Search

Neuroimaging provides rapid, noninvasive visualization of central nervous system infections for optimal diagnosis and management. Generalizable and characteristic imaging patterns help radiologists distinguish different types of intracranial infections including meningitis and cerebritis from a variety of bacterial, viral, fungal, and/or parasitic causes. Here, we describe key radiologic patterns of meningeal enhancement and diffusion restriction through profiles of meningitis, cerebritis, abscess, and ventriculitis. We discuss various imaging modalities and recent diagnostic advances such as deep learning through a survey of intracranial pathogens and their radiographic findings. Moreover, we explore critical complications and differential diagnoses of intracranial infections.

BACKGROUND. Neuroinflammation is a well-known feature of early Alzheimer disease (AD) yet astrocyte activation has not been extensively evaluated with in vivo imaging in Mild Cognitive Impairment (MCI) due to amyloid plaque pathology. Unlike neurons, astrocytes metabolize acetate, which has potential as a glial biomarker in neurodegeneration in response to AD pathologic features. Since the medial temporal lobe (MTL) is a hotspot for AD neurodegeneration and inflammation, we assessed astrocyte activity in the MTL and compared to amyloid and cognition. METHODS. We evaluate spatial patterns of in vivo astrocyte activation and their relationships to amyloid deposition and cognition in a cross-sectional pilot study of 6 participants with MCI and 5 cognitively normal (CN) participants. We measure (11)C-acetate and (18)F-florbetaben amyloid standardized uptake values ratios (SUVRs) and kinetic flux compared to cerebellum on positron emission tomography (PET), with magnetic resonance imaging and neurocognitive testing. RESULTS. Medial temporal lobe (MTL) (11)C-acetate SUVR was significantly elevated in MCI compared to CN participants (P = 0.03; Cohen d = 1.76). Moreover, MTL (11)C-acetate SUVR displayed significant associations with global and regional amyloid burden in MCI. Greater MTL (11)C-acetate retention was significantly related with worse neurocognitive measures including the Montreal Cognitive Assessment (P = 0.001), Word List Recall memory (P = 0.03), Boston Naming Test (P = 0.04) and Trails B test (P = 0.04). CONCLUSIONS. While further validation is required, this exploratory pilot study suggests a potential role for (11)C-acetate PET as a neuroinflammatory biomarker in MCI and early AD to provide clinical and translational insights into astrocyte activation as a pathological response to amyloid.

Limbic-predominant age-related TDP-43 encephalopathy (LATE) is a recently defined neurodegenerative disease characterized by amnestic phenotype and pathological inclusions of TAR DNA-binding protein 43 (TDP-43). LATE is distinct from rarer forms of TDP-43 diseases such as frontotemporal lobar degeneration with TDP-43 but is also a common copathology with Alzheimer's disease (AD) and cerebrovascular disease and accelerates cognitive decline. LATE contributes to clinicopathologic heterogeneity in neurodegenerative diseases, so it is imperative to distinguish LATE from other etiologies.Novel biomarkers for LATE are being developed with magnetic resonance imaging (MRI) and positron emission tomography (PET). When cooccurring with AD, LATE exhibits identifiable patterns of limbic-predominant atrophy on MRI and hypometabolism on

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

Alzheimer's disease (AD) is defined by amyloid (A) and tau (T) pathologies, with T better correlated to neurodegeneration (N). However, T and N have complex regional relationships in part related to non-AD factors that influence N. With machine learning, we assessed heterogeneity in

With 2020 finally behind us, we can begin to think about how the historic events that took place will be understood in years to come. To do so, we asked young scientists this question: What new word or phrase would you add to the dictionary to help scientists explain the events of 2020 to future generations? Read a selection of the best responses below. Follow NextGen Voices on Twitter with hashtag #NextGenSci. Read previous NextGen Voices survey results at https://science.sciencemag.org/collection/nextgen-voices.

Recent advances in artificial intelligence (AI) and deep learning (DL) hold promise to augment neuroimaging diagnosis for patients with brain tumors and stroke. Here, the authors review the diverse landscape of emerging neuroimaging applications of AI, including workflow optimization, lesion segmentation, and precision education. Given the many modalities used in diagnosing neurologic diseases, AI may be deployed to integrate across modalities (MR imaging, computed tomography, PET, electroencephalography, clinical and laboratory findings), facilitate crosstalk among specialists, and potentially improve diagnosis in patients with trauma, multiple sclerosis, epilepsy, and neurodegeneration. Together, there are myriad applications of AI for neuroradiology."

