A tree similarity algorithm for match-making of agents in e-Business environments is presented. Product/service descriptions of seller and buyer agents are represented as node-labelled, arc-labelled, arc-weighted trees. A similarity algorithm for such trees is developed as the basis for semantic match-making in a virtual marketplace. The trees are exchanged using an XML serialization in Object-Oriented RuleML. Correspondingly, we use the declarative language Relfun to implement the similarity algorithm as a parameterised, recursive functional program. Three main recursive functions perform a top-down traversal of trees and the bottom-up computation of similarity. Results from our experiments aiming to match buyers and sellers are found to be effective and promising for eBusiness/e-Learning environments. The algorithm can be applied in all environments where weighted trees are used.

Background: We systematically evaluated the evidences on oncological and functional outcomes of high-intensity focused ultrasound (HIFU) as the primary treatment for localized prostate cancer (PCa). Methods: A systematic review was used Medline, Embase, and the Cochrane Library from the inception of each database. The review analyzed the oncological and functional outcomes of HIFU in the treatment of PCa. The RevMan 5.3 software was used for quantity analysis incidence of complications. Results: Twenty-seven articles were included for analysis with a total of 7393 patients. Eighteen studies investigated the whole-gland HIFU, and the duration of follow-up ranged from 2 to 168 months. After whole-gland HIFU, the mean prostate-specific antigen (PSA) nadir was found to be 0.4 to 1.95 ng/mL and the mean time to PSA nadir was 2.4 to 5.4 months. The rate of positive biopsy after HIFU was 4.5% to 91.1%. Meta-analysis revealed the incidences of urinary incontinence, impotence, urinary obstruction, retention, and infection was 10%, 44%, 15%, 11%, 7%, respectively. Nine studies investigated partial-gland HIFU, and the duration of follow-up was 1 to 131 months. After partial-gland HIFU, the mean PSA nadir was 1.9 to 2.7 ng/mL and the mean time to PSA nadir 5.7 to 7.3 months. The rate of positive biopsy after HIFU in the treatment area was 14% to 37.5%. Meta-analysis revealed the incidences of urinary incontinence, impotence, urinary obstruction, retention, and infection was 2%, 21%, 2%, 9%, 11%, respectively. Conclusions: Early evidence suggested the partial-gland HIFU was safer than whole-gland HIFU, and they had similar oncological outcomes. More prospective randomized controlled trials of whole-gland and partial-gland HIFU for PCa was needed.

While active efforts are advancing medical artificial intelligence (AI) model development and clinical translation, safety issues of the AI models emerge, but little research has been done. We perform a study to investigate the behaviors of an AI diagnosis model under adversarial images generated by Generative Adversarial Network (GAN) models and to evaluate the effects on human experts when visually identifying potential adversarial images. Our GAN model makes intentional modifications to the diagnosis-sensitive contents of mammogram images in deep learning-based computer-aided diagnosis (CAD) of breast cancer. In our experiments the adversarial samples fool the AI-CAD model to output a wrong diagnosis on 69.1% of the cases that are initially correctly classified by the AI-CAD model. Five breast imaging radiologists visually identify 29%-71% of the adversarial samples. Our study suggests an imperative need for continuing research on medical AI model’s safety issues and for developing potential defensive solutions against adversarial attacks.