Synopsis

Psychiatric imaging is struggling with identifying robust biomarkers. Existing approaches do not fully leverage the power of multimodal data, despite evidence that such information is highly informative. We will draw on advances and ideas from fields of supervised learning，data fusion and deep learning, to capture rich information from imaging, cognitive, behavioral and genetic data, in order to integrate a whole picture to deepen our understanding of neural mechanism of cognitive impairment, and to identify replicable biomarkers that are able to predict individual clinical measures and help for differential diagnosis and intervention.