The usefulness of ultrasound in the classification of chronic liver disease

Chronic Liver Disease is a progressive, most of the time asymptomatic, and potentially fatal disease. In this paper, a semi-automatic procedure to stage this disease is proposed based on ultrasound liver images, clinical and laboratorial data. In the core of the algorithm two classifiers are used: a k nearest neighbor and a Support Vector Machine, with different kernels. The classifiers were trained with the proposed multi-modal feature set and the results obtained were compared with the laboratorial and clinical feature set. The results showed that using ultrasound based features, in association with laboratorial and clinical features, improve the classification accuracy. The support vector machine, polynomial kernel, outperformed the others classifiers in every class studied. For the Normal class we achieved 100% accuracy, for the chronic hepatitis with cirrhosis 73.08%, for compensated cirrhosis 59.26% and for decompensated cirrhosis 91.67%.

Chronic liver disease staging classification based on ultrasound, clinical and laboratorial data

In this work the identification and diagnosis of various stages of chronic liver disease is addressed. The classification results of a support vector machine, a decision tree and a k-nearest neighbor classifier are compared. Ultrasound image intensity and textural features are jointly used with clinical and laboratorial data in the staging process. The classifiers training is performed by using a population of 97 patients at six different stages of chronic liver disease and a leave-one-out cross-validation strategy. The best results are obtained using the support vector machine with a radial-basis kernel, with 73.20% of overall accuracy. The good performance of the method is a promising indicator that it can be used, in a non invasive way, to provide reliable information about the chronic liver disease staging.

Diffuse liver disease classification from ultrasound surface characterization, clinical and laboratorial data

In this work liver contour is semi-automatically segmented and quantified in order to help the identification and diagnosis of diffuse liver disease. The features extracted from the liver contour are jointly used with clinical and laboratorial data in the staging process. The classification results of a support vector machine, a Bayesian and a k-nearest neighbor classifier are compared. A population of 88 patients at five different stages of diffuse liver disease and a leave-one-out cross-validation strategy are used in the classification process. The best results are obtained using the k-nearest neighbor classifier, with an overall accuracy of 80.68%. The good performance of the proposed method shows a reliable indicator that can improve the information in the staging of diffuse liver disease.

Fatty liver characterization and classification by ultrasound

Steatosis, also known as fatty liver, corresponds to an abnormal retention of lipids within the hepatic cells and reflects an impairment of the normal processes of synthesis and elimination of fat. Several causes may lead to this condition, namely obesity, diabetes, or alcoholism. In this paper an automatic classification algorithm is proposed for the diagnosis of the liver steatosis from ultrasound images. The features are selected in order to catch the same characteristics used by the physicians in the diagnosis of the disease based on visual inspection of the ultrasound images. The algorithm, designed in a Bayesian framework, computes two images: i) a despeckled one, containing the anatomic and echogenic information of the liver, and ii) an image containing only the speckle used to compute the textural features. These images are computed from the estimated RF signal generated by the ultrasound probe where the dynamic range compression performed by the equipment is taken into account. A Bayes classifier, trained with data manually classified by expert clinicians and used as ground truth, reaches an overall accuracy of 95% and a 100% of sensitivity. The main novelties of the method are the estimations of the RF and speckle images which make it possible to accurately compute textural features of the liver parenchyma relevant for the diagnosis.

Perfil epidemiológico dos pacientes em terapia renal substitutiva no Brasil, 2000-2004

OBJETIVO: Descrever o perfil epidemiológico e clínico de pacientes em terapia renal substitutiva, identificando fatores associados ao risco de morte. MÉTODOS: Estudo observacional, prospectivo não concorrente, a partir de dados de 90.356 pacientes da Base Nacional em Terapias Renais Substitutivas, no Brasil. Foi realizado relacionamento determinístico-probabilístico do Sistema de Autorização de Procedimentos de Alta Complexidade/Custo e do Sistema de Informação de Mortalidade. Foram incluídos todos os pacientes incidentes que iniciaram diálise entre 1/1/2000 e 31/12/2004, acompanhados até a morte ou final de 2004. Idade, sexo, região de residência, doença renal primária, causa do óbito foram analisados. Ajustou-se um modelo de riscos proporcionais para identificar fatores associados ao risco de morte. RESULTADOS: Ocorreu um aumento médio de 5,5% na prevalência de pacientes em terapia enquanto a incidência manteve-se estável no período. Hemodiálise foi a modalidade inicial predominante (89%). A maioria dos pacientes era do sexo masculino, com idade média de 53 anos, residente na região Sudeste, e apresentava causa indeterminada como principal causa básica da doença renal crônica, seguida da hipertensão, diabetes e glomerulonefrites. Desses pacientes, 7% realizou transplante renal e 42% evoluiu para o óbito. Os pacientes em diálise peritoneal eram mais idosos e apresentavam maior prevalência de diabetes. Entre os não transplantados, 45% foi a óbito e, entre os transplantados, 7%. No modelo final de riscos proporcionais de Cox, o risco de mortalidade foi associado com o aumento da idade, sexo feminino, ter diabetes, residir nas regiões Norte e Nordeste, diálise peritoneal como modalidade de entrada e não ter realizado transplante renal. CONCLUSÕES: Houve aumento da prevalência de pacientes em terapia renal no Brasil. Pacientes com idade avançada, diabetes, do sexo feminino, residentes nas regiões Norte e Nordeste e sem transplante renal apresentam maior risco de morte.

