RESUMO

BACKGROUND AND PURPOSE: Thrombotic microangiopathy (TMA) is a group of microvascular occlusive disorders that presents with neurological involvement in up to 87% of the cases. Although the central nervous system (CNS) is an important target organ in TMA, the role of neurological manifestations in the disease clinical course is not well established. In this study, we described the neurological manifestations and CNS radiological aspects in patients with a first, acute TMA event. We also examined the association between severe neurological involvement and adverse clinical outcomes in TMA. METHODS: A cohort of patients diagnosed with a first TMA event between 1995 and 2016 was included, their medical charts and imaging tests were retrospectively evaluated. RESULTS: A total of 49 patients were included, 85.7% were women and the mean age was 36.5 years-old (SD 13.0). Neurological manifestations were described in 85.7% of the patients, most of them (88%) were considered severe and consisted of confusion, compromised sensorimotor function, stupor, seizures, and personality change. Imaging tests were performed in 62% of the patients with neurological manifestations and detected acute CNS lesions, such as posterior reversible encephalopathy syndrome, hemorrhagic and ischemic stroke were observed, in 7 (27%) of them. While the need for intensive care unit admission was greater and longer among patients with severe neurological manifestations, the number of plasma exchange sessions, the total duration of hospitalization and in-hospital death were similar between groups. CONCLUSIONS: Severe neurological manifestations are common in first TMA events and are responsible for a worse disease presentation at admission. While the effect of neurological manifestations on acute TMA clinical course seems to be modest, these manifestations may have an important impact on the development of chronic cognitive impairment, which highlights the need for proper diagnosis and treatment.

Assuntos

Síndrome da Leucoencefalopatia Posterior , Microangiopatias Trombóticas , Adulto , Progressão da Doença , Feminino , Mortalidade Hospitalar , Humanos , Masculino , Síndrome da Leucoencefalopatia Posterior/complicações , Estudos Retrospectivos , Fatores de Risco , Microangiopatias Trombóticas/diagnóstico por imagem , Microangiopatias Trombóticas/etiologia , Microangiopatias Trombóticas/terapia

RESUMO

BACKGROUND: Neuroimaging strategies are essential to locate, to elucidate the etiology, and to the follow up of brain disease patients. Magnetic resonance imaging (MRI) provides good cerebral soft-tissue contrast detection and diagnostic sensitivity. Inflammatory lesions and tumors are common brain diseases that may present a similar pattern of a cerebral ring enhancing lesion on MRI, and non-enhancing core (which may reflect cystic components or necrosis) leading to misdiagnosis. Texture analysis (TA) and machine learning approaches are computer-aided diagnostic tools that can be used to assist radiologists in such decisions. METHODS: In this study, we combined texture features with machine learning (ML) methods aiming to differentiate brain tumors from inflammatory lesions in magnetic resonance imaging. Retrospective examination of 67 patients, with a pattern of a cerebral ring enhancing lesion, 30 with inflammatory, and 37 with tumoral lesions were selected. Three different MRI sequences and textural features were extracted using gray level co-occurrence matrix and gray level run length. All diagnoses were confirmed by histopathology, laboratorial analysis or MRI. RESULTS: The features extracted were processed for the application of ML methods that performed the classification. T1-weighted images proved to be the best sequence for classification, in which the differentiation between inflammatory and tumoral lesions presented high accuracy (0.827), area under ROC curve (0.906), precision (0.837), and recall (0.912). CONCLUSION: The algorithm obtained textures capable of differentiating brain tumors from inflammatory lesions, on T1-weghted images without contrast medium using the Random Forest machine learning classifier.