Background Although artificial intelligence (AI) shows promise across many aspects of radiology, the use of AI to create differential diagnoses for rare and common diseases at brain MRI has not been demonstrated. Purpose To evaluate an AI system for generation of differential diagnoses at brain MRI compared with radiologists. Materials and Methods This retrospective study tested performance of an AI system for probabilistic diagnosis in patients with 19 common and rare diagnoses at brain MRI acquired between January 2008 and January 2018. The AI system combines data-driven and domain-expertise methodologies, including deep learning and Bayesian networks. First, lesions were detected by using deep learning. Then, 18 quantitative imaging features were extracted by using atlas-based coregistration and segmentation. Third, these image features were combined with five clinical features by using Bayesian inference to develop probability-ranked differential diagnoses. Quantitative feature extraction algorithms and conditional probabilities were fine-tuned on a training set of 86 patients (mean age, 49 years ± 16 [standard deviation]; 53 women). Accuracy was compared with radiology residents, general radiologists, neuroradiology fellows, and academic neuroradiologists by using accuracy of top one, top two, and top three differential diagnoses in 92 independent test set patients (mean age, 47 years ± 18; 52 women). Results For accuracy of top three differential diagnoses, the AI system (91% correct) performed similarly to academic neuroradiologists (86% correct; P = .20), and better than radiology residents (56%; P < .001), general radiologists (57%; P < .001), and neuroradiology fellows (77%; P = .003). The performance of the AI system was not affected by disease prevalence (93% accuracy for common vs 85% for rare diseases; P = .26). Radiologists were more accurate at diagnosing common versus rare diagnoses (78% vs 47% across all radiologists; P < .001). Conclusion An artificial intelligence system for brain MRI approached overall top one, top two, and top three differential diagnoses accuracy of neuroradiologists and exceeded that of less-specialized radiologists. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Zaharchuk in this issue.

PURPOSE: To develop and validate a system that could perform automated diagnosis of common and rare neurologic diseases involving deep gray matter on clinical brain MRI studies. MATERIALS AND METHODS: In this retrospective study, multimodal brain MRI scans from 212 patients (mean age, 55 years ± 17 [standard deviation]; 113 women) with 35 neurologic diseases and normal brain MRI scans obtained between January 2008 and January 2018 were included (110 patients in the training set, 102 patients in the test set). MRI scans from 178 patients (mean age, 48 years ± 17; 106 women) were used to supplement training of the neural networks. Three-dimensional convolutional neural networks and atlas-based image processing were used for extraction of 11 imaging features. Expert-derived Bayesian networks incorporating domain knowledge were used for differential diagnosis generation. The performance of the artificial intelligence (AI) system was assessed by comparing diagnostic accuracy with that of radiologists of varying levels of specialization by using the generalized estimating equation with robust variance estimator for the top three differential diagnoses (T3DDx) and the correct top diagnosis (TDx), as well as with receiver operating characteristic analyses. RESULTS: In the held-out test set, the imaging pipeline detected 11 key features on brain MRI scans with 89% accuracy (sensitivity, 81%; specificity, 95%) relative to academic neuroradiologists. The Bayesian network, integrating imaging features with clinical information, had an accuracy of 85% for T3DDx and 64% for TDx, which was better than that of radiology residents (n = 4; 56% for T3DDx, 36% for TDx; P < .001 for both) and general radiologists (n = 2; 53% for T3DDx, 31% for TDx; P < .001 for both). The accuracy of the Bayesian network was better than that of neuroradiology fellows (n = 2) for T3DDx (72%; P = .003) but not for TDx (59%; P = .19) and was not different from that of academic neuroradiologists (n = 2; 84% T3DDx, 65% TDx; P > .09 for both). CONCLUSION: A hybrid AI system was developed that simultaneously provides a quantitative assessment of disease burden, explainable intermediate imaging features, and a probabilistic differential diagnosis that performed at the level of academic neuroradiologists. This type of approach has the potential to improve clinical decision making for common and rare diseases. Supplemental material is available for this article. © RSNA, 2020

