Jalal. B. Andre

Background: Gadolinium‐based contrast agents are used in brain MRI to improve the visualization of disorders and improve the delineation of lesions. Higher doses of GBCAs can improve lesion sensitivity but may have safety implications, particularly in light of recent findings on gadolinium retention and deposition. Purpose: To evaluate the clinical performance of an FDA‐cleared deep‐learning (DL)‐based contrast boosting algorithm in routine clinical brain MRI exams. Study Type: Retrospective. Population: One hundred ten patients (47 ± 22 years; 52 Females, 47 Males, 11 N/A) with clinical contrast‐enhanced brain MR studies. Field Strength and Sequences: T1 weighted pre‐contrast and post‐contrast brain MRI sequences at 0.3 T, 1.5 T, and 3 T. Assessment: A multi‐center database of contrast‐enhanced brain MR images was used to evaluate a DL‐based contrast boosting algorithm. Pre‐contrast and standard post‐contrast (SC) images were processed with the algorithm to obtain contrast boosted (CB) images. CB images were compared to SC images in terms of contrast‐to‐noise ratio (CNR), lesion‐to‐brain ratio (LBR), and contrast enhancement percentage (CEP). Three board‐certified radiologists with 9, 15, and 18 years of experience reviewed CB and SC images side‐by‐side for qualitative evaluation and rated them on a 4‐point Likert scale for lesion contrast enhancement, border delineation, internal morphology, overall image quality, presence of artifacts, and changes in vessel conspicuity. The presence, cause, and severity of any false lesions was recorded. Statistical Tests: Wilcoxon signed rank test. A p value < 0.05 was considered significant. Results: CB images had significantly superior quantitative performance than SC images in terms of CNR (729.17% ± 1576.92%), LBR (87.91% ± 72.12%), and CEP (165.81% ± 42%). In the qualitative assessment, CB images showed significantly better lesion visualization (3.73 vs. 3.16) and had significantly better image quality (3.55 vs. 3.07). Data Conclusion: In this multi‐center, multi‐reader study, deep learning–based contrast boosting demonstrates robust improvements in lesion visualization and image quality without increasing contrast dosage. Evidence Level: 4. Technical Efficacy: Stage 3.

Tractometry of diffusion-weighted magnetic resonance imaging (dMRI) non-invasively quantifies tissue properties of brain connections. It is widely used in aging studies but could be less reliable in aging brains due to increased white matter free water. We demonstrate that computational free water elimination (FWE) and multi-shell multi-tissue (MSMT) modeling both increase the reliability and accuracy of tractometry in a large (n = 396) cohort of older adults (65–103 y.o.). We found substantial improvements in reliability in a split-half comparison at every stage of the pipeline: estimation of voxel-level fiber orientation distribution functions, delineation of major pathway trajectories, and assessment of tissue properties along the pathways. FWE in particular provided better tractography yield, that included more coverage of areas of leukoaraiosis. However, tractometry was strongly predictive of Fazekas scores, which assess the extent of white matter hyperintensity (WMH) burden, regardless of method. This indicates that increased WMH burden is associated with global changes to white matter. By sub-sampling a multi-shell dataset, we demonstrated that these findings generalize to single-shell data, which is important for many datasets where only one b-value may be available. Overall, the results highlight the importance of accounting for free water in tractometry studies, especially in aging brains. We provide open-source software for free-water elimination that can be applied to a wide range of clinical and research datasets (https://github.com/nrdg/fwe).

Tractometry of diffusion-weighted magnetic resonance imaging (dMRI) non-invasively quantifies tissue properties of brain connections. It is widely used in aging studies but could be less reliable in aging brains due to increased white matter free water. We demonstrate that computational free water elimination (FWE) increases reliability and accuracy of tractometry in a large (n = 339) cohort of older adults (66 – 103 y.o.). We found substantial (up to ∼37%) improvements in reliability in a split-half comparison at every stage of the pipeline: estimation of voxel-level fiber orientation distribution functions, delineation of major pathway trajectories, and assessment of tissue properties along the pathways. FWE also improves inferences from tractometry, producing more accurate cross-validated predictions of clinician Fazekas scores. By sub-sampling a multi-b-value dataset, we demonstrated that these findings generalize to both single-b-value data, which is important for many datasets where only one b-value may be available. Overall, the results highlight the importance of accounting for free water in tractometry studies, especially in aging brains. We provide opensource software for free-water elimination that can be applied to a wide range of clinical and research datasets ( https://github.com/nrdg/fwe ).

Objectives: To compare brain MRI measures between Adult Changes in Thought (ACT) participants who underwent research, clinical, or both MRI scans, and clinical health measures across the groups and non-MRI subjects. Methods: Retrospective cohort study leveraging MRI, clinical, demographic, and medication data from ACT. Three neuroradiologists reviewed MRI scans using NIH Neuroimaging Common Data Elements (CDEs). Total brain and white matter hyperintensity (WMH) volumes, clinical characteristics, and outcome measures of brain and overall health were compared between groups. 1166 MRIs were included (77 research, 1043 clinical, and 46 both) and an additional 3146 participants with no MRI were compared. Results: Compared to the group with research MRI only, the clinical MRI group had higher prevalence of the following: acute infarcts, chronic haematoma, subarachnoid haemorrhage, subdural haemorrhage, haemorrhagic transformation, and hydrocephalus (each P < .001). Quantitative WMH burden was significantly lower (P < .001) and total brain volume significantly higher (P < .001) in research MRI participants compared to other MRI groups. Prevalence of hypertension, self-reported cerebrovascular disease, congestive heart failure, dementia, and recent hospitalization (all P < .001) and diabetes (P = .002) differed significantly across groups, with smaller proportions in the research MRI group. Conclusion: In ageing populations, significant differences were observed in MRI metrics between research MRI and clinical MRI groups, and clinical health metric differences between research MRI, clinical MRI, and no-MRI groups. Advances in knowledge: This questions whether research cohorts can adequately represent the greater ageing population undergoing imaging. These findings may also be useful to radiologists when interpreting neuroimaging of ageing.

