Combined effects of Alzheimer risk variants in the CLU and ApoE genes on ventricular expansion patterns in the elderly.

The C allele at the rs11136000 locus in the clusterin (CLU) gene is the third strongest known genetic risk factor for late-onset Alzheimer's disease (LOAD). A recent genome-wide association study of LOAD found the strongest evidence of association with CLU at rs1532278, in high linkage disequilibrium with rs11136000. Brain structure and function are related to the CLU risk alleles, not just in LOAD patients but also in healthy young adults. We tracked the volume of the lateral ventricles across baseline, 1-year, and 2-year follow-up scans in a large sample of elderly human participants (N = 736 at baseline), from the Alzheimer's Disease Neuroimaging Initiative, to determine whether these CLU risk variants predicted longitudinal ventricular expansion. The rs11136000 major C allele-previously linked with reduced CLU expression and with increased risk for dementia-predicted faster expansion, independently of dementia status or ApoE genotype. Further analyses revealed that the CLU and ApoE risk variants had combined effects on both volumetric expansion and lateral ventricle surface morphology. The rs1532278 locus strongly resembles a regulatory element. Its association with ventricular expansion was slightly stronger than that of rs11136000 in our analyses, suggesting that it may be closer to a functional variant. Clusterin affects inflammation, immune responses, and amyloid clearance, which in turn may result in neurodegeneration. Pharmaceutical agents such as valproate, which counteract the effects of genetically determined reduced clusterin expression, may help to achieve neuroprotection and contribute to the prevention of dementia, especially in carriers of these CLU risk variants.

The University of California San Francisco Brain Metastases Stereotactic Radiosurgery (UCSF-BMSR) MRI Dataset.

Supplemental material is available for this article.

Along-tract statistics allow for enhanced tractography analysis.

Diffusion imaging tractography is a valuable tool for neuroscience researchers because it allows the generation of individualized virtual dissections of major white matter tracts in the human brain. It facilitates between-subject statistical analyses tailored to the specific anatomy of each participant. There is prominent variation in diffusion imaging metrics (e.g., fractional anisotropy, FA) within tracts, but most tractography studies use a "tract-averaged" approach to analysis by averaging the scalar values from the many streamline vertices in a tract dissection into a single point-spread estimate for each tract. Here we describe a complete workflow needed to conduct an along-tract analysis of white matter streamline tract groups. This consists of 1) A flexible MATLAB toolkit for generating along-tract data based on B-spline resampling and compilation of scalar data at different collections of vertices along the curving tract spines, and 2) Statistical analysis and rich data visualization by leveraging tools available through the R platform for statistical computing. We demonstrate the effectiveness of such an along-tract approach over the tract-averaged approach in an example analysis of 10 major white matter tracts in a single subject. We also show that these techniques easily extend to between-group analyses typically used in neuroscience applications, by conducting an along-tract analysis of differences in FA between 9 individuals with fetal alcohol spectrum disorders (FASDs) and 11 typically-developing controls. This analysis reveals localized differences between FASD and control groups that were not apparent using a tract-averaged method. Finally, to validate our approach and highlight the strength of this extensible software framework, we implement 2 other methods from the literature and leverage the existing workflow tools to conduct a comparison study.

Interinstitutional Portability of a Deep Learning Brain MRI Lesion Segmentation Algorithm.

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.

Longitudinal Assessment of Posttreatment Diffuse Glioma Tissue Volumes with Three-dimensional Convolutional Neural Networks.

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.

Quantitative in vivo evidence for broad regional gradients in the timing of white matter maturation during adolescence.

A fundamental tenet in the field of developmental neuroscience is that brain maturation generally proceeds from posterior/inferior to anterior/superior. This pattern is thought to underlie the similar timing of cognitive development in related domains, with the dorsal frontal cortices-important for decision making and cognitive control-the last to fully mature. While this caudal to rostral wave of structural development was first qualitatively described for white matter in classical postmortem studies, and has been discussed frequently in the developmental neuroimaging literature and in the popular press, it has never been formally demonstrated continuously and quantitatively across the whole brain with magnetic resonance imaging (MRI). Here we use diffusion imaging to map developmental changes in the white matter in 32 typically-developing individuals age 5-28 years. We then employ a novel meta-statistic that is sensitive to the timing of this developmental trajectory, and use this integrated strategy to both confirm these long-postulated broad regional gradients in the timing of white matter maturation in vivo, and demonstrate a surprisingly smooth transition in the timing of white matter maturational peaks along a caudal-rostral arc in this cross-sectional sample. These results provide further support for the notion of continued plasticity in these regions well into adulthood, and may provide a new approach for the investigation of neurodevelopmental disorders that could alter the timing of this typical developmental sequence.

