机器学习结合fMRI在抑郁症诊断中的研究进展

Current progress of machine learning combined with functional magnetic resonance imaging in depression’s diagnosis

抑郁症是严重危害人类健康的精神障碍性疾病之一,其发病率高且病情易反复。该病的诊断主要依据《精神疾病诊断与统计手册第五版》(diagnostic and statistical manual of mental disorders,fifth edition,DSM-5)及国际疾病与相关健康问题统计分类第10版(International Statistical Classification of Diseases and Related Health Problems 10th Revision,ICD-10)。目前,功能磁共振成像与机器学习结合的方法有望发现特异性标志物,为抑郁症的诊断提供客观的影像学依据。作者介绍机器学习与功能磁共振成像(包括任务态功能磁共振成像、静息态功能磁共振成像、动脉自旋标记及扩散张量成像)结合的方法在抑郁症诊断中的研究进展。

Depression is one of psychiatric disorders with serious negative health outcomes,and it is of high incidence and easily recurrence.As for its diagnosis,it relies on Diagnostic and Statistical Manual of Mental Disorders,fifth edition(DSM-5)and International Statistical Classification of Diseases and Related Health Problems 10th Revision(ICD-10).While combining fMRI with machine learning is potential to search for specific markers which provide objective imaging evidence for its diagnosis.Therefore,this review introduces current progress about task-state functional magnetic resonance imaging(task-state fMRI),rest-state functional magnetic resonance imaging(rest-state fMRI),arterial spin labeling(ASL)and diffusion tensor imaging(DTI)respectively combined with machine learning in depression’s diagnosis.