Using Deep Learning to Accelerate Knee MRI at 3 T: Results of an Interchangeability Study

Michael P. Recht, Jure Zbontar, Daniel K. Sodickson, Florian Knoll, Nafissa Yakubova, Anuroop Sriram, Tullie Murrell, Aaron Defazio, Michael Rabbat, Leon Rybak, Mitchell Kline, Gina Ciavarra, Erin F. Alaia, Mohammad Samim, William R. Walter, Dana J. Lin, Yvonne W. Lui, Matthew Muckley, Zhengnan Huang, Patricia JohnsonRuben Stern, C. Lawrence Zitnick

    Research output: Contribution to journalArticlepeer-review

    Abstract

    OBJECTIVE. Deep learning (DL) image reconstruction has the potential to disrupt the current state of MRI by significantly decreasing the time required for MRI examinations. Our goal was to use DL to accelerate MRI to allow a 5-minute comprehensive examination of the knee without compromising image quality or diagnostic accuracy. MATERIALS AND METHODS. A DL model for image reconstruction using a variational network was optimized. The model was trained using dedicated multisequence training, in which a single reconstruction model was trained with data from multiple sequences with different contrast and orientations. After training, data from 108 patients were retrospectively undersampled in a manner that would correspond with a net 3.49-fold acceleration of fully sampled data acquisition and a 1.88-fold acceleration compared with our standard twofold accelerated parallel acquisition. An interchangeability study was performed, in which the ability of six readers to detect internal derangement of the knee was compared for clinical and DL-accelerated images. RESULTS. We found a high degree of interchangeability between standard and DL-accelerated images. In particular, results showed that interchanging the sequences would produce discordant clinical opinions no more than 4% of the time for any feature evaluated. Moreover, the accelerated sequence was judged by all six readers to have better quality than the clinical sequence. CONCLUSION. An optimized DL model allowed acceleration of knee images that performed interchangeably with standard images for detection of internal derangement of the knee. Importantly, readers preferred the quality of accelerated images to that of standard clinical images.

    Original languageEnglish (US)
    Pages (from-to)1421-1429
    Number of pages9
    JournalAmerican Journal of Roentgenology
    Volume215
    Issue number6
    DOIs
    StatePublished - Dec 2020

    Keywords

    • Acceleration
    • Deep learning
    • Internal derangement
    • Knee
    • MRI

    ASJC Scopus subject areas

    • Radiology Nuclear Medicine and imaging

    Fingerprint

    Dive into the research topics of 'Using Deep Learning to Accelerate Knee MRI at 3 T: Results of an Interchangeability Study'. Together they form a unique fingerprint.

    Cite this