Deep Learning Enables 60% Accelerated Volumetric Brain MRI While Preserving Quantitative Performance: A Prospective, Multicenter, Multireader Trial

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 graywhite 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. ABBREVIATIONS: DL ¼ deep learning; FAST ¼ accelerated scan; HOC ¼ hippocampal occupancy score; HV ¼ hippocampal volumes; ILV ¼ inferior lateral ventricles; MCI ¼ mild cognitive impairment; SLV ¼ superior lateral ventricles; SOC ¼ standard of care

Cortical Grey matter volume depletion links to neurological sequelae in post COVID-19 “long haulers”

“…Serologic testing was performed at the George Washington University Pathology Laboratory using Cepheid Xpert Xpres SARS-CoV-2 real time polymerase chain reaction (PCR) test for qualitative detection of COVID-19 coronavirus. Neuroimaging employed 3D VBM NeuroQuant ® software (NeuroQuant ® v2.3), an automated software package which acquires, segments, and quantifies unenhanced 3-dimensional T1 weighted volumetric images of multiple brain structures not apparent with conventional MRI [19][20][21][22][23][24][25][26]. NeuroQuant ® was performed following acquisition of conventional MRI upon Siemens 3 T Skyra scanners each with a 16-channel head coil (Siemens Medical Systems, Erlangen, Germany).…”

“…NeuroQuant ® was performed following acquisition of conventional MRI upon Siemens 3 T Skyra scanners each with a 16-channel head coil (Siemens Medical Systems, Erlangen, Germany). Quantitative MR applications using NeuroQuant ® 3D VBM have allowed for precise measurements of GM tissue damage which can lead to cognitive and neurologic disability accumulation [19][20][21][22][23][24][25][26]. Automated 3D VBM techniques have been shown to perform at least as well as, or better than manual segmentation performed by expert Neuroradiologists, Radiologists and Neurologists, who have specialized training and expertise in anatomic labeling of MR images [24][25][26].…”

Accelerated Synthetic MRI with Deep Learning–Based Reconstruction for Pediatric Neuroimaging

“…DLR techniques can mitigate image noise induced by acceleration techniques and improve SNR/ spatial resolution, enabling a previously unattainable level of fast imaging. 12,13 We hypothesized that the application of DLR to an accelerated synthetic MR imaging protocol can reduce the scan time while maintaining image quality, facilitating the use of synthetic MR imaging in pediatric neuroimaging. 12,13 For this study, we created an accelerated synthetic MR imaging protocol by increasing both the bandwidth and parallel imaging acceleration factor and then applied a vendor-supplied DLR (AIR Recon DL; GE Healthcare) to the accelerated synthetic protocol.…”

“…12,13 We hypothesized that the application of DLR to an accelerated synthetic MR imaging protocol can reduce the scan time while maintaining image quality, facilitating the use of synthetic MR imaging in pediatric neuroimaging. 12,13 For this study, we created an accelerated synthetic MR imaging protocol by increasing both the bandwidth and parallel imaging acceleration factor and then applied a vendor-supplied DLR (AIR Recon DL; GE Healthcare) to the accelerated synthetic protocol. Although several previous studies have investigated the impact of this DLR technique on the image quality and diagnostic performance of conventional MR imaging, [13][14][15] no study has investigated the impact of DLR on synthetic MR imaging in terms of the image quality and quantitative value measurements.…”

Validation of a Denoising Method Using Deep Learning–Based Reconstruction to Quantify Multiple Sclerosis Lesion Load on Fast FLAIR Imaging

“…Indeed, new deep learning-based denoising algorithms have become accessible in clinical practice recently, but only the first few articles have demonstrated their benefits in some clinical situations. [29][30][31] However, possible interest in the context of MS, for which lesion detectability is crucial, has never been explored before. Validation inevitably requires tedious manual delineation or lesion counting by expert readers, which we report here.…”