Purpose

fMRI is increasingly used for presurgical language mapping, but lack of standard methodology has made it difficult to combine/compare data across institutions or determine the relative efficacy of different approaches. Here, we describe a quantitative analytic framework for determining language laterality in clinical fMRI that addresses these concerns.

Methods

We retrospectively analyzed fMRI data from 59 patients who underwent presurgical language mapping at our institution with identical imaging and behavioral protocols. First, we compared the efficacy of different regional masks in capturing language activations. Then, we systematically explored how laterality indices (LIs) computed from these masks vary as a function of task and activation threshold. Finally, we determined the percentile threshold that maximized the correlation between the results of our LI approach and the laterality assessments from the original clinical radiology reports.

Results

First, we found that a regional mask derived from a meta-analysis of the fMRI literature better captured language task activations than masks based on anatomically defined language areas. Then, we showed that an LI approach based on this functional mask and percentile thresholding of subject activation can quantify the relative ability of different language tasks to lateralize language function at the population level. Finally, we determined that the 92nd percentile of subject-level activation provides the optimal LI threshold with which to reproduce the original clinical reports.

Conclusion

A quantitative framework for determining language laterality that uses a functionally-derived language mask and percentile thresholding of subject activation can combine/compare results across tasks and patients and reproduce clinical assessments of language laterality.

Deep brain stimulation is a promising treatment for severe depression, but lack of efficacy in randomized trials raises questions regarding anatomical targeting. We implanted multi-site intracranial electrodes in a severely depressed patient and systematically assessed the acute response to focal electrical neuromodulation. We found an elaborate repertoire of distinctive emotional responses that were rapid in onset, reproducible, and context and state dependent. Results provide proof of concept for personalized, circuit-specific medicine in psychiatry.

Rationale and objectives

An increasing number of neurological complications and corresponding radiological findings have been reported in patients with COVID-19 infection. The purpose of this study is to systematically review the current literature on COVID-19-associated neuroradiological findings and examine the prevalence of different findings in patients with both severe and mild COVID-19 infection.

Materials and methods

A comprehensive literature search of the PubMed and Embase databases was performed. Any studies reporting CT or MRI neuroimaging findings in patients with confirmed COVID-19 infection were included. Patient demographics, main radiological findings, neurological symptoms, and severity of COVID-19 infection were tabulated and quantified according to infection severity.

Results

Sixty-one studies published between 2019 and 2020 comprising 711 patients were analyzed according to severity of respiratory symptoms. The main neuroradiological findings for patients with mild classification were cranial nerve abnormalities, ischemic infarction, and white matter abnormalities, while the main findings in patients with severe classification were white matter abnormalities, ischemic infarction, and hemorrhagic events.

Conclusion

Neuroradiological manifestations in COVID-19 infection are highly heterogeneous and differ based on the severity of COVID-19 infection. Cranial nerve abnormalities appear exclusive to mild infection, with a high degree of olfactory tract involvement, while hemorrhagic events are more common in severe infection. Notably, ischemic infarction was equally prevalent in both mild and severe COVID-19 infection. Healthcare providers treating COVID-19 patients should be aware of these potential complications and consider neurological assessment and neuroimaging studies when indicated.

Delineation and quantification of normal and abnormal brain tissues on Magnetic Resonance Images is fundamental to the diagnosis and longitudinal assessment of neurological diseases. Here we sought to develop a convolutional neural network for automated multiclass tissue segmentation of brain MRIs that was robust at typical clinical resolutions and in the presence of a variety of lesions. We trained a 3D U-Net for full brain multiclass tissue segmentation from a prior atlas-based segmentation method on an internal dataset that consisted of 558 clinical T1-weighted brain MRIs (453/52/53; training/validation/test) of patients with one of 50 different diagnostic entities (n = 362) or with a normal brain MRI (n = 196). We then used transfer learning to refine our model on an external dataset that consisted of 7 patients with hand-labeled tissue types. We evaluated the tissue-wise and intra-lesion performance with different loss functions and spatial prior information in the validation set and applied the best performing model to the internal and external test sets. The network achieved an average overall Dice score of 0.87 and volume similarity of 0.97 in the internal test set. Further, the network achieved a median intra-lesion tissue segmentation accuracy of 0.85 inside lesions within white matter and 0.61 inside lesions within gray matter. After transfer learning, the network achieved an average overall Dice score of 0.77 and volume similarity of 0.96 in the external dataset compared to human raters. The network had equivalent or better performance than the original atlas-based method on which it was trained across all metrics and produced segmentations in a hundredth of the time. We anticipate that this pipeline will be a useful tool for clinical decision support and quantitative analysis of clinical brain MRIs in the presence of lesions.

