Dilated 3D Convolutional Neural Networks for Brain MRI Data Classification

Zijian Wang,Qianzi Shen,Lei Cao,Yaoru Sun

doi:10.1109/access.2019.2941912

Abstract

Benefiting from the research of machine learning (ML) and deep learning(DL), multivariate methods based on ML and DL have been the mainstream and successful analysis methods in Neural Engineering or Neuroimaging research, for example, assisting diagnosis based on brain Magnetic Resonance Imaging (MRI). However, many existing methods based on traditional ML methods cannot sufficiently extract discriminative features, especially feature patterns across long-distance brain areas, resulting in unsatisfactory classification performance. Designing an effective and robust classifier for different MRI images remains a challenge. In this paper, we introduced dilated 3D CNN method for classifying 3D MRI images combining CNN structure and dilated convolution with a small number of feature maps. We also presented a methodology framework based on dilated 3D CNN method, which can classify both single MRI images and image sequences. Our method and framework were evaluated on the structural MRI images of ADHD-200 dataset and fMRI images of a Schizophrenia dataset, demonstrating better performances than some other state-of-the-art methods.

Highlights

In the last two decades, neuroscience and neuroimaging researchers relied on Univariate analysis, which compares patients against healthy subjects and finds anatomical or functional differences at a group level
In this method, dilated convolution was used for recognizing patterns across longdistance brain areas in both structural and functional Magnetic Resonance Imaging (MRI) images
A methodology framework based on dilated 3D Convolutional Neural Network (CNN) method was presented, including data preprocessing, data balancing, single images classifying, and prediction labels aggregating

Summary

Introduction

In the last two decades, neuroscience and neuroimaging researchers relied on Univariate analysis, which compares patients against healthy subjects and finds anatomical or functional differences at a group level. These simple and interpretable methods have two defects. Univariate analysis methods based on the assumption that activities within different brain regions or voxels are independent. This assumption is not in accord with present findings of brain function, which translate some brain function into networklevel activities [4]–[6].

Methods

Results

Conclusion