S Bash1, L Wang2, C Airriess3, G Zaharchuk4, E Gong2, A Shankaranarayanan2, L N Tanenbaum5,6. 1. From the RadNet Inc (S.B., L.N.T.), Los Angeles, California suzie.bash@radnet.com. 2. Subtle Medical (L.W., E.G., A.S.), Menlo Park, California. 3. Cortechs.ai. (C.A.), San Diego, California. 4. Stanford University Medical Center (G.Z.), Stanford, California. 5. From the RadNet Inc (S.B., L.N.T.), Los Angeles, California. 6. Lenox Hill Radiolog (L.N.T.), New York, New York.
Abstract
BACKGROUND AND PURPOSE: In this prospective, multicenter, multireader study, we evaluated the impact on both image quality and quantitative image-analysis consistency of 60% accelerated volumetric MR imaging sequences processed with a commercially available, vendor-agnostic, DICOM-based, deep learning tool (SubtleMR) compared with that of standard of care. MATERIALS AND METHODS: Forty subjects underwent brain MR imaging examinations on 6 scanners from 5 institutions. Standard of care and accelerated datasets were acquired for each subject, and the accelerated scans were enhanced with deep learning processing. Standard of care, accelerated scans, and accelerated-deep learning were subjected to NeuroQuant quantitative analysis and classified by a neuroradiologist into clinical disease categories. Concordance of standard of care and accelerated-deep learning biomarker measurements were assessed. Randomized, side-by-side, multiplanar datasets (360 series) were presented blinded to 2 neuroradiologists and rated for apparent SNR, image sharpness, artifacts, anatomic/lesion conspicuity, image contrast, and gray-white differentiation to evaluate image quality. RESULTS: Accelerated-deep learning was statistically superior to standard of care for perceived quality across imaging features despite a 60% sequence scan-time reduction. Both accelerated-deep learning and standard of care were superior to accelerated scans for all features. There was no difference in quantitative volumetric biomarkers or clinical classification for standard of care and accelerated-deep learning datasets. CONCLUSIONS: Deep learning reconstruction allows 60% sequence scan-time reduction while maintaining high volumetric quantification accuracy, consistent clinical classification, and what radiologists perceive as superior image quality compared with standard of care. This trial supports the reliability, efficiency, and utility of deep learning-based enhancement for quantitative imaging. Shorter scan times may heighten the use of volumetric quantitative MR imaging in routine clinical settings.
BACKGROUND AND PURPOSE: In this prospective, multicenter, multireader study, we evaluated the impact on both image quality and quantitative image-analysis consistency of 60% accelerated volumetric MR imaging sequences processed with a commercially available, vendor-agnostic, DICOM-based, deep learning tool (SubtleMR) compared with that of standard of care. MATERIALS AND METHODS: Forty subjects underwent brain MR imaging examinations on 6 scanners from 5 institutions. Standard of care and accelerated datasets were acquired for each subject, and the accelerated scans were enhanced with deep learning processing. Standard of care, accelerated scans, and accelerated-deep learning were subjected to NeuroQuant quantitative analysis and classified by a neuroradiologist into clinical disease categories. Concordance of standard of care and accelerated-deep learning biomarker measurements were assessed. Randomized, side-by-side, multiplanar datasets (360 series) were presented blinded to 2 neuroradiologists and rated for apparent SNR, image sharpness, artifacts, anatomic/lesion conspicuity, image contrast, and gray-white differentiation to evaluate image quality. RESULTS: Accelerated-deep learning was statistically superior to standard of care for perceived quality across imaging features despite a 60% sequence scan-time reduction. Both accelerated-deep learning and standard of care were superior to accelerated scans for all features. There was no difference in quantitative volumetric biomarkers or clinical classification for standard of care and accelerated-deep learning datasets. CONCLUSIONS: Deep learning reconstruction allows 60% sequence scan-time reduction while maintaining high volumetric quantification accuracy, consistent clinical classification, and what radiologists perceive as superior image quality compared with standard of care. This trial supports the reliability, efficiency, and utility of deep learning-based enhancement for quantitative imaging. Shorter scan times may heighten the use of volumetric quantitative MR imaging in routine clinical settings.
Authors: Vegard Antun; Francesco Renna; Clarice Poon; Ben Adcock; Anders C Hansen Journal: Proc Natl Acad Sci U S A Date: 2020-05-11 Impact factor: 11.205
Authors: Jalal B Andre; Brian W Bresnahan; Mahmud Mossa-Basha; Michael N Hoff; C Patrick Smith; Yoshimi Anzai; Wendy A Cohen Journal: J Am Coll Radiol Date: 2015-05-09 Impact factor: 5.532
Authors: Hugh G Pemberton; Lara A M Zaki; Olivia Goodkin; Ravi K Das; Rebecca M E Steketee; Frederik Barkhof; Meike W Vernooij Journal: Neuroradiology Date: 2022-03-18 Impact factor: 2.804
Authors: Jeffrey D Rudie; Tyler Gleason; Matthew J Barkovich; David M Wilson; Ajit Shankaranarayanan; Tao Zhang; Long Wang; Enhao Gong; Greg Zaharchuk; Javier E Villanueva-Meyer Journal: Radiol Artif Intell Date: 2022-01-12
Authors: T Yamamoto; C Lacheret; H Fukutomi; R A Kamraoui; L Denat; B Zhang; V Prevost; L Zhang; A Ruet; B Triaire; V Dousset; P Coupé; T Tourdias Journal: AJNR Am J Neuroradiol Date: 2022-07-28 Impact factor: 4.966
Authors: David E Ross; John Seabaugh; Jan M Seabaugh; Justis Barcelona; Daniel Seabaugh; Katherine Wright; Lee Norwind; Zachary King; Travis J Graham; Joseph Baker; Tanner Lewis Journal: Front Hum Neurosci Date: 2022-04-08 Impact factor: 3.473