[Feasibility of ultrasound radiomics-based models for classification of hepatic echinococcosis].

OBJECTIVE: To investigate the feasibility of establishment of ultrasound radiomics-based models for classification of hepatic echinococcosis, so as to provide insights into precision ultrasound diagnosis of hepatic echinococcosis. METHODS: The ultrasonographic images were retrospectively collected from 200 patients with hepatic echinococcosis in Shiqu County, Ganzi Tibetan Autonomous Prefecture, Sichuan Province in October 2014, and the regions of interest were plotted in ultrasonographic images of hepatic echinococcosis lesions. The ultrasound radiomics features of hepatic echinococcosis were extracted with 25 methods, and screened using pre-selection and the least absolute shrinkage and selection operator. Then, all ultrasonographic images were randomly assigned into the training and independent test sets according to the type of lesions at a ratio of 7:3. Machine learning models for classification of hepatic echinococcosis were created based on two classifiers, including kernel logistic regression (KLR) and medium Gaussian support vector machine (MGSVM). The receiver operating characteristic (ROC) curves were plotted, and the sensitivity, specificity and areas under the curves (AUC) of the created machine learning models for classification of hepatic echinococcosis were calculated. RESULTS: A total of 5 005 ultrasound radiomics features were extracted from 200 patients with hepatic echinococcosis using 25 methods, and 36 optimal radiomics features were screened through feature selection, based on which two machine learning models were created, including KLR and MGSVM. ROC curve analysis showed that MGS-VM presented a higher efficacy for hepatic echinococcosis classification than KLR in the training set, with a sensitivity of 0.82, a specificity of 0.78 and AUC of 0.88, while KLR presented a higher efficacy for hepatic echinococcosis classification than MGSVM in the independent test set, with a sensitivity of 0.82, a specificity of 0.72 and AUC of 0.86, respectively. CONCLUSIONS: Ultrasound radiomics-based machine learning models are feasible for hepatic echinococcosis classification.

[The clinical manifestation and analysis of eosinophilic granulomatous vasculitis].

OBJECTIVE: To evaluate the clinical features, treatment and prognosis of Eosinophilic Granulomatous Vasculitis. METHODS: We analyzed retrospectively the clinical and laboratory features, treatment and prognosis of 43 patients with Eosinophilic Granulomatous Vasculitis who admitted to the Department of Rheumatology of the First Affiliated University Hospital of Sun Yat-sen University between 2005 and 2014. RESULTS: Of the 43 patients, 31 patients (72.1%) had allergic symptoms in the disease course and 16 patients (37.2%) had asthma and lung wheezing sound when performing the physical examination.Organs involvements included skin, acra, lung, kidney, central and peripheral nervous system, digestive system and heart.Positive antineutrophilic cytoplasmic antibody (ANCA) which mainly with MPO-ANCA was found in 18 patients (41.9%). Thirty-nine patients (90.7%)had high blood eosinophil level while all patients (100%) had elevated IgE.Two patients died of multiple organ failure in their acute phase, and the others had favorable prognosis after receiving the treatment of glucocorticoid combine with cyclophosphamide or methotrexate. CONCLUSIONS: Eosinophilic Granulomatous Vasculitiscould make damage to organs and tissues.Only 72.1% patients had allergic symptoms and 37.2% patients had asthma and lung wheezing sound.More than half patients have the negative ANCA.Glucocorticoidcombine with cyclophosphamide or methotrexate can achieve satisfactory therapeutic effects.