Application of Artificial Intelligence in the MRI Classification Task of Human Brain Neurological and Psychiatric Diseases: A Scoping Review.

Zhao Zhang,Yong Xu,Xiaoying Tang,Guangfei Li

doi:10.3390/diagnostics11081402

Abstract

Artificial intelligence (AI) for medical imaging is a technology with great potential. An in-depth understanding of the principles and applications of magnetic resonance imaging (MRI), machine learning (ML), and deep learning (DL) is fundamental for developing AI-based algorithms that can meet the requirements of clinical diagnosis and have excellent quality and efficiency. Moreover, a more comprehensive understanding of applications and opportunities would help to implement AI-based methods in an ethical and sustainable manner. This review first summarizes recent research advances in ML and DL techniques for classifying human brain magnetic resonance images. Then, the application of ML and DL methods to six typical neurological and psychiatric diseases is summarized, including Alzheimer’s disease (AD), Parkinson’s disease (PD), major depressive disorder (MDD), schizophrenia (SCZ), attention-deficit/hyperactivity disorder (ADHD), and autism spectrum disorder (ASD). Finally, the limitations of the existing research are discussed, and possible future research directions are proposed.

Highlights

Magnetic resonance imaging (MRI), as a non-invasive medical imaging technique, has been widely used in the early detection, diagnosis, and treatment of diseases [1]
The search string used in this study was (“Alzheimer’s Disease” or “Parkinson’s Disease” or “Major Depressive Disorder” or “Schizophrenia” or “Attention-Deficit/Hyperactivity Disorder” or “Autism Spectrum Disorder” or “Alzheimer’s disease (AD)” or “Parkinson’s disease (PD)” or “major depressive disorder (MDD)” or “SCZ” or “attention-deficit/hyperactivity disorder (ADHD)” or “autism spectrum disorder (ASD)”) and (“machine learning” or “deep learning”) and (“MRI”)
After removing duplicates and reviewing the abstracts of these papers, 625 papers were selected for full-text review

Summary

Introduction

Magnetic resonance imaging (MRI), as a non-invasive medical imaging technique, has been widely used in the early detection, diagnosis, and treatment of diseases [1]. In the study of the human brain, MRI can provide information about the anatomical structure of the brain, and provides comprehensive multi-parameter information about the function and metabolism [2]. Structural magnetic resonance imaging (sMRI) and functional magnetic resonance imaging (fMRI) have respectively made great progress in the study of human brain structure and function, due to their high spatial resolution [3]. AI (artificial intelligence) in MRI is a technology with great potential. Based on the principles and application of ML (machine learning), DL (deep learning) is fundamental for developing AI-based algorithms that can achieve improved results, quality, and efficiency [4].

Methods

Results

Conclusion