Effectiveness and safety of ultrasound-guided percutaneous microwave ablation for hepatic alveolar echinococcosis.

BACKGROUND: Microwave ablation (MWA) is a popular therapy for liver malignant tumor in recent years. Few studies have been conducted on its use in the treatment of hepatic alveolar echinococcosis (HAE). The study aims to evaluate the efficacy and safety of MWA in the treatment of HAE. METHODS: This study analyzed the data of 45 patients (mean age, 38 ± 2 years; 24 males) diagnosed with HAE and underwent MWA treatment between June 2014 to December 2019. The patients after MWA were examined by CT or MRI [follow-up: 32 months (IQR 23-48.5)] to determine whether the lesions were relapsed and to evaluate the therapeutic effect of MWA. The safety of MWA was evaluated by monitoring postoperative complications. Clinical data, such as patient demographics, imaging features of the lesions, relevant findings of laboratory tests before and after ablation, and information related to ablation, were collected and analyzed. Paired-sample t tests and paired-sample Wilcoxon signed-rank tests were used to compare relevant laboratory indicators before and after MWA. RESULTS: MWA was applied to 57 HAE lesions in 45 patients. The median size of lesions was 3.42 cm (IQR2.85-4.41). The rate of complete ablation was 100% (57/57). The median follow-up time was 32 months (IQR 23-48.5). The recurrence rate was 13% (6/45), and the median time of recurrence was 22 months. The rate of minor complications was 11.1% (5/45), and there were no major complications and deaths. Compared to preoperative, ALB, RBC, HBG, and PLT were decreased (p < 0.001); ALT, TB, DB, and WBC were increased (p < 0.001); and no statistically difference in PT, APTT, and INR (p > 0.05). CONCLUSIONS: MWA might be a safe and effective way to cure HAE. Meanwhile, it provides a new option and a new way of thinking about treatment for patients with HAE.

Classifier Fusion With Contextual Reliability Evaluation.

Classifier fusion is an efficient strategy to improve the classification performance for the complex pattern recognition problem. In practice, the multiple classifiers to combine can have different reliabilities and the proper reliability evaluation plays an important role in the fusion process for getting the best classification performance. We propose a new method for classifier fusion with contextual reliability evaluation (CF-CRE) based on inner reliability and relative reliability concepts. The inner reliability, represented by a matrix, characterizes the probability of the object belonging to one class when it is classified to another class. The elements of this matrix are estimated from the -nearest neighbors of the object. A cautious discounting rule is developed under belief functions framework to revise the classification result according to the inner reliability. The relative reliability is evaluated based on a new incompatibility measure which allows to reduce the level of conflict between the classifiers by applying the classical evidence discounting rule to each classifier before their combination. The inner reliability and relative reliability capture different aspects of the classification reliability. The discounted classification results are combined with Dempster-Shafer's rule for the final class decision making support. The performance of CF-CRE have been evaluated and compared with those of main classical fusion methods using real data sets. The experimental results show that CF-CRE can produce substantially higher accuracy than other fusion methods in general. Moreover, CF-CRE is robust to the changes of the number of nearest neighbors chosen for estimating the reliability matrix, which is appealing for the applications.