Search

Significance: Detection and characterization of coronary atherosclerotic plaques often need reviews of a large number of optical coherence tomography (OCT) imaging slices to make a clinical decision. However, it is a challenge to manually review all the slices and consider the interrelationship between adjacent slices. Approach: Inspired by the recent success of deep convolutional network on the classification of medical images, we proposed a ResNet-3D network for classification of coronary plaque calcification in OCT pullbacks. The ResNet-3D network was initialized with a trained ResNet-50 network and a three-dimensional convolution filter filled with zeros padding and non-zeros padding with a convolutional filter. To retrain ResNet-50, we used a dataset of ∼4860 OCT images, derived by 18 entire pullbacks from different patients. In addition, we investigated a two-phase training method to address the data imbalance. For an improved performance, we evaluated different input sizes for the ResNet-3D network, such as 3, 5, and 7 OCT slices. Furthermore, we integrated all ResNet-3D results by majority voting. Results: A comparative analysis proved the effectiveness of the proposed ResNet-3D networks against ResNet-2D network in the OCT dataset. The classification performance (F1-scores=94% for non-zeros padding and F1-score=96% for zeros padding) demonstrated the potential of convolutional neural networks (CNNs) in classifying plaque calcification. Conclusions: This work may provide a foundation for further work in extending the CNN to voxel segmentation, which may lead to a supportive diagnostic tool for assessment of coronary plaque vulnerability.

Neurocysticercosis is a major cause of epilepsy in developing countries and is endemic in Brazil. To test the hypothesis that the aetiological profile of patients with intractable epilepsy in Brazil includes neurocysticercosis, we conducted a cross sectional study investigating the aetiology of intractable epilepsy.A total of 512 patients evaluated at the outpatient clinic for intractable epilepsy at the Ribeirão Preto School of Medicine were included in the survey. Medical intractability was determined on the basis of seizure incidence and severity, and response to appropriate epilepsy management. Neuroimaging included brain CT with non-contrasted and contrasted phases and high resolution MRI. Patients were divided into neurocysticercosis and non-neurocysticercosis groups according to previous diagnostic criteria.The most common epileptogenic lesions were mesial temporal sclerosis (MTS; 56.0%), malformations of cortical development (12.1%), and brain tumours (9.9%). Neuroimaging was normal in 8.7% of patients. Calcifications were found in 27% of patients and were significantly more common in patients with MTS than in those without MTS (p0.001). Isolated neurocysticercosis was found in only eight patients (1.56%).These data suggest that neurocysticercosis is an uncommon cause of intractable epilepsy, even in an endemic region such as Brazil, and that it may only represent a coexistent pathology. However, an analysis of our findings reveals that neurocysticercosis was more common in patients with MTS. This finding could suggest either that there is a cause-effect relationship between MTS and neurocysticercosis, or that MTS and neurocysticercosis co-vary with a missing variable, such as socio-economic status.

Objectives: Although chronic calcified neurocysticercosis (NCC) has been considered a major cause of symptomatic epilepsy in developing countries, it can also be an incidental pathological finding in epileptic patients from endemic regions. The mechanisms of brain plasticity occurring in patients with NCC during and after the inflammatory process related to the parasite infection, death, degeneration, and calcification within the host brain might be an independent factor for cognitive impairment in patients with NCC and epilepsy. In order to assess this possibility cognitive performance of patients with mesial temporal lobe epilepsy related to hippocampal sclerosis (MTLE-HS) with and without NCC was investigated through structured neuropsychological testing. Methods: Cognitive performance of long term MTLE-HS patients with (HS-NCC group, n = 32) and without NCC (HS only, n = 48) was compared. Imbalances between the two groups with respect to clinical, demographic, neuroimaging, and electrophysiological variables were adjusted by linear multiple regression analysis and Bonferroni correction for multiple tests. Results and conclusions: There were no cognitive performance differences between HS-NCC and HS only patients, leading to the conclusion that chronic calcified NCC per se does not aggravate the cognitive performance of patients with long term MTLE-HS.