MRI-Based Deep Neural Network Framework for Early Dyslexia Detection in Children

Read full text Summarise with VIRAT
Authors: D. Karthika, C. Radhika
Cited by: 0
References: 22

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

People with dyslexia struggle to understand and use written language because of a neurological impairment.Dyslexic children and their families endure stigma and discrimination when the disorder goes untreated.Children may face significant performance differences without intervention by the time they reach high school.Supporting children in building good self-esteem and attaining their best academic potential requires early identification and intervention programs for dyslexic pupils.This research addressed that need by developing a reliable DD model to aid doctors in using functional MRI to identify dyslexic patients.The paper constructed a model using a deep convolutional neural network to extract vital information from the MRI images.Using Deep Neural Networks (DNNs) in conjunction with Magnetic Resonance Imaging (MRI) to forecast Dyslexia Detection in Children (DNN-MRI-DD) is described in this paper.Early diagnosis is essential to ensure that children with dyslexia (DC) have access to the best possible chances for schooling.On the other hand, a lightweight, practical framework for diagnosing dyslexia in youngsters is also needed.Consequently, the proposed research is all about a dyslexia detection framework.The suggested framework includes classification models, feature extraction, and image processing.To evaluate performance, the researchers made use of the dyslexia dataset, which is publically accessible.The trial results proved that the suggested DNN-MRI-DDP model could successfully identify dyslexic children using minimal computer resources.With mean average precisions of 98.2, 97.3, accuracy, F1-Score, and recall of 96.8, 96.5, and 98.4, respectively, the suggested framework surpassed the baseline models in the experimental investigation.

Fields of Study & Subjects

Reading and Literacy Development Advanced Neural Network Applications Artificial Intelligence in Healthcare

Publication details

Journal / source
Advances in intelligent systems research/Advances in Intelligent Systems Research
Pages
1251–1269
Publication date
1 April 2026
Language
EN
Document type
Book chapter