BACKGROUND AND PURPOSE: Most brain lesions are characterized by hyperintense signal on FLAIR. We sought to develop an automated deep learning–based method for segmentation of abnormalities on FLAIR and volumetric quantification on clinical brain MRIs across many pathologic entities and scanning parameters. We evaluated the performance of the algorithm compared with manual segmentation and existing automated methods. MATERIALS AND METHODS: We adapted a U-Net convolutional neural network architecture for brain MRIs using 3D volumes. This network was retrospectively trained on 295 brain MRIs to perform automated FLAIR lesion segmentation. Performance was evaluated on 92 validation cases using Dice scores and voxelwise sensitivity and specificity, compared with radiologists9 manual segmentations. The algorithm was also evaluated on measuring total lesion volume. RESULTS: Our model demonstrated accurate FLAIR lesion segmentation performance (median Dice score, 0.79) on the validation dataset across a large range of lesion characteristics. Across 19 neurologic diseases, performance was significantly higher than existing methods (Dice, 0.56 and 0.41) and approached human performance (Dice, 0.81). There was a strong correlation between the predictions of lesion volume of the algorithm compared with true lesion volume (ρ = 0.99). Lesion segmentations were accurate across a large range of image-acquisition parameters on >30 different MR imaging scanners. CONCLUSIONS: A 3D convolutional neural network adapted from a U-Net architecture can achieve high automated FLAIR segmentation performance on clinical brain MR imaging across a variety of underlying pathologies and image acquisition parameters. The method provides accurate volumetric lesion data that can be incorporated into assessments of disease burden or into radiologic reports.

We asked young scientists: Are our schools and universities adequately prepared to educate young people for future challenges? What is the most pressing issue in your field, and what one improvement could your country make to its current education system to prepare students to face it? The responses expressed concerns about the current state of education in countries around the world. Many students lack access to the information they need, and those with access are often constrained by curriculum that emphasizes rote learning and isolated subjects. Our respondents suggested a variety of improvements to prepare the next generation for success.

CTCF is an architectural protein with a critical role in connecting higher-order chromatin folding in pluripotent stem cells. Recent reports have suggested that CTCF binding is more dynamic during development than previously appreciated. Here, we set out to understand the extent to which shifts in genome-wide CTCF occupancy contribute to the 3D reconfiguration of fine-scale chromatin folding during early neural lineage commitment. Unexpectedly, we observe a sharp decrease in CTCF occupancy during the transition from naïve/primed pluripotency to multipotent primary neural progenitor cells (NPCs). Many pluripotency gene-enhancer interactions are anchored by CTCF, and its occupancy is lost in parallel with loop decommissioning during differentiation. Conversely, CTCF binding sites in NPCs are largely preexisting in pluripotent stem cells. Only a small number of CTCF sites arise de novo in NPCs. We identify another zinc finger protein, Yin Yang 1 (YY1), at the base of looping interactions between NPC-specific genes and enhancers. Putative NPC-specific enhancers exhibit strong YY1 signal when engaged in 3D contacts and negligible YY1 signal when not in loops. Moreover, siRNA knockdown of Yy1 specifically disrupts interactions between key NPC enhancers and their target genes. YY1-mediated interactions between NPC regulatory elements are often nested within constitutive loops anchored by CTCF. Together, our results support a model in which YY1 acts as an architectural protein to connect developmentally regulated looping interactions; the location of YY1-mediated interactions may be demarcated in development by a preexisting topological framework created by constitutive CTCF-mediated interactions.

In the era of personalized medicine, the emphasis of health care is shifting from populations to individuals. Artificial intelligence (AI) is capable of learning without explicit instruction and has emerging applications in medicine, particularly radiology. Whereas much attention has focused on teaching radiology trainees about AI, here our goal is to instead focus on how AI might be developed to better teach radiology trainees. While the idea of using AI to improve education is not new, the application of AI to medical and radiological education remains very limited. Based on the current educational foundation, we highlight an AI-integrated framework to augment radiology education and provide use case examples informed by our own institution’s practice. The coming age of “AI-augmented radiology” may enable not only “precision medicine” but also what we describe as “precision medical education,” where instruction is tailored to individual trainees based on their learning styles and needs.