Three-dimensional U-Net Convolutional Neural Network for Detection and Segmentation of Intracranial Metastases.

PURPOSE: To develop and validate a neural network for automated detection and segmentation of intracranial metastases on brain MRI studies obtained for stereotactic radiosurgery treatment planning. MATERIALS AND METHODS: In this retrospective study, 413 patients (average age, 61 years ± 12 [standard deviation]; 238 women) with a total of 5202 intracranial metastases (median volume, 0.05 cm3; interquartile range, 0.02-0.18 cm3) undergoing stereotactic radiosurgery at one institution were included (January 2017 to February 2020). A total of 563 MRI examinations were performed among the patients, and studies were split into training (n = 413), validation (n = 50), and test (n = 100) datasets. A three-dimensional (3D) U-Net convolutional network was trained and validated on 413 T1 postcontrast or subtraction scans, and several loss functions were evaluated. After model validation, 100 discrete test patients, who underwent imaging after the training and validation patients, were used for final model evaluation. Performance for detection and segmentation of metastases was evaluated using Dice scores, false discovery rates, and false-negative rates, and a comparison with neuroradiologist interrater reliability was performed. RESULTS: The median Dice score for segmenting enhancing metastases in the test set was 0.75 (interquartile range, 0.63-0.84). There were strong correlations between manually segmented and predicted metastasis volumes (r = 0.98, P < .001) and between the number of manually segmented and predicted metastases (R = 0.95, P < .001). Higher Dice scores were strongly correlated with larger metastasis volumes on a logarithmically transformed scale (r = 0.71). Sensitivity across the whole test sample was 70.0% overall and 96.4% for metastases larger than 6 mm. There was an average of 0.46 false-positive results per scan, with the positive predictive value being 91.5%. In comparison, the median Dice score between two neuroradiologists was 0.85 (interquartile range, 0.80-0.89), with sensitivity across the test sample being 87.9% overall and 98.4% for metastases larger than 6 mm. CONCLUSION: A 3D U-Net-based convolutional neural network was able to segment brain metastases with high accuracy and perform detection at the level of human interrater reliability for metastases larger than 6 mm.Keywords: Adults, Brain/Brain Stem, CNS, Feature detection, MR-Imaging, Neural Networks, Neuro-Oncology, Quantification, Segmentation© RSNA, 2021.

Multi-Disease Segmentation of Gliomas and White Matter Hyperintensities in the BraTS Data Using a 3D Convolutional Neural Network.

An important challenge in segmenting real-world biomedical imaging data is the presence of multiple disease processes within individual subjects. Most adults above age 60 exhibit a variable degree of small vessel ischemic disease, as well as chronic infarcts, which will manifest as white matter hyperintensities (WMH) on brain MRIs. Subjects diagnosed with gliomas will also typically exhibit some degree of abnormal T2 signal due to WMH, rather than just due to tumor. We sought to develop a fully automated algorithm to distinguish and quantify these distinct disease processes within individual subjects' brain MRIs. To address this multi-disease problem, we trained a 3D U-Net to distinguish between abnormal signal arising from tumors vs. WMH in the 3D multi-parametric MRI (mpMRI, i.e., native T1-weighted, T1-post-contrast, T2, T2-FLAIR) scans of the International Brain Tumor Segmentation (BraTS) 2018 dataset (n training = 285, n validation = 66). Our trained neuroradiologist manually annotated WMH on the BraTS training subjects, finding that 69% of subjects had WMH. Our 3D U-Net model had a 4-channel 3D input patch (80 × 80 × 80) from mpMRI, four encoding and decoding layers, and an output of either four [background, active tumor (AT), necrotic core (NCR), peritumoral edematous/infiltrated tissue (ED)] or five classes (adding WMH as the fifth class). For both the four- and five-class output models, the median Dice for whole tumor (WT) extent (i.e., union of AT, ED, NCR) was 0.92 in both training and validation sets. Notably, the five-class model achieved significantly (p = 0.002) lower/better Hausdorff distances for WT extent in the training subjects. There was strong positive correlation between manually segmented and predicted volumes for WT (r = 0.96) and WMH (r = 0.89). Larger lesion volumes were positively correlated with higher/better Dice scores for WT (r = 0.33), WMH (r = 0.34), and across all lesions (r = 0.89) on a log(10) transformed scale. While the median Dice for WMH was 0.42 across training subjects with WMH, the median Dice was 0.62 for those with at least 5 cm3 of WMH. We anticipate the development of computational algorithms that are able to model multiple diseases within a single subject will be a critical step toward translating and integrating artificial intelligence systems into the heterogeneous real-world clinical workflow.

