Resting state fMRI functional connectivity-based classification using a convolutional neural network architecture

TL;DR

This paper introduces a novel convolutional neural network architecture called CCNN for classifying resting state fMRI connectomes, demonstrating its effectiveness on simulated and real datasets, and its ability to integrate multiple connectivity metrics.

Contribution

The paper presents the first application of a connectome-convolutional neural network (CCNN) for resting state fMRI classification, capable of combining diverse connectivity metrics.

Findings

CCNN effectively distinguishes between subject groups.

Models with multiple connectivity metrics outperform single-metric models.

CCNN can be adapted for various connectome-based classification and regression tasks.

Abstract

Machine learning techniques have become increasingly popular in the field of resting state fMRI (functional magnetic resonance imaging) network based classification. However, the application of convolutional networks has been proposed only very recently and has remained largely unexplored. In this paper we describe a convolutional neural network architecture for functional connectome classification called connectome-convolutional neural network (CCNN). Our results on simulated datasets and a publicly available dataset for amnestic mild cognitive impairment classification demonstrate that our CCNN model can efficiently distinguish between subject groups. We also show that the connectome-convolutional network is capable to combine information from diverse functional connectivity metrics and that models using a combination of different connectivity descriptors are able to outperform classifiers using only one metric. From this flexibility follows that our proposed CCNN model can be easily adapted to a wide range of connectome based classification or regression tasks, by varying which connectivity descriptor combinations are used to train the network.