Differences in educational opportunity predict white matter development.

Coarse measures of socioeconomic status, such as parental income or parental education, have been linked to differences in white matter development. However, these measures do not provide insight into specific aspects of an individual's environment and how they relate to brain development. On the other hand, educational intervention studies have shown that changes in an individual's educational context can drive measurable changes in their white matter. These studies, however, rarely consider socioeconomic factors in their results. In the present study, we examined the unique relationship between educational opportunity and white matter development, when controlling other known socioeconomic factors. To explore this question, we leveraged the rich demographic and neuroimaging data available in the ABCD study, as well the unique data-crosswalk between ABCD and the Stanford Education Data Archive (SEDA). We find that educational opportunity is related to accelerated white matter development, even when accounting for other socioeconomic factors, and that this relationship is most pronounced in white matter tracts associated with academic skills. These results suggest that the school a child attends has a measurable relationship with brain development for years to come.

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

Supplemental material is available for this article.

Automated neonatal nnU-Net brain MRI extractor trained on a large multi-institutional dataset.

Brain extraction, or skull-stripping, is an essential data preprocessing step for machine learning approaches to brain MRI analysis. Currently, there are limited extraction algorithms for the neonatal brain. We aim to adapt an established deep learning algorithm for the automatic segmentation of neonatal brains from MRI, trained on a large multi-institutional dataset for improved generalizability across image acquisition parameters. Our model, ANUBEX (automated neonatal nnU-Net brain MRI extractor), was designed using nnU-Net and was trained on a subset of participants (N = 433) enrolled in the High-dose Erythropoietin for Asphyxia and Encephalopathy (HEAL) study. We compared the performance of our model to five publicly available models (BET, BSE, CABINET, iBEATv2, ROBEX) across conventional and machine learning methods, tested on two public datasets (NIH and dHCP). We found that our model had a significantly higher Dice score on the aggregate of both data sets and comparable or significantly higher Dice scores on the NIH (low-resolution) and dHCP (high-resolution) datasets independently. ANUBEX performs similarly when trained on sequence-agnostic or motion-degraded MRI, but slightly worse on preterm brains. In conclusion, we created an automatic deep learning-based neonatal brain extraction algorithm that demonstrates accurate performance with both high- and low-resolution MRIs with fast computation time.

White matter and literacy: A dynamic system in flux.

Cross-sectional studies have linked differences in white matter tissue properties to reading skills. However, past studies have reported a range of, sometimes conflicting, results. Some studies suggest that white matter properties act as individual-level traits predictive of reading skill, whereas others suggest that reading skill and white matter develop as a function of an individual's educational experience. In the present study, we tested two hypotheses: a) that diffusion properties of the white matter reflect stable brain characteristics that relate to stable individual differences in reading ability or b) that white matter is a dynamic system, linked with learning over time. To answer these questions, we examined the relationship between white matter and reading in a five-year longitudinal dataset and a series of large-scale, single-observation, cross-sectional datasets (N = 14,249 total participants). We find that gains in reading skill correspond to longitudinal changes in the white matter. However, in the cross-sectional datasets, we find no evidence for the hypothesis that individual differences in white matter predict reading skill. These findings highlight the link between dynamic processes in the white matter and learning.

Bayesian Networks in Radiology.

A Bayesian network is a graphical model that uses probability theory to represent relationships among its variables. The model is a directed acyclic graph whose nodes represent variables, such as the presence of a disease or an imaging finding. Connections between nodes express causal influences between variables as probability values. Bayesian networks can learn their structure (nodes and connections) and/or conditional probability values from data. Bayesian networks offer several advantages: (a) they can efficiently perform complex inferences, (b) reason from cause to effect or vice versa, (c) assess counterfactual data, (d) integrate observations with canonical ("textbook") knowledge, and (e) explain their reasoning. Bayesian networks have been employed in a wide variety of applications in radiology, including diagnosis and treatment planning. Unlike deep learning approaches, Bayesian networks have not been applied to computer vision. However, hybrid artificial intelligence systems have combined deep learning models with Bayesian networks, where the deep learning model identifies findings in medical images and the Bayesian network formulates and explains a diagnosis from those findings. One can apply a Bayesian network's probabilistic knowledge to integrate clinical and imaging findings to support diagnosis, treatment planning, and clinical decision-making. This article reviews the fundamental principles of Bayesian networks and summarizes their applications in radiology. Keywords: Bayesian Network, Machine Learning, Abdominal Imaging, Musculoskeletal Imaging, Breast Imaging, Neurologic Imaging, Radiology Education Supplemental material is available for this article. © RSNA, 2023.

