Autistic Spectrum Disorder Detection and Structural Biomarker Identification Using Self-Attention Model and Individual-Level Morphological Covariance Brain Networks

Abstract

Autism spectrum disorder (ASD) is a range of neurodevelopmental disorders, which brings enormous burdens to the families of patients and society. However, due to the lack of representation of variance for diseases and the absence of biomarkers for diagnosis, the early detection and intervention of ASD are remarkably challenging. In this study, we proposed a self-attention deep learning framework based on the transformer model on structural MR images from the ABIDE consortium to classify ASD patients from normal controls and simultaneously identify the structural biomarkers. In our work, the individual structural covariance networks are used to perform ASD/NC classification via a self-attention deep learning framework, instead of the original structural MR data, to take full advantage of the coordination patterns of morphological features between brain regions. The self-attention deep learning framework based on the transformer model can extract both local and global information from the input data, making it more suitable for the brain network data than the CNN- structural model. Meanwhile, the potential diagnosis structural biomarkers are identified by the self-attention coefficients map. The experimental results showed that our proposed method outperforms most of the current methods for classifying ASD patients with the ABIDE data and achieves a classification accuracy of 72.5% across different sites. Furthermore, the potential diagnosis biomarkers were found mainly located in the prefrontal cortex, temporal cortex, and cerebellum, which may be treated as the early biomarkers for the ASD diagnosis. Our study demonstrated that the self-attention deep learning framework is an effective way to diagnose ASD and establish the potential biomarkers for ASD.

Identification of Young High-Functioning Autism Individuals Based on Functional Connectome Using Graph Isomorphism Network: A Pilot Study

“…Liloia et al (2021) found middle occipital gyrus in GM co-alteration network of ASD [ 53 ]. Wang et al (2021) used the deep learning method and structural covariance network to classify ASD and found salient ROIs in prefrontal regions [ 54 ]. In our experiment, each layer had salient ROIs from the visual network associated with ASD, and more ROIs of the frontoparietal control network became more significant with the depth of layers.…”

Machine learning for autism spectrum disorder diagnosis using structural magnetic resonance imaging: Promising but challenging

“…Grad-CAM heat maps are hierarchical, like CNN's simpleto-complex feature extraction algorithm (Gao et al, 2022). However, in Wang et al (2021), the maps of self-attention coefficients in the first and second layers are similar, indicating a consistent diagnosis. In Leming et al (2021), the authors verified their suggested approach for classifying individuals with ASD and age-, motion-, and intracranial-volume-matched HCs by feeding a CNN the symmetric similarity matrix from regional histograms of estimated GM volumes.…”

“…The F1 score is calculated by averaging the PPV and Sen scores. Therefore, this score takes both FP and FN into account ( Panja et al, 2018 ; Wang et al, 2021 ).…”

“…The prefrontal cortex and cerebellum ( Gao et al, 2022 ; Wang et al, 2021 ) and the temporal cortex ( Wang et al, 2021 ) help classify structural covariance brain networks. Basic conscious motions are physically and functionally linked to the prefrontal cortex, and its abnormality is associated with ASD’s emotional and social domain.…”

“…MBNs that measure intracortical GM similarity are useful in the study of neurological disorders ( Kong et al, 2019 ; Wang et al, 2021 ). The brain can be represented as a single view representation network or as a multi-view representation network ( Graa and Rekik, 2019 ).…”