FaithfulNet: An explainable deep learning framework for autism diagnosis using structural MRI

Title

FaithfulNet: An explainable deep learning framework for autism diagnosis using structural MRI

Creator

Sujana, D. Swainson; Augustine, D. Peter

Description

Explainable Artificial Intelligence (XAI) can decode the black box models, enhancing trust in clinical decision-making. XAI makes the predictions of deep learning models interpretable, transparent, and trustworthy. This study employed XAI techniques to explain the predictions made by a deep learning-based model for diagnosing autism and identifying the memory regions responsible for children's academic performance. This study utilized publicly available sMRI data from the ABIDE-II repository. First, a deep learning model, FaithfulNet, was developed to aid in the diagnosis of autism. Next, gradient-based class activation maps and the SHAP gradient explainer were employed to generate explanations for the model's predictions. These explanations were integrated to develop a novel and faithful visual explanation, Faith_CAM. Finally, this faithful explanation was quantified using the pointing game score and analyzed with cortical and subcortical structure masks to identify the impaired brain regions in the autistic brain. This study achieved a classification accuracy of 99.74% with an AUC value of 1. In addition to facilitating autism diagnosis, this study assesses the degree of impairment in memory regions responsible for the children's academic performance, thus contributing to the development of personalized treatment plans. 2025 Elsevier B.V.

Source

Brain Research;Volume;1866;Issue;;Article No.;149904;

Date

01-01-2025

Publisher

Elsevier B.V.

Subject

Autism diagnosis; Grad_CAM; SHAP; sMRI; XAI

Coverage

Sujana D.S., Department of Computer Science, Christ (Deemed to be University), Karnataka, Bangalore, 560 029, India; Augustine D.P., Department of Computer Science, Christ (Deemed to be University), Karnataka, Bangalore, 560 029, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISSN: 68993; CODEN: BRREA

Format

online

Language

English

Type

Article

Identifier

https://doi.org/10.1016/j.brainres.2025.149904

https://www.scopus.com/pages/publications/105014541873?origin=resultslist