Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations.

. We use deep learning models to classify cervix images-collected with a low-cost, portable Pocket colposcope-with biopsy-confirmed high-grade precancer and cancer. We boost classification performance on a screened-positive population by using a class-balanced loss and incorporating green-light colposcopy image pairs, which come at no additional cost to the provider.

A verification and parametric analysis of an analytical model of a flexural vibration mode piezoelectric transformer.

In this paper, a circuit model equivalent to that proposed in a previous work was verified through experimental and finite element methods. On the basis of this verified model, the impact of the parameters on the electrical characteristics of a circular flexural vibration mode piezoelectric transformer was systematically investigated through the orthogonal experiment design method. Some interesting and valuable rules were found.