Abstract #4697

Comparison of Quality Assessment Methods for Deep-Learning-Based MR Image Reconstruction

Mohammadhassan Izady Yazdanabady ^1,2, Kyoko Fujimoto³, Benjamin Paul Berman³, Matthew S Rosen^4,5,6, Neha Koonjoo^4,5, Bo Zhu^4,5,6, Christian George Graff³, and Aria Pezeshk³

¹School of Computing, Informatics, and Decision Systems Engineering, Arizona State Univerisity, Tempe, AZ, United States, ²Department of Neurosurgery, Barrow Neurological Institute, St. Joseph’s Hospital and Medical Center, Phoenix, AZ, United States, ³Center for Devices and Radiological Health, US Food and Drug Administration, Silver Spring, MD, United States, ⁴A. A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA, United States, ⁵Harvard Medical School, Boston, MA, United States, ⁶Department of Physics, Harvard University, Cambridge, MA, United States

The proper methodology to perform rigorous quantitative task-based assessment of image quality for deep learning based MR reconstruction methods has not been devised yet. In this study we reconstructed T₁-weighted brain images using neural networks trained with five different datasets, and explored the consistency and relationship between rankings of image quality using three different assessment metrics and FreeSurfer-based quantitative analysis. Our study indicates that assessment of image quality for a data-driven reconstruction algorithm may require several types of analysis including using different image quality assessment metrics and their agreement with clinically relevant tasks.

This abstract and the presentation materials are available to members only; a login is required.

Join Here