Automatic diagnosis of liver steatosis by ultrasound using autoregressive tissue characterization

Liver steatosis is mainly a textural abnormality of the hepatic parenchyma due to fat accumulation on the hepatic vesicles. Today, the assessment is subjectively performed by visual inspection. Here a classifier based on features extracted from ultrasound (US) images is described for the automatic diagnostic of this phatology. The proposed algorithm estimates the original ultrasound radio-frequency (RF) envelope signal from which the noiseless anatomic information and the textural information encoded in the speckle noise is extracted. The features characterizing the textural information are the coefficients of the first order autoregressive model that describes the speckle field. A binary Bayesian classifier was implemented and the Bayes factor was calculated. The classification has revealed an overall accuracy of 100%. The Bayes factor could be helpful in the graphical display of the quantitative results for diagnosis purposes.

Permanent vascular access in patients with end-stage renal disease, Brazil

OBJECTIVE: To assess factors associated with the establishment of permanent vascular access for patients with end-stage renal disease. METHODS: Cross-sectional study conducted in a nationally representative sample of Brazilian end-stage renal disease patients in dialysis and transplant centers during 2007. The sample comprised only patients who received hemodialysis as a primary therapy modality and reported the type of vascular access for their primary hemodialysis treatment (N=2,276). Data were from the TRS Project - "Economic and Epidemiologic Evaluation of Modalities of Renal Replacement Therapy in Brazil". Multiple logistic regression analysis was used to assess factors associated with the establishment of permanent vascular access in these patients. RESULTS: About 30% of the patients studied had an arteriovenous vascular access. The following factors were associated with a lower likelihood of having an arteriovenous vascular access as a primary type of access: time of hemodialysis start since the diagnosis of chronic renal failure < 1 year; shorter dialysis therapy; having no private health insurance; living in the central-western, northeastern and southeastern regions of Brazil; and living in the northern region plus having no private health insurance. In the final model there was found a positive association between the outcome and pre-dialysis care and no were association with socioeconomic and comorbidity variables. CONCLUSIONS: The study results showed that the focus should on pre-dialysis care to increase the establishment of an arteriovenous vascular access before starting hemodialysis in Brazil.

Influência dos métodos de correção de atenuação na quantificação da função renal relativa em cintigrafia renal com 99mTc-DMSA

Introdução – A estimativa da função renal relativa (FRR) através de cintigrafia renal (CR) com ácido dimercaptossuccínico marcado com tecnécio-99 metaestável (99mTc-DMSA) pode ser influenciada pela profundidade renal (PR), atendendo ao efeito de atenuação por parte dos tecidos moles que envolvem os rins. Dado que raramente é conhecida esta mesma PR, diferentes métodos de correção de atenuação (CA) foram desenvolvidos, nomeadamente os que utilizam fórmulas empíricas, como os de Raynaud, de Taylor ou de Tonnesen, ou recorrendo à aplicação direta da média geométrica (MG). Objetivos – Identificar a influência dos diferentes métodos de CA na quantificação da função renal relativa através da CR com 99mTc-DMSA e avaliar a respetiva variabilidade dos resultados de PR. Metodologia – Trinta e um pacientes com indicação para realização de CR com 99mTc-DMSA foram submetidos ao mesmo protocolo de aquisição. O processamento foi efetuado por dois operadores independentes, três vezes por exame, variando para o mesmo processamento o método de determinação da FRR: Raynaud, Taylor, Tonnesen, MG ou sem correção de atenuação (SCA). Aplicou-se o teste de Friedman para o estudo da influência dos diferentes métodos de CA e a correlação de Pearson para a associação e significância dos valores de PR com as variáveis idade, peso e altura. Resultados – Da aplicação do teste de Friedman verificaram-se diferenças estatisticamente significativas entre os vários métodos (p=0,000), excetuando as comparações SCA/Raynaud, Tonnesen/MG e Taylor/MG (p=1,000) para ambos os rins. A correlação de Pearson demonstra que a variável peso apresenta uma correlação forte positiva com todos os métodos de cálculo da PR. Conclusões – O método de Taylor, entre os três métodos de cálculo de PR, é o que apresenta valores de FRR mais próximos da MG. A escolha do método de CA influencia significativamente os parâmetros quantitativos de FRR.