Importance

Hereditary hemochromatosis (HH) is an autosomal recessive genetic disorder that leads to iron overload. Conflicting results from previous research has led some to believe the brain is spared the toxic effects of iron in HH.

Objective

To test the association of the strongest genetic risk variant for HH on brainwide measures sensitive to iron deposition and the rates of movement disorders in a substantially larger sample than previous studies of its kind.

Design, setting, and participants

This cross-sectional retrospective study included participants from the UK Biobank, a population-based sample. Genotype, health record, and neuroimaging data were collected from January 2006 to May 2021. Data analysis was conducted from January 2021 to April 2022. Disorders tested included movement disorders (International Statistical Classification of Diseases and Related Health Problems, Tenth Revision [ICD-10], codes G20-G26), abnormalities of gait and mobility (ICD-10 codes R26), and other disorders of the nervous system (ICD-10 codes G90-G99).

Exposures

Homozygosity for p.C282Y, the largest known genetic risk factor for HH.

Main outcomes and measures

T2-weighted and T2* signal intensity from brain magnetic resonance imaging scans, measures sensitive to iron deposition, and clinical diagnosis of neurological disorders.

Results

The total cohort consisted of 488 288 individuals (264 719 female; ages 49-87 years, largely northern European ancestry), 2889 of whom were p.C282Y homozygotes. The neuroimaging analysis consisted of 836 individuals: 165 p.C282Y homozygotes (99 female) and 671 matched controls (399 female). A total of 206 individuals were excluded from analysis due to withdrawal of consent. Neuroimaging analysis showed that p.C282Y homozygosity was associated with decreased T2-weighted and T2* signal intensity in subcortical motor structures (basal ganglia, thalamus, red nucleus, and cerebellum; Cohen d >1) consistent with substantial iron deposition. Across the whole UK Biobank (2889 p.C282Y homozygotes, 485 399 controls), we found a significantly increased prevalence for movement disorders in male homozygotes (OR, 1.80; 95% CI, 1.28-2.55; P = .001) but not female individuals (OR, 1.09; 95% CI, 0.70-1.73; P = .69). Among the 31 p.C282Y male homozygotes with a movement disorder, only 10 had a concurrent HH diagnosis.

Conclusions and relevance

These findings indicate increased iron deposition in subcortical motor circuits in p.C282Y homozygotes and confirm an increased association with movement disorders in male homozygotes. Early treatment in HH effectively prevents the negative consequences of iron overload in the liver and heart. Our work suggests that screening for p.C282Y homozygosity in high-risk individuals also has the potential to reduce brain iron accumulation and to reduce the risk of movement disorders among male individuals who are homozygous for this mutation.

Purpose

To assess how well a brain MRI lesion segmentation algorithm trained at one institution performed at another institution, and to assess the effect of multi-institutional training datasets for mitigating performance loss.

Materials and methods

In this retrospective study, a three-dimensional U-Net for brain MRI abnormality segmentation was trained on data from 293 patients from one institution (IN1) (median age, 54 years; 165 women; patients treated between 2008 and 2018) and tested on data from 51 patients from a second institution (IN2) (median age, 46 years; 27 women; patients treated between 2003 and 2019). The model was then trained on additional data from various sources: (a) 285 multi-institution brain tumor segmentations, (b) 198 IN2 brain tumor segmentations, and (c) 34 IN2 lesion segmentations from various brain pathologic conditions. All trained models were tested on IN1 and external IN2 test datasets, assessing segmentation performance using Dice coefficients.

Results

The U-Net accurately segmented brain MRI lesions across various pathologic conditions. Performance was lower when tested at an external institution (median Dice score, 0.70 [IN2] vs 0.76 [IN1]). Addition of 483 training cases of a single pathologic condition, including from IN2, did not raise performance (median Dice score, 0.72; P = .10). Addition of IN2 training data with heterogeneous pathologic features, representing only 10% (34 of 329) of total training data, increased performance to baseline (Dice score, 0.77; P < .001). This final model produced total lesion volumes with a high correlation to the reference standard (Spearman r = 0.98).

