基于脑结构像的精神分裂症机器学习分类

将机器学习应用于精神疾患的临床和基础研究是近年来的趋势。研究者将机器学习应用于精神分裂症患者及高危人群的T1加权像和弥散张量成像的脑影像数据中, 为了解疾病的生理病理学机制提供帮助。回顾以往研究发现额叶及颞叶的脑结构特征具有较高的区分能力, 行为数据和脑影像数据结合的分类效果优于单模态数据。现阶段研究存在样本量不足和泛化能力欠缺的局限, 未来研究应注意扩大样本量、制定标准化的分类方法, 从而进一步探究机器学习在精神疾患中的作用。

The classification of schizophrenia based on brain structural features: A machine learning approach

Machine learning is a promising approach for mental disorders. In recent years, machine learning based on T1 weighted imaging and Diffusion Tensor Imaging (DTI) data has been used to investigate the psychopathology and underlying mechanisms of schizophrenia patients and high-risk population. The findings from the previous literature suggest that structural features of frontal lobe and temporal lobe can improve classification performance. In addition, the combination of behavioural performances and the features of brain structure is superior to the single-modality structural images on classification accuracy. However, the existing empirical studies classifying schizophrenia patients or high-risk population from controls are limited in sample size and generalization ability.