The reliability of a deep learning model in clinical out-of-distribution MRI data: A multicohort study
Medical Image Analysis(2020)
摘要
•The performance of a deep learning model for visual ratings of atrophy was investigated in clinical out-of-distribution data.•Model is more robust on unseen clinical data when trained on more heterogeneous training data.•Model trained on research data with harmonized protocols perform well in cohorts where data is acquired with similar scanning parameters but fails in others.
更多查看译文
关键词
Neuroimaging,Deep learning,Domain shift,Clinical application
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要