SSFD: Self-Supervised Feature Distance Outperforms Conventional MR Image Reconstruction Quality Metrics

作者：Philip B. Adamson, Jeffrey Dominic, Arjun Desai, Christian Bluethgen, Jeff Wood, Ali Syed, Robert D. Boutin, Kathryn J. Stevens, Daniel M. Spielman, Shreyas Vasanawala, John M. Pauly, Akshay Chaudhari, Beliz Gunel · 发表于：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 · 年份：2023 · DOI：10.58530/2022/1870 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Medical Imaging Techniques and Applications、Advanced X-ray and CT Imaging

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.