume":"170","author":"H Chen","year":"2018","journal-title":"Neuroimage"},{"issue":"6","key":"pone.0245579.ref043","first-page":"398","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","volume":"75","author":"K Simonyan","year":"2015","journal-title":"ICLR"},{"key":"pone.0245579.ref044","first-page":"2322","article-title":"Going Deeper with Convolutions","author":"C Szegedy","year":"2015","journal-title":"CVPR2015: Computer Vision Foundation"},{"key":"pone.0245579.ref045","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J. Rethinking the Inception Architecture for Computer Vision. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2016. p. 2818\u201326.","DOI":"10.1109\/CVPR.2016.308"},{"issue":"3","key":"pone.0245579.ref046","first-page":"1","article-title":"Optimized deep convolutional neural networks for identification of macular diseases from optical coherence tomography images","volume":"12","author":"Q Ji","year":"2019","journal-title":"Algorithms"},{"issue":"5","key":"pone.0245579.ref047","first-page":"1","article-title":"CryptoDL: Predicting Dyslexia Biomarkers from Encrypted Neuroimaging Dataset Using Energy-E ffi cient Residue Number System and Deep Convolutional Neural Network","volume":"12","author":"OL Usman","year":"2020","journal-title":"Symmetry (Basel)"},{"key":"pone.0245579.ref048","first-page":"1","article-title":"An Image Segmentation Framework Based on Patch Segmentation Fusion An Image Segmentation Framework Based on Patch Segmentation Fusion","author":"L Zhang","year":"2006","journal-title":"IEEE Xplore"},{"key":"pone.0245579.ref049","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J. Pyramid Scene Parsing Network. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2017. p. 6230\u20139.","DOI":"10.1109\/CVPR.2017.660"},{"key":"pone.0245579.ref050","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.simpat.2014.05.005","article-title":"Parallel and distributed computing models on a graphics processing unit to accelerate simulation of membrane systems","volume":"47","author":"A Maroosi","year":"2014","journal-title":"Simul Model Pract Theory"},{"key":"pone.0245579.ref051","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.imu.2017.10.008","article-title":"Review of GPU implementation to process of RNA sequence on cancer","volume":"10","author":"MA Rahman","year":"2018","journal-title":"Informatics Med Unlocked"},{"key":"pone.0245579.ref052","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1177\/0022219414558123","article-title":"Five Describing Factors of Dyslexia","volume":"49","author":"P Tamboer","year":"2016","journal-title":"Journal of Learning Disabilities"},{"key":"pone.0245579.ref053","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1016\/j.nicl.2016.03.014","article-title":"Machine learning and dyslexia: Classification of individual structural neuro-imaging scans of students with and without dyslexia","volume":"11","author":"P Tamboer","year":"2016","journal-title":"NeuroImage Clin"},{"issue":"4","key":"pone.0245579.ref054","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1002\/hbm.23112","article-title":"Disrupted white matter connectivity underlying developmental dyslexia: A machine learning approach","volume":"37","author":"Z Cui","year":"2016","journal-title":"Hum Brain Mapp"},{"issue":"2","key":"pone.0245579.ref055","first-page":"3","article-title":"Brain Activation During Addition and Subtraction Tasks In-Noise and In-Quiet","volume":"18","author":"AI Abd Hamid","year":"2011","journal-title":"Malaysian J Med Sci"},{"issue":"01","key":"pone.0245579.ref056","doi-asserted-by":"crossref","first-page":"35","DOI":"10.17576\/jskm-2018-1601-05","article-title":"Brain Activation Display Functional Asymmetry in Response to Action, Background and Tonal Frequency During a Pitch Memory Processing: An fMRI Study","volume":"16","author":"AN Yusoff","year":"2018","journal-title":"J Sains Kesihat Malaysia"},{"issue":"12","key":"pone.0245579.ref057","first-page":"1","article-title":"Screening for dyslexia using eye tracking during reading","volume":"11","author":"MN Benfatto","year":"2016","journal-title":"PLoS One"},{"key":"pone.0245579.ref058","unstructured":"Frid A, Manevitz LM. Features and machine learning for correlating and classifying between brain areas and dyslexia. In: arXiv:181210622. 2018."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0245579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T13:55:10Z","timestamp":1614261310000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0245579"}},"subtitle":[],"editor":[{"given":"Gulistan","family":"Raja","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,2,25]]},"references-count":58,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,2,25]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0245579","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,25]]}}}