Diagnosing Distensible Venous Malformations of the Orbit With Diffusion-weighted Magnetic Resonance Imaging.

PURPOSE: To compare the diffusion-weighted imaging of nonthrombosed distensible venous malformations of the orbit with that of other histologically-proven orbital tumors. DESIGN: Retrospective case-control study. METHODS: Patients with nonthrombosed distensible venous malformations of the orbit and patients with other histologically-proven orbital tumors were selected for chart review. The main outcome measure was the apparent diffusion coefficient of these lesions. RESULTS: Sixty-seven patients qualified for chart review; 9 patients had nonthrombosed distensible venous malformations and 58 patients had other histologically-proven tumors. Three of the 9 patients with nonthrombosed distensible venous malformations were initially misdiagnosed as having had solid orbital tumors. The mean apparent diffusion coefficient of distensible venous malformations was 2.80 ± 0.48 × 10-3 mm2/s, whereas the mean apparent diffusion coefficient of other histologically-proven tumors was 1.18 ± 0.39 × 10-3 mm2/s (P < .001). The mean apparent diffusion coefficient ranged from 2.42 to 3.94 × 10-3 mm2/s in the distensible venous malformation group, whereas other histologically-proven tumors ranged from 0.53 to 2.08 × 10-3 mm2/s. Therefore, in this single-institution series, a threshold value of 2.10 × 10-3 mm2/s was 100% sensitive and 100% specific for distensible venous malformations. CONCLUSION: Certain nonthrombosed distensible venous malformations can evade diagnostic suspicion and mimic solid orbital tumors on standard magnetic resonance imaging sequences. In this single-institution series, diffusion-weighted imaging effectively distinguished these nonthrombosed distensible venous malformations from other orbital tumors.

Machine learning classification of mesial temporal sclerosis in epilepsy patients.

BACKGROUND AND PURPOSE: Novel approaches applying machine-learning methods to neuroimaging data seek to develop individualized measures that will aid in the diagnosis and treatment of brain-based disorders such as temporal lobe epilepsy (TLE). Using a large cohort of epilepsy patients with and without mesial temporal sclerosis (MTS), we sought to automatically classify MTS using measures of cortical morphology, and to further relate classification probabilities to measures of disease burden. MATERIALS AND METHODS: Our sample consisted of high-resolution T1 structural scans of 169 adults with epilepsy collected across five different 1.5T and four different 3T scanners at UCLA. We applied a multiple support vector machine recursive feature elimination algorithm to morphological measures generated from FreeSurfer's automated segmentation and parcellation in order to classify Epilepsy patients with MTS (n=85) from those without MTS (N=84). RESULTS: In addition to hippocampal volume, we found that alterations in cortical thickness, surface area, volume and curvature in inferior frontal and anterior and inferior temporal regions contributed to a classification accuracy of up to 81% (p=1.3×10(-17)) in identifying MTS. We also found that MTS classification probabilities were associated with a longer duration of disease for epilepsy patients both with and without MTS. CONCLUSIONS: In addition to implicating extra-hippocampal involvement of MTS, these findings shed further light on the pathogenesis of TLE and may ultimately assist in the development of automated tools that incorporate multiple neuroimaging measures to assist clinicians in detecting more subtle cases of TLE and MTS.

White matter connectivity and aerobic fitness in male adolescents.

Exercise has been shown to have positive effects on the brain and behavior throughout various stages of the lifespan. However, little is known about the impact of exercise on neurodevelopment during the adolescent years, particularly with regard to white matter microstructure, as assessed by diffusion tensor imaging (DTI). Both tract-based spatial statistics (TBSS) and tractography-based along-tract statistics were utilized to examine the relationship between white matter microstructure and aerobic exercise in adolescent males, ages 15-18. Furthermore, we examined the data by both (1) grouping individuals based on aerobic fitness self-reports (high fit (HF) vs. low fit (LF)), and (2) using VO2 peak as a continuous variable across the entire sample. Results showed that HF youth had an overall higher number of streamline counts compared to LF peers, which was driven by group differences in corticospinal tract (CST) and anterior corpus callosum (Fminor). In addition, VO2 peak was negatively related to FA in the left CST. Together, these results suggest that aerobic fitness relates to white matter connectivity and microstructure in tracts carrying frontal and motor fibers during adolescence. Furthermore, the current study highlights the importance of considering the environmental factor of aerobic exercise when examining adolescent brain development.

