QEI-Net: A Deep learning-based automated quality evaluation index for ASL CBF Maps

Motivation: Arterial Spin Labeling (ASL) cerebral blood flow (CBF) maps can be noisy, which can bias statistical results. Quality control (QC) by visual inspection is subjective and time-consuming. Automated objective QC addresses these limitations, but previous methods lacked consistency across datasets. Goal(s): Develop a deep learning model (QEI-Net) to derive a robust quality evaluation index (QEI) for ASL CBF maps. Approach: We trained QEI-Net on manually rated multi-protocol ASL datasets and compared QEI-Net with both manual ratings and the previous state-of-the-art method. Results: QEI-Net strongly correlated with manual ratings and outperformed the reference approach. This provides reliable and reproducible assessments suitable for large-scale studies. Impact: We propose QEI-Net, a deep learning based automated quality evaluation method for Arterial Spin Labeling (ASL) derived cerebral blood flow images. QEI-Net can enable consistent and reproducible quality assessments and reduce the time burden and subjectivity in studies using ASL.