Clinical evaluation of deep learning accelerated 3D magnetic resonance cholangiopancreatography at 1.5 T and 3 T.
Authors
Affiliations (8)
Affiliations (8)
- Wentworth-Douglass Hospital, Enterprise Service Group - Radiology at Mass General Brigham, Dover, NH, USA; Department of Radiology, University of Turku, Turku, Finland. Electronic address: [email protected].
- Department of Radiology, Massachusetts General Hospital at Mass General Brigham, Boston, MA, USA.
- GE HealthCare, Boston, MA, USA.
- GE HealthCare, Rochester, MN, USA.
- GE HealthCare, Waukesha, WI, USA.
- Department of Radiology, Massachusetts General Hospital at Mass General Brigham, Boston, MA, USA; Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School, Charlestown, MA, USA.
- Department of Radiology, Women's and Brigham's Hospital at Mass General Brigham, Boston, MA, USA.
- Department of Radiology, University of Turku, Turku, Finland.
Abstract
Routine clinical 3D magnetic resonance cholangiopancreatography (MRCP) is typically performed either as lower resolution breath-hold (BH) acquisition or higher resolution triggered navigator breathing (NAV) acquisition with a longer acquisition time, potentially limiting clinically applicability. Our aim was to evaluate the clinical feasibility of MRCP obtained using a new deep learning acceleration approach, Sonic DL<sup>TM</sup> 3D (SDL), as compared to the standard 3D MRCP.. Sixty-four and 32 patients underwent 1.5 T and 3 T MRCP scans, respectively. The standard 3D MRCP was obtained using a BH and NAV. Two SDL MRCP acquisitions for each magnetic field were performed with BH and scan times of 11-17 s, utilizing the SDL based acquisition and reconstruction technique. Three radiologists visually evaluated all MRCP datasets for 4 different features: overall image quality, image noise, image sharpness and artifacts. Differences were compared using the Wilcoxon matched-pairs signed rank and chi-squared tests. At both field strengths (1.5 T and 3 T) the proportion of overall image quality scores of 3 or higher (good, very good and excellent) and proportion of cases with reduced artifacts were better (p < 0.05) for both SDL MRCP acquisitions compared to the standard with NAV or BH. However, SDL MRCP was not superior to the standard MRCP technique for all evaluated feature categories and scoring varied between readers. SDL MRCP demonstrated improved image quality consistency and scan time, however, variations between radiologists in quality scores were present, underlying the need for future development and validation.