3-Resultados e Discussões Tabela 3.29: Valores de distribuição de escore-z obtido para Homogeneidade em córtex saudável e DCF, bem como razão entre as duas médias. Estes valores ilustram o quanto cada voxel dentro da máscara de DCF se diferencia do grupo controle em relação aos voxel da máscara de córtex saudável. É desejado que o valor da razão seja diferente de 1.
Background: Multiple Sclerosis (MS) diagnosis and evaluation is often a challenging task due to its growing need for multimodal MRI acquisition protocol. Recently, the scientific community offers several computational alternatives to the time-consuming and subjective task of manual MS lesion segmentation. Although there is an increasing number of MS lesion segmentation methods, a controlled and realistic simulation environment can benefit the community for a reliable evaluation procedure. Methods: This study proposes an automatic parametric MS lesion simulation framework (MS-MIST) with the objective to emulate real MS-like pattern on MRI data of healthy individuals. The voxel graylevel patterns, spatial location, and shapes extracted from MS patient allow consistent simulation features. We used both visual evaluation from an expert radiologist in the field of MS diagnosis and SPM Lesion Segmentation Tool (LST) for qualitative and quantitative simulation quality, respectively. Results: Our results show that both the agreement between the automatic segmentation with the simulated lesions (Pearson's correlation R=0.977) and the segmentation quality scores, i.e., sensitivity (mean=0.9050), specificity (mean=0.9992), dice similarity (mean=0.8972), and accuracy (mean=0.9984), are consistent between MS-MIST and real clinical settings. Conclusions: MS-MIST proposes a practical solution to common issues discussed in the literature, such as inconsistency with real lesions geometry, imprecise lesion spatial and signal variability, lack of multiple MRI modalities and restrictions to simulate different lesion loads. It is worth noting that the simulation platform is freely available as an open-source code to the community.
Refractory epilepsy is a condition characterized by epileptic seizure occurrence which cannot be controlled with antiepileptic drugs. This condition is associated with an excessive neuronal discharge produced by a group of neurons in a certain epileptogenic zone. Focal Cortical Dysplasia (FCD), usually found in these zones, was detected as one of the main causes of refractory epilepsy. In these cases, surgical intervention is necessary to minimize or eliminate the seizure occurrences. However, surgical treatment is only indicated in cases where there is complete certainty of the FCD. In order to assist neurosurgeons to detect precisely these regions, this paper aims to develop a classification method to detect FCD on MRI based on morphological and textural features from a voxel-level perspective. Multiple classifiers were tested throughout the extracted features, the best results achieved an accuracy of 91.76% using a Deep Neural Network classifier and 96.15% with J48 Decision Tree. The set of evaluating metrics showed that the results are promising.
We tested the applicability of methods based on Detrended Fluctuation Analysis and HFO detection to the analysis of EEG signals from patients diagnosed with epilepsy, in order to test how efficient these methods would behave in a seizure prediction application. We were able to statistically distinguish the coefficients estimated in the pre-ictal period from the coefficients obtained on the inter-ictal period, suggesting that the methods can be used to the development of seizure detection algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.