Construction of a confounder-free clinical MRI dataset in the Mass General Brigham system for classification of Alzheimer's disease

作者：

Highlights：

• Applied deep learning to a large database of clinical brain MRIs

• Alzheimer's, Mild Cognitive Impairment, and controls labeled using medication history

• Describe unique algorithms to isolate datasets without confounding factors

• Achieved >0.80 AUROC when distinguishing AD/MCI from controls

摘要

•Applied deep learning to a large database of clinical brain MRIs•Alzheimer's, Mild Cognitive Impairment, and controls labeled using medication history•Describe unique algorithms to isolate datasets without confounding factors•Achieved >0.80 AUROC when distinguishing AD/MCI from controls

论文关键词：Deep learning,Magnetic resonance imaging,Alzheimer's disease,Mild cognitive impairment,Data matching,Confounding factors

论文评审过程：Received 20 August 2021, Revised 21 February 2022, Accepted 16 April 2022, Available online 27 April 2022, Version of Record 30 April 2022.

论文官网地址：https://doi.org/10.1016/j.artmed.2022.102309