3D U-Net for automated detection of multiple sclerosis lesions: utility of transfer learning from other pathologies.

Background and purpose: Deep learning algorithms for segmentation of multiple sclerosis (MS) plaques generally require training on large datasets. This manuscript evaluates the effect of transfer learning from segmentation of another pathology to facilitate use of smaller MS-specific training datasets. That is, a model trained for detection of one type of pathology was re-trained to identify MS lesions and active demyelination. Materials and methods: In this retrospective study using MRI exams from 149 patients spanning 4/18/2014 to 7/8/2021, 3D convolutional neural networks were trained with a variable number of manually-segmented MS studies. Models were trained for FLAIR lesion segmentation at a single timepoint, new FLAIR lesion segmentation comparing two timepoints, and enhancing (actively demyelinating) lesion segmentation on T1 post-contrast imaging. Models were trained either de-novo or fine-tuned with transfer learning applied to a pre-existing model initially trained on non-MS data. Performance was evaluated with lesionwise sensitivity and positive predictive value (PPV). Results: For single timepoint FLAIR lesion segmentation with 10 training studies, a fine-tuned model demonstrated improved performance [lesionwise sensitivity 0.55 ± 0.02 (mean ± standard error), PPV 0.66 ± 0.02] compared to a de-novo model (sensitivity 0.49 ± 0.02, p = 0.001; PPV 0.32 ± 0.02, p < 0.001). For new lesion segmentation with 30 training studies and their prior comparisons, a fine-tuned model demonstrated similar sensitivity (0.49 ± 0.05) and significantly improved PPV (0.60 ± 0.05) compared to a de-novo model (sensitivity 0.51 ± 0.04, p = 0.437; PPV 0.43 ± 0.04, p = 0.002). For enhancement segmentation with 20 training studies, a fine-tuned model demonstrated significantly improved overall performance (sensitivity 0.74 ± 0.06, PPV 0.69 ± 0.05) compared to a de-novo model (sensitivity 0.44 ± 0.09, p = 0.001; PPV 0.37 ± 0.05, p = 0.001). Conclusion: By fine-tuning models trained for other disease pathologies with MS-specific data, competitive models identifying existing MS plaques, new MS plaques, and active demyelination can be built with substantially smaller datasets than would otherwise be required to train new models.

Reducing Gadolinium Contrast With Artificial Intelligence.

Gadolinium contrast is an important agent in magnetic resonance imaging (MRI), particularly in neuroimaging where it can help identify blood-brain barrier breakdown from an inflammatory, infectious, or neoplastic process. However, gadolinium contrast has several drawbacks, including nephrogenic systemic fibrosis, gadolinium deposition in the brain and bones, and allergic-like reactions. As computer hardware and technology continues to evolve, machine learning has become a possible solution for eliminating or reducing the dose of gadolinium contrast. This review summarizes the clinical uses of gadolinium contrast, the risks of gadolinium contrast, and state-of-the-art machine learning methods that have been applied to reduce or eliminate gadolinium contrast administration, as well as their current limitations, with a focus on neuroimaging applications. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 1.

The University of California San Francisco Preoperative Diffuse Glioma MRI Dataset.

Supplemental material is available for this article. Keywords: Informatics, MR Diffusion Tensor Imaging, MR Perfusion, MR Imaging, Neuro-Oncology, CNS, Brain/Brain Stem, Oncology, Radiogenomics, Radiology-Pathology Integration © RSNA, 2022.

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.

Application of a Domain-specific BERT for Detection of Speech Recognition Errors in Radiology Reports.

Purpose: To develop radiology domain-specific bidirectional encoder representations from transformers (BERT) models that can identify speech recognition (SR) errors and suggest corrections in radiology reports. Materials and Methods: A pretrained BERT model, Clinical BioBERT, was further pretrained on a corpus of 114 008 radiology reports between April 2016 and August 2019 that were retrospectively collected from two hospitals. Next, the model was fine-tuned on a training dataset of generated insertion, deletion, and substitution errors, creating Radiology BERT. This model was retrospectively evaluated on an independent dataset of radiology reports with generated errors (n = 18 885) and on unaltered report sentences (n = 2000) and prospectively evaluated on true clinical SR errors (n = 92). Correction Radiology BERT was separately trained to suggest corrections for detected deletion and substitution errors. Area under the receiver operating characteristic curve (AUC) and bootstrapped 95% CIs were calculated for each evaluation dataset. Results: Radiology-specific BERT had AUC values of >.99 (95% CI: >0.99, >0.99), 0.94 (95% CI: 0.93, 0.94), 0.98 (95% CI: 0.98, 0.98), and 0.97 (95% CI: 0.97, 0.97) for detecting insertion, deletion, substitution, and all errors, respectively, on the independently generated test set. Testing on unaltered report impressions revealed a sensitivity of 82% (28 of 34; 95% CI: 70%, 93%) and specificity of 88% (1521 of 1728; 95% CI: 87%, 90%). Testing on prospective SR errors showed an accuracy of 75% (69 of 92; 95% CI: 65%, 83%). Finally, the correct word was the top suggestion for 45.6% (475 of 1041; 95% CI: 42.5%, 49.3%) of errors. Conclusion: Radiology-specific BERT models fine-tuned on generated errors were able to identify SR errors in radiology reports and suggest corrections.Keywords: Computer Applications, Technology Assessment Supplemental material is available for this article. © RSNA, 2022See also the commentary by Abajian and Cheung in this issue.

