Automated whole breast ultrasound (ABUS) has been widely used as a screening modality for examination of breast abnormalities. Reviewing hundreds of slices produced by ABUS, however, is time-consuming. Therefore, in this study, a fast and effective computer-aided detection (CADe) system based on 3-D convolutional neural networks (CNN) and prioritized candidate aggregation is proposed to accelerate this reviewing. Firstly, an efficient sliding window method is used to extract volumes of interest (VOIs). Then, each VOI is estimated the tumor probability with a 3-D CNN, and VOIs with higher estimated probability are selected as tumor candidates. Since the candidates may overlap each other, a novel scheme is designed to aggregate the overlapped candidates. During the aggregation, candidates are prioritized based on estimated tumor probability to alleviate over-aggregation issue. The relationship between the sizes of VOI and target tumor is optimally exploited to effectively perform each stage of our detection algorithm. On evaluation with a test set of 171 tumors, our method achieved sensitivities of 95% (162/171), 90% (154/171), 85% (145/171), and 80% (137/171) with 14.03, 6.92, 4.91, and 3.62 FPs per patient (with 6 passes), respectively. In summary, our method is more general and much faster than preliminary works, and demonstrates promising results.
This paper presents a novel single-stage push-pull boost converter with improved integrated magnetics and a better low-ripple input current. Most of the reported single-stage power factor corrected (PFC) rectifiers cascade a boost-type converter with a dc-dc converter. It is found that the push-pull converter, when the duty cycles are greater than 50%, can simplify the front end of the boost-type converter to a novel single-stage converter. Coupled inductor techniques provide a method to reduce the converter size and weight and to achieve a ripple-free current. All the magnetic components including the input filter inductor and the step-down transformer are integrated into a single EI core. The proposed integrated magnetic structure has a simple core structure, a small leakage inductance, and low core losses. The prototype is built to demonstrate the theoretical prediction.
To promote the development of user-oriented technology, different approaches are explored, with living labs being one of the most promising. This paper introduces the strategies in making of a community-based living lab with a specific focus on the users. We introduce the practical mechanisms built in a community environment and the methods to facilitate user innovation. We also report a case study of the users’ response to a health care technology, finding out that most of the users did not change their opinion after a year’s use. The major finding is on the dynamics between living lab construction and the transformation of the users. We reflect on the phenomenon of a living lab itself transforming the users and making it difficult for them to provide specific opinions of the technology
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.