Brain Biomarker Interpretation in ASD Using Deep Learning and fMRI

Abstract

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder. Finding the biomarkers associated with ASD is extremely helpful to understand the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatment. Although Deep Neural Networks (DNNs) have been applied in functional magnetic resonance imaging (fMRI) to identify ASD, understanding the data driven computational decision making procedure has not been previously explored. Therefore, in this work, we address the problem of interpreting reliable biomarkers associated with identifying ASD; specifically, we propose a 2-stage method that classifies ASD and control subjects using fMRI images and interprets the saliency features activated by the classifier. First, we trained an accurate DNN classifier. Then, for detecting the biomarkers, different from the DNN visualization works in computer vision, we take advantage of the anatomical structure of brain fMRI and develop a frequency-normalized sampling method to corrupt images. Furthermore, in the ASD vs. control subjects classification scenario, we provide a new approach to detect and characterize important brain features into three categories. The biomarkers we found by the proposed method are robust and consistent with previous findings in the literature. We also validate the detected biomarkers by neurological function decoding and comparing with the DNN activation maps.

Efficient Interpretation of Deep Learning Models Using Graph Structure and Cooperative Game Theory: Application to ASD Biomarker Discovery

“…The Spearman rank-order correlation coefficient [15] of the importance score ranks of all the ROIs explained by both methods was 0.58. These detected regions were consistent with the previous findings in the literature [2,3]. Also, we used Neurosynth [16] to decode the functional keywords associated with the overlapping biomarkers found by C-SVE and H-SVE (Fig.…”

Dictionary Learning-Based fMRI Data Analysis for Capturing Common and Individual Neural Activation Maps

“…A restricted Boltzmann machine (RBM) and a deep belief network (DBN) were employed for fMRI and structural MRI (sMRI) data analysis in [16], and the interpretation of the learned deep network features was attempted using their nonlinear embeddings. Convolutional neural networks (CNNs) were adopted for predicting Alzheimer's disease and autism spectrum disorder (ASD) with good prediction performances [17], [18]. In order to interpret the learned biomarkers, the difference in prediction performance was analyzed when a region of interest (ROI) was corrupted in the input data [18], or a direct sensitivity analysis was performed to the learned network [19].…”

Going Deep in Medical Image Analysis: Concepts, Methods, Challenges, and Future Directions

“…Relating to the anatomical region of Brain, Li et al [228] used deep learning to detect Autism Spectrum disorder (ASD) in functional Magnetic Resonance Imaging (fMRI). They developed a 2-stage neural network method.…”