Search

Objectives: Artificial intelligence (AI) is thought to improve lesion detection. However, a lack of knowledge about human performance prevents a comparative evaluation of AI and an accurate assessment of its impact on clinical decision-making. The objective of this work is to quantitatively evaluate the ability of humans to detect focal cortical dysplasia (FCD), compare it to state-of-the-art AI, and determine how it may aid diagnostics., Materials and Methods: We prospectively recorded the performance of readers in detecting FCDs using single points and 3-dimensional bounding boxes. We acquired predictions of 3 AI models for the same dataset and compared these to readers. Finally, we analyzed pairwise combinations of readers and models., Results: Twenty-eight readers, including 20 nonexpert and 5 expert physicians, reviewed 180 cases: 146 subjects with FCD (median age: 25, interquartile range: 18) and 34 healthy control subjects (median age: 43, interquartile range: 19). Nonexpert readers detected 47% (95% confidence interval [CI]: 46, 49) of FCDs, whereas experts detected 68% (95% CI: 65, 71). The 3 AI models detected 32%, 51%, and 72% of FCDs, respectively. The latter, however, also predicted more than 13 false-positive clusters per subject on average. Human performance was improved in the presence of a transmantle sign (P < 0.001) and cortical thickening (P < 0.001). In contrast, AI models were sensitive to abnormal gyration (P < 0.01) or gray-white matter blurring (P < 0.01). Compared with single experts, expert-expert pairs detected 13% (95% CI: 9, 18) more FCDs (P < 0.001). All AI models increased expert detection rates by up to 19% (95% CI: 15, 24) (P < 0.001). Nonexpert+AI pairs could still outperform single experts by up to 13% (95% CI: 10, 17)., Conclusions: This study pioneers the comparative evaluation of humans and AI for FCD lesion detection. It shows that AI and human predictions differ, especially for certain MRI features of FCD, and, thus, how AI may complement the diagnostic workup., Competing Interests: Conflicts of interest and sources of funding: A.R. has received fees as a speaker from UCB Pharma and travel support from the Elisabeth und Helmut Uhl Stiftung. U.A. has received fees as a speaker for Siemens Healthineers and as clinical consultant for Bayer. A.R. lectures for Guerbet and Bayer, and is part of the Advisory Board for GE, Bracco, and Guerbet. R.S. has received personal fees as speaker or for serving on advisory boards from Angelini, Arvelle, Bial, Desitin, Eisai, Jazz Pharmaceuticals Germany GmbH, Janssen-Cilag GmbH, LivaNova, LivAssured B.V., Novartis, Precisis GmbH, Rapport Therapeutics, Tabuk Pharmaceuticals, UCB Pharma, UNEEG, and Zogenix. T.R. has received fees as a speaker from Eisai. None of the previously mentioned activities were related to the content of this manuscript. The remaining authors have nothing to declare. No external funding was received for this work., (Copyright © 2024 Wolters Kluwer Health, Inc. All rights reserved.)

Objectives: Impaired perivascular clearance has been suggested as a contributing factor to the pathogenesis of Alzheimer disease (AD). However, it remains unresolved when the anatomy of the perivascular space (PVS) is altered during AD progression. Therefore, this study investigates the association between PVS volume and AD progression in cognitively unimpaired (CU) individuals, both with and without subjective cognitive decline (SCD), and in those clinically diagnosed with mild cognitive impairment (MCI) or mild AD., Materials and Methods: A convolutional neural network was trained using manually corrected, filter-based segmentations (n = 1000) to automatically segment the PVS in the centrum semiovale from interpolated, coronal T2-weighted magnetic resonance imaging scans (n = 894). These scans were sourced from the national German Center for Neurodegenerative Diseases Longitudinal Cognitive Impairment and Dementia Study. Convolutional neural network-based segmentations and those performed by a human rater were compared in terms of segmentation volume, identified PVS clusters, as well as Dice score. The comparison revealed good segmentation quality (Pearson correlation coefficient r = 0.70 with P < 0.0001 for PVS volume, detection rate in cluster analysis = 84.3%, and Dice score = 59.0%). Subsequent multivariate linear regression analysis, adjusted for participants' age, was performed to correlate PVS volume with clinical diagnoses, disease progression, cerebrospinal fluid biomarkers, lifestyle factors, and cognitive function. Cognitive function was assessed using the Mini-Mental State Examination, the Comprehensive Neuropsychological Test Battery, and the Cognitive Subscale of the 13-Item Alzheimer's Disease Assessment Scale., Results: Multivariate analysis, adjusted for age, revealed that participants with AD and MCI, but not those with SCD, had significantly higher PVS volumes compared with CU participants without SCD ( P = 0.001 for each group). Furthermore, CU participants who developed incident MCI within 4.5 years after the baseline assessment showed significantly higher PVS volumes at baseline compared with those who did not progress to MCI ( P = 0.03). Cognitive function was negatively correlated with PVS volume across all participant groups ( P ≤ 0.005 for each). No significant correlation was found between PVS volume and any of the following parameters: cerebrospinal fluid biomarkers, sleep quality, body mass index, nicotine consumption, or alcohol abuse., Conclusions: The very early changes of PVS volume may suggest that alterations in PVS function are involved in the pathophysiology of AD. Overall, the volumetric assessment of centrum semiovale PVS represents a very early imaging biomarker for AD., Competing Interests: Conflicts of interest and sources of funding: The authors have declared that no conflict of interest exists. This work was supported by the Deutsche Forschungsgemeinschaft (DFG German Research Foundation) through projects EXC-2047/1-390685813 and EXC2151-390873048 and by the EU–Joint Programme for Neurodegenerative Disease Research through project 01ED2208., (Copyright © 2024 Wolters Kluwer Health, Inc. All rights reserved.)

Objectives: Reducing gadolinium-based contrast agents to lower costs, the environmental impact of gadolinium-containing wastewater, and patient exposure is still an unresolved issue. Published methods have never been compared. The purpose of this study was to compare the performance of 2 reimplemented state-of-the-art deep learning methods (settings A and B) and a proposed method for contrast signal extraction (setting C) to synthesize artificial T1-weighted full-dose images from corresponding noncontrast and low-dose images., Materials and Methods: In this prospective study, 213 participants received magnetic resonance imaging of the brain between August and October 2021 including low-dose (0.02 mmol/kg) and full-dose images (0.1 mmol/kg). Fifty participants were randomly set aside as test set before training (mean age ± SD, 52.6 ± 15.3 years; 30 men). Artificial and true full-dose images were compared using a reader-based study. Two readers noted all false-positive lesions and scored the overall interchangeability in regard to the clinical conclusion. Using a 5-point Likert scale (0 being the worst), they scored the contrast enhancement of each lesion and its conformity to the respective reference in the true image., Results: The average counts of false-positives per participant were 0.33 ± 0.93, 0.07 ± 0.33, and 0.05 ± 0.22 for settings A-C, respectively. Setting C showed a significantly higher proportion of scans scored as fully or mostly interchangeable (70/100) than settings A (40/100, P < 0.001) and B (57/100, P < 0.001), and generated the smallest mean enhancement reduction of scored lesions (-0.50 ± 0.55) compared with the true images (setting A: -1.10 ± 0.98; setting B: -0.91 ± 0.67, both P < 0.001). The average scores of conformity of the lesion were 1.75 ± 1.07, 2.19 ± 1.04, and 2.48 ± 0.91 for settings A-C, respectively, with significant differences among all settings (all P < 0.001)., Conclusions: The proposed method for contrast signal extraction showed significant improvements in synthesizing postcontrast images. A relevant proportion of images showing inadequate interchangeability with the reference remains at this dosage., Competing Interests: Conflicts of interest and sources of funding: R.H., T.P., E.K., D.P., A.E., A.R., and K.D. are cofounders and stakeholders of relios.vision GmbH; Z.B. and C.G. have no conflicts to declare. R.H. is funded by a research grant (BONFOR; O-194.0002.1 and O-194.0003.1) of the Medical Faculty of the University of Bonn. A.E. and T.P. are funded by the German Research Foundation under Germany's Excellence Strategy (EXC-2047/1, 390685813 and EXC-2151, 390873048)., (Copyright © 2024 Wolters Kluwer Health, Inc. All rights reserved.)

Abstract: Deep learning approaches are playing an ever-increasing role throughout diagnostic medicine, especially in neuroradiology, to solve a wide range of problems such as segmentation, synthesis of missing sequences, and image quality improvement. Of particular interest is their application in the reduction of gadolinium-based contrast agents, the administration of which has been under cautious reevaluation in recent years because of concerns about gadolinium deposition and its unclear long-term consequences. A growing number of studies are investigating the reduction (low-dose approach) or even complete substitution (zero-dose approach) of gadolinium-based contrast agents in diverse patient populations using a variety of deep learning methods. This work aims to highlight selected research and discusses the advantages and limitations of recent deep learning approaches, the challenges of assessing its output, and the progress toward clinical applicability distinguishing between the low-dose and zero-dose approach., Competing Interests: Conflicts of interest and sources of funding: R.H. is funded by a research grant (BONFOR; O-194.0002.1) of the Medical Faculty of the University of Bonn. A.E. and T.P. are funded by the German Research Foundation under Germany's Excellence Strategy (EXC-2047/1, 390685813 and EXC-2151, 390873048). All authors are cofounders of relios.vision., (Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.)

Objective: To determine whether thrombectomy is safe in children up to 24 hours after onset of symptoms when selected by mismatch between clinical deficit and infarct., Methods: A secondary analysis of the Save ChildS Study (January 2000-December 2018) was performed, including all pediatric patients (<18 years) diagnosed with arterial ischemic stroke who underwent endovascular recanalization at 27 European and United States stroke centers. Patients were included if they had a relevant mismatch between clinical deficit and infarct., Results: Twenty children with a median age of 10.5 (interquartile range [IQR] 7-14.6) years were included. Of those, 7 were male (35%), and median time from onset to thrombectomy was 9.8 (IQR 7.8-16.2) hours. Neurologic outcome improved from a median Pediatric NIH Stroke Scale score of 12.0 (IQR 8.8-20.3) at admission to 2.0 (IQR 1.2-6.8) at day 7. Median modified Rankin Scale (mRS) score was 1.0 (IQR 0-1.6) at 3 months and 0.0 (IQR 0-1.0) at 24 months. One patient developed transient peri-interventional vasospasm; no other complications were observed. A comparison of the mRS score to the mRS score in the DAWN and DEFUSE 3 trials revealed a higher proportion of good outcomes in the pediatric compared to the adult study population., Conclusions: Thrombectomy in pediatric ischemic stroke in an extended time window of up to 24 hours after onset of symptoms seems safe and neurologic outcomes are generally good if patients are selected by a mismatch between clinical deficit and infarct., Classification of Evidence: This study provides Class IV evidence that for children with acute ischemic stroke with a mismatch between clinical deficit and infarct size, thrombectomy is safe., (© 2020 American Academy of Neurology.)

Objectives: In recent years, complaints of patients about burning pain in arms and legs after the injection of gadolinium-based contrast agents (GBCAs) have been reported. In the current study, we investigated changes of small fibers in the epidermis as a potential cause of the patient complaints in a mouse model., Methods: Six groups of 8 mice were intravenously injected with either a macrocyclic GBCA (gadoteridol, gadoterate meglumine, gadobutrol), a linear GBCA (gadodiamide or gadobenate dimeglumine) (1 mmol/kg body weight), or saline (NaCl 0.9%). Four weeks after injection, animals were euthanized, and footpads were assessed using immunofluorescence staining. Intraepidermal nerve fiber density (IENFD) was calculated, and the median number of terminal axonal swellings (TASs) per IENFD was determined., Results: Nonparametric Wilcoxon signed-rank test revealed significantly lower IENFDs for all GBCAs compared with the control group (P < 0.0001) with the linear GBCAs showing significantly lower IENFDs than the macrocyclic GBCAs (P < 0.0001). The linear GBCAs presented significantly more TAS per IENFD than the control group (P < 0.0001), whereas no significant increase of TAS per IENFD compared with the control group was found for macrocyclic GBCAs (P < 0.237)., Interpretation: It is unclear whether or at what dosage the decrease of IENFDs and the increase of TAS per IENFD found in the current animal model will appear in humans and if it translates into clinical symptoms. However, given the highly significant findings of the current study, more research in this field is required.

Objective: To determine the role of associated developmental venous anomalies (DVAs) in intracranial hemorrhage (ICH) caused by cerebral cavernous malformations (CCMs)., Methods: We analyzed patient registry data of 1,219 patients with cavernous malformations treated in our institution between 2003 and 2018. Patients with spinal and familial CCM and patients without complete MRI data were excluded. The impact of various variables on ICH as a mode of presentation was assessed with multivariate binary logistic regression analysis. Kaplan Meier/Cox regression analysis was performed to analyze cumulative 5-year-risk for (re)hemorrhage and to identify baseline predictors of this outcome., Results: Seven hundred thirty-one patients with CCM were included. Multivariate logistic regression confirmed a statistically significant negative correlation with DVA (odds ratio [OR] 0.635 [95% confidence interval (CI) 0.459-0.878]) and positive correlation with brainstem localization (OR 6.277 [95% CI 4.287-9.191]) with ICH as the mode of presentation. Among 731 patients, 76 experienced (re)hemorrhage during 2,338 person-years of follow-up. Overall cumulative 5-year risk was 24.1% (95% CI 21.1%-27.5%). Cox regression analysis revealed initial presentation with ICH (hazard ratio [HR] 8.0 [95% CI 3.549-18.122]) and brainstem localization (HR 2.9 [95% CI 1.756-4.765]) as independent baseline predictors of (re)hemorrhage. Presence of DVA added no independent prognostic information (HR 1.1 [95% CI 0.717-1.885])., Conclusion: Patients with CCM with associated DVA are at lower risk to present with ICH. During untreated 5-year follow-up, they showed equal (re)hemorrhage risk compared to patients with CCM without DVA., (© 2020 American Academy of Neurology.)

Background and Purpose- The recent Save ChildS study provides multicenter evidence for the use of mechanical thrombectomy in children with large vessel occlusion arterial ischemic stroke. However, device selection for thrombectomy may influence rates of recanalization, complications, and neurological outcomes, especially in pediatric patients of different ages. We, therefore, performed additional analyses of the Save ChildS data to investigate a possible association of different thrombectomy techniques and devices with angiographic and clinical outcome parameters. Methods- The Save ChildS cohort study (January 2000-December 2018) analyzed data from 27 European and United States stroke centers and included all pediatric patients (<18 years), diagnosed with arterial ischemic stroke who underwent endovascular recanalization. Patients were grouped into first-line contact aspiration (A Direct Aspiration First Pass Technique [ADAPT]) and non-ADAPT groups as well as different stent retriever size groups. Associations with baseline characteristics, recanalization rates (modified Treatment in Cerebral Infarction), complication rates, and neurological outcome parameters (Pediatric National Institutes of Health Stroke Scale after 24 hours and 7 days; modified Rankin Scale and Pediatric Stroke Outcome Measure at discharge, after 6 and 24 months) were investigated. Results- Seventy-three patients with a median age of 11.3 years were included. Currently available stent retrievers were used in 59 patients (80.8%), of which 4×20 mm (width×length) was the most frequently chosen size (36 patients =61%). A first-line ADAPT approach was used in 7 patients (9.6%), and 7 patients (9.6%) were treated with first-generation thrombectomy devices. In this study, a first-line ADAPT approach was neither associated with the rate of successful recanalization (ADAPT 85.7% versus 87.5% No ADAPT) nor with the complication rate or the neurological outcome. Moreover, there were no associations of stent retriever sizes with rates of recanalization, complication rates, or outcome parameters. Conclusions- Our study suggests that neurological outcomes are generally good regardless of any specific device selection and suggests that it is important to offer thrombectomy in eligible children regardless of technique or device selection. Registration- URL: https://www.drks.de/; Unique identifier: DRKS00016528.

Objective: Recent studies reported a signal intensity increase in the deep cerebellar nuclei (DCN) on magnetic resonance images caused by gadolinium deposition after the injection of gadolinium-based contrast agents (GBCAs). There is an ongoing debate if the propensity of a GBCA to deposit gadolinium is primarily determined by its class as either linear or macrocyclic. In the current study, we aimed to compare the amount and the distribution of retained gadolinium of linear and macrocyclic GBCAs in the DCN after a single injection at a dose comparable to a human patient's in a large animal model., Materials and Methods: Eighteen sheep were randomly assigned in 6 groups of 3 animals, which received a single injection of 0.1 mmol/kg body weight of either the macrocyclic GBCAs gadobutrol, gadoteridol, or gadoterate meglumine; the linear GBCAs gadobenate dimeglumine or gadodiamide; or saline. Animals were euthanized 10 weeks after injection. Local distribution and concentration of gadolinium and colocalization to other metals (iron, zinc, copper) in the DCN was assessed by laser ablation-inductively coupled plasma-mass spectrometry., Results: Average gadolinium concentration for the macrocyclic GBCAs and the saline group was below the limit of quantification (5.7 ng/g tissue). In contrast, 14 (for gadobenate) and 27 (for gadodiamide) times more gadolinium than the limit of quantification was found for the linear GBCAs gadobenate (mean, 83 ng/g) or gadodiamide (mean, 155 ng/g brain tissue). Gadolinium distribution colocalized with other metals for linear GBCAs and a specific accumulation in the DCN was found., Discussion: The current study supports the hypothesis that the amount of gadolinium deposited in the brain is primarily determined by its class as either macrocyclic or linear. The accumulation of gadolinium in the DCN for linear GBCAs explains the hyperintensities in the DCN found in previous patient studies with linear GBCAs.