Background and PurposeTo assess the feasibility of 3-dimensional stereotactic surface projection (3D-SSP) as applied to arterial spin labeling (ASL) in a clinical pilot study.MethodsA retrospective sample of 10 consecutive patients who underwent ASL as part of a clinically indicated MR examination was collected during this pilot study. Five additional subjects with normal cerebral perfusion served as a control group. Following voxel-wise M0-correction, cerebral blood flow (CBF) quantification, and stereotactic anatomic standardization, voxel-wise CBF from an individual's ASL dataset was extracted to a set of predefined surface pixels (3D-SSP). A normal database was created from averaging the extracted CBF datasets of the control group. Patients' datasets were compared individually with the normal database by calculating a Z-score on a pixel-by-pixel basis and were displayed in 3D-SSP views for visual inspection. Independent, two-expert reader assessment, using a 3-point scale, compared standard quantitative CBF images to the 3D-SSP maps.ResultsPatterns and severities of regionally reduced CBF were identified, by both independent readers, in the 3D-SSP maps. Reader assessment demonstrated preference for 3D-SSP over traditionally displayed standard quantitative CBF images in three of four evaluated imaging metrics (p = .026, .031, and .013, respectively); 3D-SSP maps were never found to be inferior to the standard quantitative CBF images.ConclusionsThree-dimensional SSP maps are feasible in a clinical population and enable quantitative data extraction and localization of perfusion abnormalities by means of stereotactic coordinates in a condensed display. The proposed method is a promising approach for interpreting cerebrovascular pathophysiology.

RSNA Case Collection is a collection of peer-reviewed radiology cases.

BACKGROUND AND PURPOSE: Motion artifacts are a frequent source of image degradation in the clinical application of MR imaging (MRI). Here we implement and validate an MRI motion-artifact correction method using a multiscale fully convolutional neural network. MATERIALS AND METHODS: The network was trained to identify motion artifacts in axial T2-weighted spin-echo images of the brain. Using an extensive data augmentation scheme and a motion artifact simulation pipeline, we created a synthetic training dataset of 93,600 images based on only 16 artifact-free clinical MRI cases. A blinded reader study using a unique test dataset of 28 additional clinical MRI cases with real patient motion was conducted to evaluate the performance of the network. RESULTS: Application of the network resulted in notably improved image quality without the loss of morphologic information. For synthetic test data, the average reduction in mean squared error was 41.84%. The blinded reader study on the real-world test data resulted in significant reduction in mean artifact scores across all cases (P < .03). CONCLUSIONS: Retrospective correction of motion artifacts using a multiscale fully convolutional network is promising and may mitigate the substantial motion-related problems in the clinical MRI workflow.

BACKGROUND AND PURPOSE: Spiral MR imaging has several advantages compared with Cartesian MR imaging that can be leveraged for added clinical value. A multicenter multireader study was designed to compare spiral with standard-of-care Cartesian postcontrast structural brain MR imaging on the basis of relative performance in 10 metrics of image quality, artifact prevalence, and diagnostic benefit. MATERIALS AND METHODS: Seven clinical sites acquired 88 total subjects. For each subject, sites acquired 2 postcontrast MR imaging scans: a spiral 2D T1 spin-echo, and 1 of 4 routine Cartesian 2D T1 spin-echo/TSE scans (fully sampled spin-echo at 3T, 1.5T, partial Fourier, TSE). The spiral acquisition matched the Cartesian scan for scan time, geometry, and contrast. Nine neuroradiologists independently reviewed each subject, with the matching pair of spiral and Cartesian scans compared side-by-side, and scored on 10 image-quality metrics (5-point Likert scale) focused on intracranial assessment. The Wilcoxon signed rank test evaluated relative performance of spiral versus Cartesian, while the Kruskal-Wallis test assessed interprotocol differences. RESULTS: Spiral was superior to Cartesian in 7 of 10 metrics (flow artifact mitigation, SNR, GM/WM contrast, image sharpness, lesion conspicuity, preference for diagnosing abnormal enhancement, and overall intracranial image quality), comparable in 1 of 10 metrics (motion artifacts), and inferior in 2 of 10 metrics (susceptibility artifacts, overall extracranial image quality) related to magnetic susceptibility (P < .05). Interprotocol comparison confirmed relatively higher SNR and GM/WM contrast for partial Fourier and TSE protocol groups, respectively (P < .05). CONCLUSIONS: Spiral 2D T1 spin-echo for routine structural brain MR imaging is feasible in the clinic with conventional scanners and was preferred by neuroradiologists for overall postcontrast intracranial evaluation.