Conclusion

For brain MRI lesion segmentation, adding a modest amount of relevant training data from an external institution to a previously trained model supported successful application of the model to this external institution.Keywords: Neural Networks, Brain/Brain Stem, Segmentation Supplemental material is available for this article. © RSNA, 2021.

Neural networks were trained for segmentation and longitudinal assessment of posttreatment diffuse glioma. A retrospective cohort (from January 2018 to December 2019) of 298 patients with diffuse glioma (mean age, 52 years ± 14 [SD]; 177 men; 152 patients with glioblastoma, 72 patients with astrocytoma, and 74 patients with oligodendroglioma) who underwent two consecutive multimodal MRI examinations were randomly selected into training (n = 198) and testing (n = 100) samples. A posttreatment tumor segmentation three-dimensional nnU-Net convolutional neural network with multichannel inputs (T1, T2, and T1 postcontrast and fluid-attenuated inversion recovery [FLAIR]) was trained to segment three multiclass tissue types (peritumoral edematous, infiltrated, or treatment-changed tissue [ED]; active tumor or enhancing tissue [AT]; and necrotic core). Separate longitudinal change nnU-Nets were trained on registered and subtracted FLAIR and T1 postlongitudinal images to localize and better quantify and classify changes in ED and AT. Segmentation Dice scores, volume similarities, and 95th percentile Hausdorff distances ranged from 0.72 to 0.89, 0.90 to 0.96, and 2.5 to 3.6 mm, respectively. Accuracy rates of the posttreatment tumor segmentation and longitudinal change networks being able to classify longitudinal changes in ED and AT as increased, decreased, or unchanged were 76%-79% and 90%-91%, respectively. The accuracy levels of the longitudinal change networks were not significantly different from those of three neuroradiologists (accuracy, 90%-92%; κ, 0.58-0.63; P > .05). The results of this study support the potential clinical value of artificial intelligence-based automated longitudinal assessment of posttreatment diffuse glioma. Keywords: MR Imaging, Neuro-Oncology, Neural Networks, CNS, Brain/Brain Stem, Segmentation, Quantification, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2022.

Background

Anti-NMDA receptor encephalitis is an immune-mediated disorder characterized by antibodies against the GluN1 subunit of the NMDA receptor that is increasingly recognized as a treatable cause of childhood epileptic encephalopathy. In adults, the disorder has been associated with reversible changes in brain volume over the course of treatment and recovery, but in children, little is known about its time course and associated imaging manifestations.

Case presentation

A previously healthy 20-month-old boy presented with first-time unprovoked seizures, dysautonomia, and dyskinesia. Paraneoplastic workup was negative, but CSF was positive for anti-NMDAR antibodies. The patient's clinical condition waxed and waned over a 14-month course of treatment with first- and second-line immunotherapies (including steroids, IVIG, rituximab, and cyclophosphamide). Serial brain MRIs scans obtained at 5 time points spanning this same period showed no abnormal signal or enhancement but were remarkable for cycles of reversible regional cortical volume loss. All scans included identical 1-mm resolution 3D T1-weighted sequences obtained on the same 3 T scanner. Using a novel longitudinal processing stream in FreeSurfer6 (Reuter M, et. al, Neuroimage 61:1402-18, 2012) we quantified the rate of change in cortical volume at each vertex (% volume change per month) between consecutive scans and correlated these changes with the time course of the patient's treatment and clinical response. We found regionally specific changes in cortical volume (up to 7% per month) that preferentially affected the frontal and occipital lobes and paralleled the patient's clinical course, with clinical decline associated with volume loss and clinical improvement associated with volume gain.

Conclusions

Our results suggest that reversible cortical volume loss in anti-NMDA encephalitis has a regional specificity that mirrors many of the clinical symptoms associated with the disorder and tracks the dynamics of disease severity over time. This case illustrates how quantitative morphometric techniques can be applied to clinical imaging data to reveal patterns of brain change that may provide insight into disease pathophysiology. More widespread application of this approach might reveal regional and temporal patterns specific to different types of autoimmune encephalitis, providing a tool for diagnosis and a surrogate marker for monitoring treatment response.

Supplemental material is available for this article.