Dyslexia detection using 3D convolutional neural networks and functional magnetic resonance imaging

Vista sencilla de ítem
dc.contributor.authorZahia, Sofia
dc.contributor.authorGarcía-Zapirain, Begoña
dc.contributor.authorSaralegui, Ibone
dc.contributor.authorFernandez-Ruanova, Begoña
dc.date.accessioned2024-11-14T11:37:36Z
dc.date.available2024-11-14T11:37:36Z
dc.date.issued2020-12
dc.date.updated2024-11-14T11:37:36Z
dc.description.abstractBackground and Objectives: Dyslexia is a disorder of neurological origin which affects the learning of those who suffer from it, mainly children, and causes difficulty in reading and writing. When undiagnosed, dyslexia leads to intimidation and frustration of the affected children and also of their family circles. In case no early intervention is given, children may reach high school with serious achievement gaps. Hence, early detection and intervention services for dyslexic students are highly important and recommended in order to support children in developing a positive self-esteem and reaching their maximum academic capacities. This paper presents a new approach for automatic recognition of children with dyslexia using functional magnetic resonance Imaging. Methods: Our proposed system is composed of a sequence of preprocessing steps to retrieve the brain activation areas during three different reading tasks. Conversion to Nifti volumes, adjustment of head motion, normalization and smoothing transformations were performed on the fMRI scans in order to bring all the subject brains into one single model which will enable voxels comparison between each subject. Subsequently, using Statistical Parametric Maps (SPMs), a total of 165 3D volumes containing brain activation of 55 children were created. The classification of these volumes was handled using three parallel 3D Convolutional Neural Network (3D CNN), each corresponding to a brain activation during one reading task, and concatenated in the last two dense layers, forming a single architecture devoted to performing optimized detection of dyslexic brain activation. Additionally, we used 4-fold cross validation method in order to assess the generalizability of our model and control overfitting. Results: Our approach has achieved an overall average classification accuracy of 72.73%, sensitivity of 75%, specificity of 71.43%, precision of 60% and an F1-score of 67% in dyslexia detection. Conclusions: The proposed system has demonstrated that the recognition of dyslexic children is feasible using deep learning and functional magnetic resonance Imaging when performing phonological and orthographic reading tasks.en
dc.description.sponsorshipThis project has been partially funded by the Basque government , and eVida certified Group IT905-16 for publication fees and grants for research projects of the Health Department (2019222044 and 2018222002). The authors would like to thank Osatek (Mag- netic Resonance Unit, Galdakao, Spain) for the data provided in order to carry out this work. Acknowledgment to Basque country government that partially funded this project with IT905-16 , 2019222044 and 2018222002 grantsen
dc.identifier.citationZahia, S., Garcia-Zapirain, B., Saralegui, I., & Fernandez-Ruanova, B. (2020). Dyslexia detection using 3D convolutional neural networks and functional magnetic resonance imaging. Computer Methods and Programs in Biomedicine, 197. https://doi.org/10.1016/J.CMPB.2020.105726
dc.identifier.doi10.1016/J.CMPB.2020.105726
dc.identifier.eissn1872-7565
dc.identifier.issn0169-2607
dc.identifier.urihttp://hdl.handle.net/20.500.14454/1862
dc.language.isoeng
dc.publisherElsevier Ireland Ltd
dc.rights© 2020 The Author(s)
dc.subject.other3D Convolutional Neural Networks
dc.subject.otherComputer-aided diagnosis (CAD)
dc.subject.otherDeep learning
dc.subject.otherDyslexia
dc.subject.otherFunctional magnetic resonance Imaging
dc.titleDyslexia detection using 3D convolutional neural networks and functional magnetic resonance imagingen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.titleComputer Methods and Programs in Biomedicine
oaire.citation.volume197
oaire.licenseConditionhttps://creativecommons.org/licenses/by-nc-nd/4.0/
oaire.versionVoR
Ficheros en el ítem
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
zahia_dyslexia_2020.pdf
Tamaño:
1.72 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos