Search

A encefalopatia traumática crônica (ETC) representa a consequência a longo prazo de traumatismos cranioencefálicos (TCE), podendo estar relacionada a uma tauopatia progressiva. Ela tem sido reconhecida como uma causa importante de declínio cognitivo em pacientes submetidos a TCEs leves repetitivos por longos períodos, como no contexto esportivo do boxe e futebol americano. Dada a possibilidade de ocorrência desta doença neurodegenerativa em jogadores profissionais de futebol, foi realizado um estudo com o objetivo de avaliar se um dos parâmetros de ressonância magnética (RM), a tratografia, pode ser utilizada como biomarcador de imagem para avaliação de pacientes com suspeita de ETC. Foram avaliados 20 ex-jogadores profissionais e 20 voluntários saudáveis pareados por idade, os quais foram submetidos a avaliação clínica, testes neuropsicológicos e estudo de Ressonância Magnética do encéfalo. As imagens da sequência de tensor de difusão foram processadas e analisadas através das ferramentas encontradas no programa FSL (FMRIB Software Library), o qual possui a ferramenta TBSS (Tract-Based Spacial Statistics) na qual foi realizada a análise estatística, sendo adotado o nível de significância de 5% (alfa = 0,05). Foram analisados dados dos mapas de anisotropia fracionada (FA) e difusividade média (MD), bem como difusividade axial (AD) e difusividade radial (RD). Através de análise baseada em voxel comparando os mapas de FA, MD, AD e RD dos jogadores e controles, observamos o aumento de MD no esplênio do corpo caloso, coroa radiada e na substância branca subcortical parietal direita. Os demais mapas não apresentaram alterações estatisticamente significativas. Ao compararmos jogadores com MEEM alterado (abaixo de 1,5 desvios padrões), não encontramos resultados estatisticamente significativos, contudo foi observada uma tendência a redução da FA nas regiões frontobasais, rostro do corpo caloso à direita e centro semioval à esquerda. Tais achados podem estar relacionados a alterações na integridade e estrutura da substância branca nos jogadores de futebol aposentados Chronic traumatic encephalopathy (CTE) represents the long-term consequence of head trauma and may be secondary to a progressive tauopathy. It has been recognized as an important cause of cognitive decline in patients who have undergone repetitive mild traumatic brain injury (TBI) for long periods of time, such as football and boxing players, in the sports context. Given the importance of soccer practice in our environment and its potential predisposition to CTE, a study was carried out with the objective of determining whether one of the magnetic resonance imaging (MRI) parameters, tractography, can be used as an imaging biomarker for evaluation of patients with suspected CTE. Twenty former professional players and 20 age-matched healthy volunteers underwent a clinical evaluation, neuropsychological testing and a brain PET-MRI. The diffusion tensor images were processed and analyzed using the tools found in the FSL program (FMRIB Software Library), which has the TBSS (Tract-Based Spatial Statistics) tool where we performed the statistical analysis, with a 5% significance level adopted (alpha = 0.05). Data from fractional anisotropy (FA) and mean diffusivity (MD) maps, as well as axial diffusivity (AD) and radial diffusivity (RD) were analyzed. Through voxel-based analysis comparing the FA, MD, AD and RD maps of soccer players and controls groups, we observed an increased MD in the splenium of the corpus callosum, corona radiata and right parietal subcortical white matter in the players group. The other maps showed no statistically significant alterations. When comparing the soccer players group with altered MEEM (below 1.5 standard deviations), we did not find statistically significant results, however, a tendency for reduced FA was observed in the frontobasal regions, right aspect of the corpus callosum rostrum and left centrum semiovale. Such findings may be related to changes in the integrity and structure of the white matter in retired soccer players

We describe the curation, annotation methodology and characteristics of the dataset used in an artificial intelligence challenge for detection and localization of COVID-19 on chest radiographs. The chest radiographs were annotated by an international group of radiologists into four mutually exclusive categories, including “typical”, “indeterminate”, and “atypical appearance” for COVID-19, or “negative for pneumonia”, adapted from previously published guidelines, and bounding boxes were placed on airspace opacities. This dataset and respective annotations are freely available to all researchers for academic and noncommercial use.

OBJECTIVES: Atypical teratoid/rhabdoid tumor (AT/RT) is a rare, highly malignant tumor of the central nervous system with poor prognosis. Nowadays, multimodal management, including surgery, chemotherapy (CMT), radiation therapy (RT) and Bone Marrow Transplantation (BMT). The aim of this study was to assess the experience and survival in a center of reference of treatment in childhood cancer in Brazil. PATIENTS AND METHODS: Medical records of AT/RT patients who underwent surgery from 2008 to 2020 at a center of childhood cancer treatment (ITACI) in São Paulo University were retrospectively reviewed and statistically analyzed. RESULTS: Eight patients (2 males and 6 females) were presented with AT/RTs. Median age during presentation was 22 months (range, 0 - 6 years). Seven patients (88%) were < 18 months and one patient were >18 months. Tumor location was supratentorial in four patients, infratentorial in 2 patients. Kidney disease as the primary diagnosis in 2 patients (25%). Surgical treatment was performed in 4 patients. Seven children underwent total CMT and 3 children were treated with RT. Only 3 patients underwent Autologous Bone Marrow Transplantation (ABMT). The chemotherapy management protocol of the patients was variable: 2 patients received the EU-RHAB protocol, 2 patients received the HEAD START III protocol, 3 patients received chemotherapy in the ICE regimen (Ifosfamide + Carboplatin + Etoposide) and 1 patient received chemotherapy in the CDDP+CTX+VCR (Cyclophosphamide + Cisplatin + Vincristine) regimen. All patients had episodes of neutropenic fever when they received chemotherapy, requiring hospitalization and use of an antibiotic treatment. Among the 8 patients analyzed, all died. CONCLUSIONS: Despite progress in treatment, AT/RT of the CNS disease or primary kidney disease associated with a lack of standardization in a regimen contributes to the dismal prognosis. There is a high mortality in patients with AT/RT, similar to that found in the literature.

Summary Background The CNS manifestations of COVID-19 in children have primarily been described in case reports, which limit the ability to appreciate the full spectrum of the disease in paediatric patients. We aimed to identify enough cases that could be evaluated in aggregate to better understand the neuroimaging manifestations of COVID-19 in the paediatric population. Methods An international call for cases of children with encephalopathy related to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and abnormal neuroimaging findings was made. Clinical history and associated plasma and cerebrospinal fluid data were requested. These data were reviewed by a central neuroradiology panel, a child neurologist, and a paediatric infectious diseases expert. The children were categorised on the basis of their time of probable exposure to SARS-CoV-2. In addition, cases were excluded when a direct link to SARS-CoV-2 infection could not be established or an established alternate diagnostic cause could be hypothesised. The accepted referral centre imaging data, from ten countries, were remotely reviewed by a central panel of five paediatric neuroradiologists and a consensus opinion obtained on the imaging findings. Findings 38 children with neurological disease related to SARS-CoV-2 infection were identified from France (n=13), the UK (n=8), the USA (n=5), Brazil (n=4), Argentina (n=4), India (n=2), Peru (n=1), and Saudi Arabia (n=1). Recurring patterns of disease were identified, with neuroimaging abnormalities ranging from mild to severe. The most common imaging patterns were postinfectious immune-mediated acute disseminated encephalomyelitis-like changes of the brain (16 patients), myelitis (eight patients), and neural enhancement (13 patients). Cranial nerve enhancement could occur in the absence of corresponding neurological symptoms. Splenial lesions (seven patients) and myositis (four patients) were predominantly observed in children with multisystem inflammatory syndrome. Cerebrovascular complications in children were less common than in adults. Significant pre-existing conditions were absent and most children had favourable outcomes. However, fatal atypical CNS co-infections developed in four previously healthy children infected with SARS-CoV-2. Interpretation Acute-phase and delayed-phase SARS-CoV-2-related CNS abnormalities are seen in children. Recurring patterns of disease and atypical neuroimaging manifestations can be found and should be recognised being as potentially due to SARS-CoV-2 infection as an underlying aetiological factor. Studies of paediatric specific cohorts are needed to better understand the effects of SARS-CoV-2 infection on the CNS at presentation and on long-term follow-up in children. Funding American Society of Pediatric Neuroradiology, University of Manchester (Manchester, UK). Video Abstract Neuroimaging manifestations in children with SARS-CoV-2 infection

PurposeTo improve and test the generalizability of a deep learning-based model for assessment of COVID-19 lung disease severity on chest radiographs (CXRs) from different patient populations.Materials and MethodsA published convolutional Siamese neural network-based model previously trained on hospitalized patients with COVID-19 was tuned using 250 outpatient CXRs. This model produces a quantitative measure of COVID-19 lung disease severity (pulmonary x-ray severity (PXS) score). The model was evaluated on CXRs from four test sets, including 3 from the United States (patients hospitalized at an academic medical center (N=154), patients hospitalized at a community hospital (N=113), and outpatients (N=108)) and 1 from Brazil (patients at an academic medical center emergency department (N=303)). Radiologists from both countries independently assigned reference standard CXR severity scores, which were correlated with the PXS scores as a measure of model performance (Pearson r). The Uniform Manifold Approximation and Projection (UMAP) technique was used to visualize the neural network results.ResultsTuning the deep learning model with outpatient data improved model performance in two United States hospitalized patient datasets (r=0.88 and r=0.90, compared to baseline r=0.86). Model performance was similar, though slightly lower, when tested on the United States outpatient and Brazil emergency department datasets (r=0.86 and r=0.85, respectively). UMAP showed that the model learned disease severity information that generalized across test sets.ConclusionsPerformance of a deep learning-based model that extracts a COVID-19 severity score on CXRs improved using training data from a different patient cohort (outpatient versus hospitalized) and generalized across multiple populations.

PURPOSE: To develop a deep learning model for detecting brain abnormalities on MR images. MATERIALS AND METHODS: In this retrospective study, a deep learning approach using T2-weighted fluid-attenuated inversion recovery images was developed to classify brain MRI findings as “likely normal” or “likely abnormal.” A convolutional neural network model was trained on a large, heterogeneous dataset collected from two different continents and covering a broad panel of pathologic conditions, including neoplasms, hemorrhages, infarcts, and others. Three datasets were used. Dataset A consisted of 2839 patients, dataset B consisted of 6442 patients, and dataset C consisted of 1489 patients and was only used for testing. Datasets A and B were split into training, validation, and test sets. A total of three models were trained: model A (using only dataset A), model B (using only dataset B), and model A + B (using training datasets from A and B). All three models were tested on subsets from dataset A, dataset B, and dataset C separately. The evaluation was performed by using annotations based on the images, as well as labels based on the radiology reports. RESULTS: Model A trained on dataset A from one institution and tested on dataset C from another institution reached an F1 score of 0.72 (95% CI: 0.70, 0.74) and an area under the receiver operating characteristic curve of 0.78 (95% CI: 0.75, 0.80) when compared with findings from the radiology reports. CONCLUSION: The model shows relatively good performance for differentiating between likely normal and likely abnormal brain examination findings by using data from different institutions. Keywords: MR-Imaging, Head/Neck, Computer Applications-General (Informatics), Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms © RSNA, 2021 Supplemental material is available for this article.