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

DOI

10.2991/978-94-6239-616-6_92How to use a DOI?

Keywords

Dyslexia; Disease Detection; Magnetic Resonance Imaging (MRI); Deep Neural Networks (DNNs)

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.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - D. Karthika
AU  - C. Radhika
PY  - 2026
DA  - 2026/03/31
TI  - MRI-Based Deep Neural Network Framework for Early Dyslexia Detection in Children
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 1251
EP  - 1269
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_92
DO  - 10.2991/978-94-6239-616-6_92
ID  - Karthika2026
ER  -