SSFD: Self-Supervised Feature Distance Outperforms Conventional MR Image Reconstruction Quality Metrics
Lists
Only you see this
Abstract
Evaluation of accelerated magnetic resonance imaging (MRI) reconstruction methods is imperfect due to the discordance between quantitative image quality metrics (IQMs) and radiologist-perceived image quality. Self-supervised learning (SSL) is a deep learning (DL) method that has become a popular pre-training tool due to its ability to capture generalizable and domain-specific feature representations of the underlying data without the need for labels. In this study, we derive a data-driven self-supervised feature distance (SSFD) IQM to assess MR image reconstruction quality. We demonstrate that SSFD is more highly correlated to three radiologist’s perceived image quality on DL-based sparse reconstructions than conventional IQMs.
BibTeX
@inproceedings{adamson2023ssfd,
author = {Philip B. Adamson and Jeffrey Dominic and Arjun Desai and Christian Bluethgen and Jeff Wood and Ali Syed and Robert D. Boutin and Kathryn J. Stevens and Daniel M. Spielman and Shreyas Vasanawala and John M. Pauly and Akshay Chaudhari and Beliz Gunel},
title = {{SSFD: Self-Supervised Feature Distance Outperforms Conventional MR Image Reconstruction Quality Metrics}},
booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
year = {2023},
doi = {10.58530/2022/1870},
}Loading related content...