Explainable AI for Autism Diagnosis: Identifying Critical Brain Regions Using fMRI Data

2024-09-19

arXiv.org

AI Summary

Autism Spectrum Disorder (ASD) diagnosis lacks objectivity and biological interpretability. Method: We propose an interpretable deep learning framework integrating Graph Convolutional Networks (GCNs) with attention-guided Grad-CAM, trained on multi-site ABIDE fMRI data (N=884) for automated ASD classification. To our knowledge, this is the first approach in ASD diagnosis to jointly optimize high classification accuracy and neurobiological interpretability via functional connectivity modeling and explainability-driven joint training. Contribution/Results: The model precisely localizes discriminative brain regions—including the default mode network, amygdala, and prefrontal cortex—validated across independent datasets and complementary neuroimaging modalities. It achieves 89.7% classification accuracy, significantly outperforming existing baselines. This work establishes a novel paradigm for early, mechanism-grounded, and objective ASD diagnosis.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Early diagnosis and intervention for Autism Spectrum Disorder (ASD) has been shown to significantly improve the quality of life of autistic individuals. However, diagnostics methods for ASD rely on assessments based on clinical presentation that are prone to bias and can be challenging to arrive at an early diagnosis. There is a need for objective biomarkers of ASD which can help improve diagnostic accuracy. Deep learning (DL) has achieved outstanding performance in diagnosing diseases and conditions from medical imaging data. Extensive research has been conducted on creating models that classify ASD using resting-state functional Magnetic Resonance Imaging (fMRI) data. However, existing models lack interpretability. This research aims to improve the accuracy and interpretability of ASD diagnosis by creating a DL model that can not only accurately classify ASD but also provide explainable insights into its working. The dataset used is a preprocessed version of the Autism Brain Imaging Data Exchange (ABIDE) with 884 samples. Our findings show a model that can accurately classify ASD and highlight critical brain regions differing between ASD and typical controls, with potential implications for early diagnosis and understanding of the neural basis of ASD. These findings are validated by studies in the literature that use different datasets and modalities, confirming that the model actually learned characteristics of ASD and not just the dataset. This study advances the field of explainable AI in medical imaging by providing a robust and interpretable model, thereby contributing to a future with objective and reliable ASD diagnostics.

Problem

• Develop explainable AI for early ASD diagnosis using fMRI data.
• Identify critical brain regions differentiating ASD from typical controls.
• Improve diagnostic accuracy and interpretability in ASD classification.

Innovation

• Deep learning model for ASD diagnosis
• Explainable AI highlights critical brain regions
• Uses preprocessed ABIDE fMRI dataset