ABSTRACT
Abstract Background Sjogren-Larsson syndrome (SLS) is a neurocutaneous disease with an autosomal recessive inheritance, caused by mutations in the gene that encodes fatty aldehyde dehydrogenase (ALDH3A2), clinically characterized by ichthyosis, spastic diplegia, and cognitive impairment. Brain imaging plays an essential role in the diagnosis, demonstrating a nonspecific leukoencephalopathy. Data regarding brain atrophy and grey matter involvement is scarce and discordant. Objective We performed a volumetric analysis of the brain of two siblings with SLS with the aim of detecting deep grey matter nuclei, cerebellar grey matter, and brainstem volume reduction in these patients. Methods Volume data obtained from the brain magnetic resonance imaging (MRI) of the two patients using an automated segmentation software (Freesurfer) was compared with the volumes of a healthy control group. Results Statistically significant volume reduction was found in the cerebellum cortex, the brainstem, the thalamus, and the pallidum nuclei. Conclusion Volume reduction in grey matter leads to the hypothesis that SLS is not a pure leukoencephalopathy. Grey matter structures affected in the present study suggest a dysfunction more prominent in the thalamic motor pathways.
Resumo Antecedentes A Síndrome de Sjogren-Larsson (SSL) é uma doença neurocutânea de herança autossômica recessiva, causada por mutações no gene que codifica a aldeído graxo desidrogenase (ALDH3A2), caracterizada clinicamente por ictiose, diplegia espástica e comprometimento cognitivo. A imagiologia cerebral desempenha um papel essencial no diagnóstico, demonstrando uma leucoencefalopatia inespecífica. Dados sobre atrofia cerebral e envolvimento da substância cinzenta são escassos e discordantes. Objetivo Realizamos uma análise volumétrica do cérebro de dois irmãos com SLS com o objetivo de detectar núcleos profundos de substância cinzenta, substância cerebral cinzenta e redução do volume do tronco encefálico nestes pacientes. Métodos Os dados de volume obtidos da ressonância magnética (RM) cerebral dos dois pacientes usando um software de segmentação automática (Freesurfer) foram comparados com os volumes de um grupo controle saudável. Resultados Redução de volume estatisticamente significativa foi encontrada no córtex do cerebelo, no tronco cerebral, no tálamo e nos núcleos pálidos. Conclusão A redução do volume da substância cinzenta leva à hipótese de que a SSL não é uma leucoencefalopatia pura. As estruturas da substância cinzenta afetadas no presente estudo sugerem uma disfunção mais proeminente nas vias motoras talâmicas.
ABSTRACT
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.(AU)