Lesion Volume Quantification Using Two Convolutional Neural Networks in MRIs of Multiple Sclerosis Patients.

BACKGROUND: Multiple sclerosis (MS) is a neurologic disease of the central nervous system which affects almost three million people worldwide. MS is characterized by a demyelination process that leads to brain lesions, allowing these affected areas to be visualized with magnetic resonance imaging (MRI). Deep learning techniques, especially computational algorithms based on convolutional neural networks (CNNs), have become a frequently used algorithm that performs feature self-learning and enables segmentation of structures in the image useful for quantitative analysis of MRIs, including quantitative analysis of MS. To obtain quantitative information about lesion volume, it is important to perform proper image preprocessing and accurate segmentation. Therefore, we propose a method for volumetric quantification of lesions on MRIs of MS patients using automatic segmentation of the brain and lesions by two CNNs. METHODS: We used CNNs at two different moments: the first to perform brain extraction, and the second for lesion segmentation. This study includes four independent MRI datasets: one for training the brain segmentation models, two for training the lesion segmentation model, and one for testing. RESULTS: The proposed brain detection architecture using binary cross-entropy as the loss function achieved a 0.9786 Dice coefficient, 0.9969 accuracy, 0.9851 precision, 0.9851 sensitivity, and 0.9985 specificity. In the second proposed framework for brain lesion segmentation, we obtained a 0.8893 Dice coefficient, 0.9996 accuracy, 0.9376 precision, 0.8609 sensitivity, and 0.9999 specificity. After quantifying the lesion volume of all patients from the test group using our proposed method, we obtained a mean value of 17,582 mm3. CONCLUSIONS: We concluded that the proposed algorithm achieved accurate lesion detection and segmentation with reproducibility corresponding to state-of-the-art software tools and manual segmentation. We believe that this quantification method can add value to treatment monitoring and routine clinical evaluation of MS patients.

Quality of life after gastric sleeve and gastric bypass for morbid obesity.

HIGHLIGHTS: Quality-of-life measures improve as early as 3 months after bariatric surgery.There is wide variability in reporting that renders direct comparisons difficult.The available comparisons between RYGB and sleeve gastrectomy could not detect any difference.Improvement in PRO measures might be related to weight loss.Larger and better designed studies are required to achieve discrimination in PRO measures. BACKGROUND: Obesity is associated with reduced quality-of-life (QoL), which generally improves after bariatric surgery. The differential effect of each type of surgery (gastric sleeve [SG] and gastric bypass [RYGB]) on QoL is not yet fully understood. OBJECTIVES: To understand which of these surgeries offers greatest improvement in QoL and patient satisfaction. METHODS: Systematic literature search on Pubmed in July 2014. Relevant articles were selected in a step-wise approach. The 2482 titles were scanned for relevance and 191 were selected for abstract reviewing; and 88 papers were selected for full text analysis. RESULTS: Only 5 papers compared the 2 techniques and only 17 more had retrievable data either on SG or RYGB. The reports were very heterogeneous, preventing a direct comparison of patient reported outcomes (PRO) among studies.Improved results have been reported as early has 3 months and SF-36 scores were improved in all domains in medium to long-term. The question remains whether the improvement in QoL is related to the weight loss and which factors are associated with improved patients' perceptions. CONCLUSIONS: There is wide heterogeneity in the reporting of PRO measures after bariatric surgery, but data is consistent with a significant improvement after both surgeries.Larger and better-designed studies are required to understand if there are significant differences in the quality of life after SG or RYGB.

Infarto do miocárdio de localizaçäo anterior: valor prognóstico do índice de Gaasch / Myocardial infarction of anterior localization: prognostic value of the Gaasch index

Trinta doentes (28 do sexo masculino), com idade média 55 + ou - 12 anos, com seguimento de 13 a 25 meses (média 20 meses), acometidos de infarto do miocárdio de localizaçäo anterior, anteriormente estudados, foram submetidos a novos ecocardiograma e a reavaliaçäo clínica. Quatro doentes (13,3%) morreram de causa cardíaca (grupo A). Os sobreviventes (83,3%) formaram o grupo B e o foram divididos em sintomáticos (28%-grupo I) e assintomáticos (72%-grupo II). Compararam-se as variáveis ecocardiográficas dos grupos A e B, tendo havido diferenças significativas no que respeita ao índice de Gaasch (IG). A comparaçäo entre os grupos I e II, revelou diferenças estatisticamente significativas em relaçäo ao diâmetro diastólico, à distância E-septo e ao IG. Conclui-se que o IG forneceu a única diferença estatisticamente significativa entre os grupos A e B (p < 0,02), sendo 3,2 um valor discriminativo entre os grupos A e B os grupos I e II (p < 0,001), constituindo uma variável ecocardiográfica com valor prognóstico nos doentes com infarto do miocárdio de localizaçäo anterior, apesar do seguimento ter sido só de 20 meses

Relação volume/massa miocárdica do ventrículo esquerdo em portadores de fístulas artério-venosas perféricos: Estudo ecocardiográfico (Modo M) / Myocardial volume/mass ratio of the left ventricule in patients with peripheral arteriovenous fistulas echocardiographic study (M.Mode)

Foram estudados, ecocardiograficamente (modelo M) 20 nefropatas crônicos, em regime de hemodiálise periódica, dos quais 9 eram hipertensos (grupos H) e 11 normotensos (grupos N). Compararam estes dois grupos com una série de 8 grávidas normais (grupo G), relacionando os respectivos septos interventriculares (SIV) e diastólicos (DD).Calculou-se a massa miocárdica e a área transversal da parede (Cross Sectional Area) e utilizou-se um índice ecocardiográfico de volume/massa (Indice de Gassch). Todas estas variáveis eram estatisticamente diferentes (p < 0,001) com exceçäo da massa miocárdica, em que näo se encontrou diferença significativa entre os grupos N e H. Concluiu-se haver diferença significativas na forma de crecimento de ventrículo esquerdo nos indivíduos com fístulas artério-venosas periféricas, a qual pode também ser modificada pela coexistência de hipertençäo arterial. Assim, encontro-se hipertrofia inadequada nos grupos G e N (Indice de Gaach aumentado) e hipertrofia apropriada (Indice de Gassch normal) na maioria dos casos do grupo H.