Abstract
Individuals with dyslexia exhibit altered brain connectivity during reading-related tasks, but temporal dynamics have been understudied. We integrate Dynamic Functional Connectivity analysis with SHAP-based explainable AI on task-based fMRI, achieving 0.758 classification accuracy with XGBoost and revealing gender-stratified differences and key discriminative connectivity involving language, parietal, default mode, salience, and cognitive control networks.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/MLCN_2026_020.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=5WxIDLGJbS
BibTex
@InProceedings{ThoBle_Toward_MICCAISAT2026,
author = { Thomas, Blessy AND Saleh, Moutaz AND Al Maadeed, Somaya AND Akbari, Younes AND Kunhoth, Jayakanth},
title = { { Toward Personalized Dyslexia Classification via Dynamic Functional Connectivity and Explainable AI } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17255},
month = {pending},
page = {pending}
}