A reliable M-mode ultrasound protocol for the assessment of diaphragm motion

Diaphragm is the principal inspiratory muscle. Different techniques have been used to assess diaphragm motion. Among them, M-mode ultrasound has gain particular interest since it is non-invasive and accessible. However it is operator-dependent and no objective acquisition protocol has been established. Purpose: to establish a reliable method for the assessment of the diaphragmatic motion via the M-mode ultrasound.

Cyclosporine versus tacrolimus: cost-effectiveness analysis for renal transplantation in Brazil

OBJECTIVE To analyze the cost-effectiveness of treatment regimens with cyclosporine or tacrolimus, five years after renal transplantation.METHODS This cost-effectiveness analysis was based on historical cohort data obtained between 2000 and 2004 and involved 2,022 patients treated with cyclosporine or tacrolimus, matched 1:1 for gender, age, and type and year of transplantation. Graft survival and the direct costs of medical care obtained from the National Health System (SUS) databases were used as outcome results.RESULTS Most of the patients were women, with a mean age of 36.6 years. The most frequent diagnosis of chronic renal failure was glomerulonephritis/nephritis (27.7%). In five years, the tacrolimus group had an average life expectancy gain of 3.96 years at an annual cost of R$78,360.57 compared with the cyclosporine group with a gain of 4.05 years and an annual cost of R$61,350.44.CONCLUSIONS After matching, the study indicated better survival of patients treated with regimens using tacrolimus. However, regimens containing cyclosporine were more cost-effective.

Fatty liver automatic diagnosis from ultrasound images

In this paper an automatic classification algorithm is proposed for the diagnosis of the liver steatosis, also known as, fatty liver, from ultrasound images. The features, automatically extracted from the ultrasound images used by the classifier, are basically the ones used by the physicians in the diagnosis of the disease based on visual inspection of the ultrasound images. The main novelty of the method is the utilization of the speckle noise that corrupts the ultrasound images to compute textural features of the liver parenchyma relevant for the diagnosis. The algorithm uses the Bayesian framework to compute a noiseless image, containing anatomic and echogenic information of the liver and a second image containing only the speckle noise used to compute the textural features. The classification results, with the Bayes classifier using manually classified data as ground truth show that the automatic classifier reaches an accuracy of 95% and a 100% of sensitivity.

Histoplasmose disseminada em transplantado renal

Os Autores registram caso de histoplasmose generalizada em paciente transplantado com rim de doador não aparentado. Além da infecção fúngica diagnosticada sorologicamente e pela histopatologia, a autópsia revelou cirrose hepática macro e micronodular, de provável etiologia viral (vírus B), hepatocarcinoma, depleção linfóide do baço e glomerulopatia de transplante. Revendo a literatura sobre o assunto, chegam à conclusão de que, provavelmente, com a imunodepressão medicamentosa, as lesões pulmonares por reinfecção endógena foram as primeiras a aparecer sob a forma de uma histoplasmose pulmonar crônica.

Acute renal failure after rifampicin

A patient with miliary tuberculosis and a chronic urogenital focus is described, who had a borderline renal function at diagnosis and developed overt renal failure upon daily treatment with rifampin (RMP), isoniazid (INH) and ethambutol (EMB). This is the first Brazilian report of BMP induced renal damage. A renal biopsy taken on the third day of oliguria showed recent tubular necrosis with acute interstitial inflammation and granuloma formation. The aspect of the granulomatous lesion hightly suggested drug etiology because of the lack of palisading, high incidence of neutrophils and absence of facid-fast bacilli. This is the first presentation of an acute granulomatous interstitial nephritis probably due to RMP. Furthermore the pathogenesis of the renal damage caused by tuberculosis and RMP are discussed.

Função renal em pacientes com leishmaniose muco-cutânea tratados com antimoniais pentavalentes

Avaliou-se a função renal em 10 pacientes com leishmaniose muco-cutânea tratados com glucantime (antimoniato de Meglumine, Rhodia) ou Pentostam (estibogluconato de sólio, Wellcome). Durante o uso das drogas, verificou-se a existência de um defeito na capacidade concentrante do rim, obtendo-se menores valores da osmolaridade urinária máxima e de depuração negativa máxima de água livre, neste período, em relação aos testes efetuados antes do tratamento. A capacidade de concentração urinária normalizou-se em 5, de 8 pacientes estudados no período de 15 a 30 dias, após a suspensão dos medicamentos, embora com valores de osmolaridade urinária máxima inferiores aos obtidos antes do tratamento. Em dois pacientes surgiu proteínúria, acima de 150 mg/dia, com o uso dos antimoniais, normalizando-se posteriormente. A depuração de creatinina endógena não se alterou significativamente com o uso das drogas. Os resultados sugerem que os antimoniais pentavalentes podem levar a uma disfunção tubular renal, caracterizada por um defeito na capacidade de concentrar a urina, reversível após a retirada dos medicamentos.