Lev E. Givon,Laura Jane Mariano,Abraham Schneider,John Irvine
申请号：
US16748717
公开号：
US20200229753A1
申请日:
2020.01.21
申请国别(地区):
US
年份:
2020
代理人:
摘要：
A method of predicting progression of a cognitive state in a subject is disclosed including obtaining a neuroimage of the subject, acquiring a data sample from the neuroimage, selecting a time at which to predict progression of the cognitive state, and performing a calculation on the data sample by a transformation function to determine data associated with multiple cognitive metrics. A method of evaluating a cognitive state of a subject is also disclosed including providing a convolutional neural network, training the convolutional neural network with reference data to construct a transformation function, using the transformation function to predict multiple cognitive metrics from a subject data sample and a selected time, and determining the cognitive state of the subject from the predicted cognitive metrics. A cognitive evaluation system is also disclosed including a memory, a processor, and a cognitive state prediction component configured to program the processor with a transformation function.
