Discriminant Spatial Filtering Method (DSFM) for the identification and analysis of abnormal resting state brain activities
作者：
Highlights：
• Identification of discriminant regions is vital for feature selection.
• Discriminant spatial filtering helps identify abnormal neural activities using fMRI.
• Discriminant spatial projection improves separability and classification accuracy.
• Disruption of DMN and frequent shifts in attention were observed in ADHD patients.
• DSFM classifier achieves a 73.83% classification accuracy over the ADHD200 dataset.
摘要
•Identification of discriminant regions is vital for feature selection.•Discriminant spatial filtering helps identify abnormal neural activities using fMRI.•Discriminant spatial projection improves separability and classification accuracy.•Disruption of DMN and frequent shifts in attention were observed in ADHD patients.•DSFM classifier achieves a 73.83% classification accuracy over the ADHD200 dataset.
论文关键词：Feature selection,Spatial transformation,Projection based learning,rs-fMRI,ADHD
论文评审过程：Received 14 July 2020, Revised 16 March 2021, Accepted 18 April 2021, Available online 24 April 2021, Version of Record 18 May 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115074