Apolipoprotein E epsilon 4 allele is associated with ventricular expansion rate and surface morphology in dementia and normal aging.

The apolipoprotein E epsilon 4 allele (ApoE-ε4) is the strongest known genetic risk factor for late onset Alzheimer's disease. Expansion of the lateral ventricles occurs with normal aging, but dementia accelerates this process. Brain structure and function depend on ApoE genotype not just for Alzheimer's disease patients but also in healthy elderly individuals, and even in asymptomatic young individuals. Therefore, we hypothesized that the ApoE-ε4 allele is associated with altered patterns of longitudinal ventricular expansion, in dementia and normal aging. We tested this hypothesis in a large sample of elderly participants, using a linear discriminant analysis-based approach. Carrying more ApoE-ε4 alleles was associated with faster ventricular expansion bilaterally and with regional patterns of lateral ventricle morphology at 1- and 2-year follow up, after controlling for sex, age, and dementia status. ApoE genotyping is considered critical in clinical trials of Alzheimer's disease. These findings, combined with earlier investigations showing that ApoE is also directly implicated in other conditions, suggest that the selective enrollment of ApoE-ε4 carriers may empower clinical trials of other neurological disorders.

White matter microstructural alterations in children with prenatal methamphetamine/polydrug exposure.

Little is known about the effects of prenatal methamphetamine exposure on white matter microstructure, and the impact of concomitant alcohol exposure. Diffusion tensor imaging and neurocognitive testing were performed on 21 children with prenatal methamphetamine exposure (age 9.8±1.8 years; 17 also exposed to alcohol), 19 children with prenatal alcohol but not methamphetamine exposure (age 10.8±2.3 years) and 27 typically developing children (age 10.3±3.3 years). Whole-brain maps of fractional anisotropy (FA) were evaluated using tract-based spatial statistics. Relative to unexposed controls, children with prenatal methamphetamine exposure demonstrated higher FA mainly in left-sided regions, including the left anterior corona radiata (LCR) and corticospinal tract Post-hoc analyses of these FA differences showed they likely result more from lower radial diffusivity (RD) than higher axial diffusivity (AD). Relative to the methamphetamine-exposed group, children with prenatal alcohol exposure showed lower FA in frontotemporal regions-particularly, the right external capsule. We failed to find any group-performance interaction (on tests of executive functioning and visuomotor integration) in predicting FA; however, FA in the right external capsule was significantly associated with performance on a test of visuomotor integration across groups. This report demonstrates unique diffusion abnormalities in children with prenatal methamphetamine/polydrug exposure that are distinct from those associated with alcohol exposure alone, and illustrates that these abnormalities in brain microstructure are persistent into childhood and adolescence--long after the polydrug exposure in utero.

Insights into multimodal imaging classification of ADHD.

Attention deficit hyperactivity disorder (ADHD) currently is diagnosed in children by clinicians via subjective ADHD-specific behavioral instruments and by reports from the parents and teachers. Considering its high prevalence and large economic and societal costs, a quantitative tool that aids in diagnosis by characterizing underlying neurobiology would be extremely valuable. This provided motivation for the ADHD-200 machine learning (ML) competition, a multisite collaborative effort to investigate imaging classifiers for ADHD. Here we present our ML approach, which used structural and functional magnetic resonance imaging data, combined with demographic information, to predict diagnostic status of individuals with ADHD from typically developing (TD) children across eight different research sites. Structural features included quantitative metrics from 113 cortical and non-cortical regions. Functional features included Pearson correlation functional connectivity matrices, nodal and global graph theoretical measures, nodal power spectra, voxelwise global connectivity, and voxelwise regional homogeneity. We performed feature ranking for each site and modality using the multiple support vector machine recursive feature elimination (SVM-RFE) algorithm, and feature subset selection by optimizing the expected generalization performance of a radial basis function kernel SVM (RBF-SVM) trained across a range of the top features. Site-specific RBF-SVMs using these optimal feature sets from each imaging modality were used to predict the class labels of an independent hold-out test set. A voting approach was used to combine these multiple predictions and assign final class labels. With this methodology we were able to predict diagnosis of ADHD with 55% accuracy (versus a 39% chance level in this sample), 33% sensitivity, and 80% specificity. This approach also allowed us to evaluate predictive structural and functional features giving insight into abnormal brain circuitry in ADHD.