An Integrated Analysis of Clinical, Genomic, and Imaging Features Reveals Predictors of Neurocognitive Outcomes in a Longitudinal Cohort of Pediatric Cancer Survivors, Enriched with CNS Tumors (Rad ART Pro).

Background: Neurocognitive deficits in pediatric cancer survivors occur frequently; however, individual outcomes are unpredictable. We investigate clinical, genetic, and imaging predictors of neurocognition in pediatric cancer survivors, with a focus on survivors of central nervous system (CNS) tumors exposed to radiation. Methods: One hundred eighteen patients with benign or malignant cancers (median diagnosis age: 7; 32% embryonal CNS tumors) were selected from an existing multi-institutional cohort (RadART Pro) if they had: 1) neurocognitive evaluation; 2) available DNA; 3) standard imaging. Utilizing RadART Pro, we collected clinical history, genomic sequencing, CNS imaging, and neurocognitive outcomes. We performed single nucleotide polymorphism (SNP) genotyping for candidate genes associated with neurocognition: COMT, BDNF, KIBRA, APOE, KLOTHO. Longitudinal neurocognitive testing were performed using validated computer-based CogState batteries. The imaging cohort was made of patients with available iron-sensitive (n = 28) and/or T2 FLAIR (n = 41) sequences. Cerebral microbleeds (CMB) were identified using a semi-automated algorithm. Volume of T2 FLAIR white matter lesions (WML) was measured using an automated method based on a convolutional neural network. Summary statistics were performed for patient characteristics, neurocognitive assessments, and imaging. Linear mixed effects and hierarchical models assessed patient characteristics and SNP relationship with neurocognition over time. Nested case-control analysis was performed to compare candidate gene carriers to non-carriers. Results: CMB presence at baseline correlated with worse performance in 3 of 7 domains, including executive function. Higher baseline WML volumes correlated with worse performance in executive function and verbal learning. No candidate gene reliably predicted neurocognitive outcomes; however, APOE ϵ4 carriers trended toward worse neurocognitive function over time compared to other candidate genes and carried the highest odds of low neurocognitive performance across all domains (odds ratio 2.85, P=0.002). Hydrocephalus and seizures at diagnosis were the clinical characteristics most frequently associated with worse performance in neurocognitive domains (5 of 7 domains). Overall, executive function and verbal learning were the most frequently negatively impacted neurocognitive domains. Conclusion: Presence of CMB, APOE ϵ4 carrier status, hydrocephalus, and seizures correlate with worse neurocognitive outcomes in pediatric cancer survivors, enriched with CNS tumors exposed to radiation. Ongoing research is underway to verify trends in larger cohorts.

Deep Learning to Predict Neonatal and Infant Brain Age from Myelination on Brain MRI Scans.

