Meeting Banner
Abstract #0730

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

Xavier Beltran Urbano1,2, Manuel Taso3, Ilya Nasrallah1, John A. Detre1,2, Ze Wang4, and Sudipto Dolui1
1Department of Radiology, University of Pennsylvania, Philadelphia, PA, United States, 2Department of Neurology, University of Pennsylvania, Philadelphia, PA, United States, 3Siemens Medical Solutions, Philadelphia, PA, United States, 4University of Maryland School of Medicine, Maryland, MD, United States

Synopsis

Keywords: Arterial Spin Labelling, Arterial spin labelling, Machine Learning/ Artificial Intelligence, cerebral blood flow (CBF), MRI

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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords