Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (22): 57-68.DOI: 10.3778/j.issn.1002-8331.2303-0324

• Research Hotspots and Reviews • Previous Articles     Next Articles

Survey of Artificial Intelligence in Functional Magnetic Resonance Imaging Data for Autism

GU Jian, QIAN Yurong, WANG Lanlan, HU Yue, CHEN Jiaying, LENG Hongyong, MA Mengnan   

  1. 1.School of Software, Xinjiang University, Urumqi 830091, China
    2.Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region, Xinjiang University, Urumqi 830046, China
    3.Key Laboratory of Software Engineering, Xinjiang University, Urumqi 830000, China
    4.School of Computer Science, Central South University, Changsha 410083, China
    5.School of Computer Science, Beijing Institute of Technology, Beijing 100081, China
  • Online:2023-11-15 Published:2023-11-15



  1. 1.新疆大学 软件学院,乌鲁木齐 830091
    2.新疆大学 新疆维吾尔自治区信号检测与处理重点实验室,乌鲁木齐 830046
    3.新疆大学 软件工程重点实验室,乌鲁木齐 830000
    4.中南大学 计算机学院,长沙 410083
    5.北京理工大学 计算机学院,北京 100081

Abstract: Autism spectrum disorder is a serious mental disorder that occurs in childhood and affects the social and daily life of individuals. In recent years, artificial intelligence diagnosis of autism based on functional magnetic resonance imaging(fMRI) data has become a current research hotspot. Advanced technologies such as machine learning and deep learning have been used in the research of intelligent assisted diagnosis of autism, aiming to improve the efficiency and accuracy of diagnosis as well as to explore the pathogenesis. This paper firstly introduces the background, importance and challenges of intelligent diagnosis of autism. Secondly, this paper reviews the progress of intelligent diagnosis-related technologies in the classification and identification of autism in the past five years, summarizes and analyzes the characteristics and limitations of different methods of intelligent diagnosis from two aspects:machine learning and deep learning. Finally, this paper discusses the urgent problems and future research trends of intelligent diagnosis of autism, and provides guidance for early diagnosis and clinical application of autism.

Key words: artificial intelligence, autism spectrum disorder, functional magnetic resonance imaging, machine learning, deep learning

摘要: 自闭症谱系障碍是一种严重的精神障碍疾病,多发于儿童时期,影响个体的社交和日常生活。近年来,基于功能磁共振成像(functional magnetic resonance imaging,fMRI)数据的自闭症人工智能诊断成为研究热点。机器学习、深度学习等先进技术已经被用于自闭症的智能辅助诊断研究中,旨在提高诊断的效率、准确性以及探索发病机制。首先介绍了自闭症智能诊断的背景、重要意义和面临的挑战;其次回顾了近5年智能诊断相关技术在自闭症分类识别中的进展,从机器学习和深度学习两方面总结、分析智能诊断不同方法的特点和局限性;最后探讨了自闭症智能诊断亟需解决的问题及未来研究趋势,为自闭症早期诊断和临床应用提供指导和参考。

关键词: 人工智能, 自闭症谱系障碍, 功能磁共振成像, 机器学习, 深度学习