Background Assessment of appropriate brain myelination on T1- and T2-weighted MRI scans is based on gestationally corrected age (GCA) and requires subjective visual inspection of the brain with knowledge of normal myelination milestones. Purpose To develop a convolutional neural network (CNN) capable of estimating neonatal and infant GCA based on brain myelination on MRI scans. Materials and methods In this retrospective study from one academic medical center, brain MRI scans of patients aged 0-25 months with reported normal myelination were consecutively collected between January 1995 and June 2019. The GCA at MRI was manually calculated. After exclusion criteria were applied, T1- and T2-weighted MRI scans were preprocessed with skull stripping, linear registration, z scoring for normalization, and downsampling. A three-dimensional regression CNN was trained to predict GCA using mean absolute error (MAE) as its loss function. Attention maps were calculated using layer-wise relevance propagation. Models were validated on an external test set from the National Institutes of Health (NIH). Model MAEs were compared using Kruskal-Wallis and Mann-Whitney tests. Results A total of 518 neonates and infants (mean GCA, 67 weeks ± 33 [SD], 56% male) was included, comprising 469 T1-, 438 T2-, and 389 T1- and T2-weighted studies. Across 10 runs, MAEs of T1-, T2-, and T1- and T2-weighted networks were 9.8 ± 2.3, 9.1 ± 1.9, and 7.7 ± 1.7 weeks, respectively. Attention map analysis demonstrated increased network attention to the cerebellum, posterior white matter, and basal ganglia signal in neonates with GCA of less than 40 weeks and the anterior white matter signal in infants with GCA of more than 120 weeks, corresponding to the known progression of myelination. The T1- and T2-weighted network tested on the external NIH test set had an MAE of 9.1 weeks, which was reduced to 5.9 weeks with further training using half the external test set (P < .001). Conclusion A three-dimensional convolutional neural network can predict the gestationally corrected age of neonates and infants aged 0-25 months based on brain myelination patterns on T1- and T2-weighted MRI scans. © RSNA, 2022 Online supplemental material is available for this article.

Combining radiomics and deep convolutional neural network features from preoperative MRI for predicting clinically relevant genetic biomarkers in glioblastoma.

Background: Glioblastoma is the most common primary brain malignancy, yet treatment options are limited, and prognosis remains guarded. Individualized tumor genetic assessment has become important for accurate prognosis and for guiding emerging targeted therapies. However, challenges remain for widespread tumor genetic testing due to costs and the need for tissue sampling. The aim of this study is to evaluate a novel artificial intelligence method for predicting clinically relevant genetic biomarkers from preoperative brain MRI in patients with glioblastoma. Methods: We retrospectively analyzed preoperative MRI data from 400 patients with glioblastoma, IDH-wildtype or WHO grade 4 astrocytoma, IDH mutant who underwent resection and genetic testing. Nine genetic biomarkers were assessed: hotspot mutations of IDH1 or TERT promoter, pathogenic mutations of TP53, PTEN, ATRX, or CDKN2A/B, MGMT promoter methylation, EGFR amplification, and combined aneuploidy of chromosomes 7 and 10. Models were developed to predict biomarker status from MRI data using radiomics features, convolutional neural network (CNN) features, and a combination of both. Results: Combined model performance was good for IDH1 and TERT promoter hotspot mutations, pathogenic mutations of ATRX and CDKN2A/B, and combined aneuploidy of chromosomes 7 and 10, with receiver operating characteristic area under the curve (ROC AUC) >0.85 and was fair for all other tested biomarkers with ROC AUC >0.7. Combined model performance was statistically superior to individual radiomics and CNN feature models for prediction chromosome 7 and 10 aneuploidy, MGMT promoter methylation, and PTEN mutation. Conclusions: Combining radiomics and CNN features from preoperative MRI yields improved noninvasive genetic biomarker prediction performance in patients with WHO grade 4 diffuse astrocytic gliomas.

Diagnostic Approach to Pulsatile Tinnitus: A Narrative Review.

Importance: Pulsatile tinnitus is a debilitating symptom affecting millions of Americans and can be a harbinger of hemorrhagic or ischemic stroke. Careful diagnostic evaluation of pulsatile tinnitus is critical in providing optimal care and guiding the appropriate treatment strategy. Observations: An underlying cause of pulsatile tinnitus can be identified in more than 70% of patients with a thorough evaluation. We advocate categorizing the myriad causes of pulsatile tinnitus into structural, metabolic, and vascular groups. Structural causes of pulsatile tinnitus include neoplasms and temporal bone pathologic abnormalities. Metabolic causes of pulsatile tinnitus include ototoxic medications and systemic causes of high cardiac output. Vascular causes of pulsatile tinnitus include idiopathic intracranial hypertension and dural arteriovenous fistulas. This categorization facilitates a practical evaluation, referral, and treatment pattern. Conclusions and Relevance: Categorizing the underlying cause of pulsatile tinnitus ensures that dangerous causes of pulsatile tinnitus are not missed, and that patients receive the appropriate care from the proper specialist when needed.

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.

Feasibility of Simulated Postcontrast MRI of Glioblastomas and Lower-Grade Gliomas by Using Three-dimensional Fully Convolutional Neural Networks.

PURPOSE: To evaluate the feasibility and accuracy of simulated postcontrast T1-weighted brain MR images generated by using precontrast MR images in patients with brain glioma. MATERIALS AND METHODS: In this retrospective study, a three-dimensional deep convolutional neural network was developed to simulate T1-weighted postcontrast images from eight precontrast sequences in 400 patients (mean age, 57 years; 239 men; from 2015 to 2020), including 332 with glioblastoma and 68 with lower-grade gliomas. Performance was evaluated by using quantitative image similarity and error metrics and enhancing tumor overlap analysis. Performance was also assessed on a multicenter external dataset (n = 286 from the 2019 Multimodal Brain Tumor Segmentation Challenge; mean age, 60 years; ratio of men to women unknown) by using transfer learning. A subset of cases was reviewed by neuroradiologist readers to assess whether simulated images affected the ability to determine the tumor grade. RESULTS: Simulated whole-brain postcontrast images were both qualitatively and quantitatively similar to the real postcontrast images in terms of quantitative image similarity (structural similarity index of 0.84 ± 0.05), pixelwise error (symmetric mean absolute percent error of 3.65%), and enhancing tumor compartment overlap (Dice coefficient, 0.65 ± 0.25). Similar results were achieved with the external dataset (Dice coefficient, 0.62 ± 0.27). There was no difference in the ability of the neuroradiologist readers to determine the tumor grade in real versus simulated images (accuracy, 87.7% vs 90.6%; P = .87). CONCLUSION: The developed model was capable of producing simulated postcontrast T1-weighted MR images that were similar to real acquired images as determined by both quantitative analysis and radiologist assessment.Keywords: MR-Contrast Agent, MR-Imaging, CNS, Brain/Brain Stem, Contrast Agents-Intravenous, Neoplasms-Primary, Experimental Investigations, Technology Assessment, Supervised Learning, Transfer Learning, Convolutional Neural Network, Deep Learning Algorithms, Machine Learning Algorithms Supplemental material is available for this article. © RSNA, 2021.

Detection of Neoplasms by Metagenomic Next-Generation Sequencing of Cerebrospinal Fluid.

Importance: Cerebrospinal fluid (CSF) cytologic testing and flow cytometry are insensitive for diagnosing neoplasms of the central nervous system (CNS). Such clinical phenotypes can mimic infectious and autoimmune causes of meningoencephalitis. Objective: To ascertain whether CSF metagenomic next-generation sequencing (mNGS) can identify aneuploidy, a hallmark of malignant neoplasms, in difficult-to-diagnose cases of CNS malignant neoplasm. Design, Setting, and Participants: Two case-control studies were performed at the University of California, San Francisco (UCSF). The first study used CSF specimens collected at the UCSF Clinical Laboratories between July 1, 2017, and December 31, 2019, and evaluated test performance in specimens from patients with a CNS malignant neoplasm (positive controls) or without (negative controls). The results were compared with those from CSF cytologic testing and/or flow cytometry. The second study evaluated patients who were enrolled in an ongoing prospective study between April 1, 2014, and July 31, 2019, with presentations that were suggestive of neuroinflammatory disease but who were ultimately diagnosed with a CNS malignant neoplasm. Cases of individuals whose tumors could have been detected earlier without additional invasive testing are discussed. Main Outcomes and Measures: The primary outcome measures were the sensitivity and specificity of aneuploidy detection by CSF mNGS. Secondary subset analyses included a comparison of CSF and tumor tissue chromosomal abnormalities and the identification of neuroimaging characteristics that were associated with test performance. Results: Across both studies, 130 participants were included (median [interquartile range] age, 57.5 [43.3-68.0] years; 72 men [55.4%]). The test performance study used 125 residual laboratory CSF specimens from 47 patients with a CNS malignant neoplasm and 56 patients with other neurological diseases. The neuroinflammatory disease study enrolled 12 patients and 17 matched control participants. The sensitivity of the CSF mNGS assay was 75% (95% CI, 63%-85%), and the specificity was 100% (95% CI, 96%-100%). Aneuploidy was detected in 64% (95% CI, 41%-83%) of the patients in the test performance study with nondiagnostic cytologic testing and/or flow cytometry, and in 55% (95% CI, 23%-83%) of patients in the neuroinflammatory disease study who were ultimately diagnosed with a CNS malignant neoplasm. Of the patients in whom aneuploidy was detected, 38 (90.5%) had multiple copy number variations with tumor fractions ranging from 31% to 49%. Conclusions and Relevance: This case-control study showed that CSF mNGS, which has low specimen volume requirements, does not require the preservation of cell integrity, and was orginally developed to diagnose neurologic infections, can also detect genetic evidence of a CNS malignant neoplasm in patients in whom CSF cytologic testing and/or flow cytometry yielded negative results with a low risk of false-positive results.

Automated multiclass tissue segmentation of clinical brain MRIs with lesions.

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.