Interpretable Learning Approaches in Resting-State Functional Connectivity Analysis: The Case of Autism Spectrum Disorder.

Computational and Mathematical Methods in Medicine
Jinlong HuPing Li

Abstract

Deep neural networks have recently been applied to the study of brain disorders such as autism spectrum disorder (ASD) with great success. However, the internal logics of these networks are difficult to interpret, especially with regard to how specific network architecture decisions are made. In this paper, we study an interpretable neural network model as a method to identify ASD participants from functional magnetic resonance imaging (fMRI) data and interpret results of the model in a precise and consistent manner. First, we propose an interpretable fully connected neural network (FCNN) to classify two groups, ASD versus healthy controls (HC), based on input data from resting-state functional connectivity (rsFC) between regions of interests (ROIs). The proposed FCNN model is a piecewise linear neural network (PLNN) which uses piecewise linear function LeakyReLU as its activation function. We experimentally compared the FCNN model against widely used classification models including support vector machine (SVM), random forest, and two new classes of deep neural network models in a large dataset containing 871 subjects from ABIDE I database. The results show the proposed FCNN model achieves the highest classification accuracy. S...Continue Reading

References

Aug 16, 2014·PloS One·Sylvain TakerkartLiva Ralaivola
Oct 18, 2016·Brain Informatics·Bokai CaoPhilip S Yu
Oct 17, 2017·NeuroImage. Clinical·Anibal Sólon HeinsfeldFelipe Meneguzzi
Feb 20, 2018·Neuroinformatics·Runa BhaumikDulal K Bhaumik
Jul 13, 2018·Frontiers in Human Neuroscience·Xia-An BiJianhua Dai
Feb 23, 2019·Frontiers in Neuroinformatics·David N KennedyMatt Travers

❮ Previous
Next ❯

Citations

Jun 27, 2021·Journal of Neuroscience Methods·Ming XuJing Sui

❮ Previous
Next ❯

Software Mentioned

Configurable Pipeline for the Analysis of Connectomes ( CPAC )
BrainNetCNN
ABIDE
AAL
AAL atlas
ASD
DiagNet

Related Concepts

Related Feeds

Autism

Autism spectrum disorder is associated with challenges with social skills, repetitive behaviors, and often accompanied by sensory sensitivities and medical issues. Here is the latest research on autism.