Background Human papillomavirus vaccination and cervical screening are lacking in most lower resource settings, where approximately 80% of more than 500 000 cancer cases occur annually. Visual inspection of the cervix following acetic acid application is practical but not reproducible or accurate. The objective of this study was to develop a “deep learning”-based visual evaluation algorithm that automatically recognizes cervical precancer/cancer. Methods A population-based longitudinal cohort of 9406 women ages 18–94 years in Guanacaste, Costa Rica was followed for 7 years (1993–2000), incorporating multiple cervical screening methods and histopathologic confirmation of precancers. Tumor registry linkage identified cancers up to 18 years. Archived, digitized cervical images from screening, taken with a fixed-focus camera (“cervicography”), were used for training/validation of the deep learning-based algorithm. The resultant image prediction score (0–1) could be categorized to balance sensitivity and specificity for detection of precancer/cancer. All statistical tests were two-sided. Results Automated visual evaluation of enrollment cervigrams identified cumulative precancer/cancer cases with greater accuracy (area under the curve [AUC] = 0.91, 95% confidence interval [CI] = 0.89 to 0.93) than original cervigram interpretation (AUC = 0.69, 95% CI = 0.63 to 0.74; P < .001) or conventional cytology (AUC = 0.71, 95% CI = 0.65 to 0.77; P < .001). A single visual screening round restricted to women at the prime screening ages of 25–49 years could identify 127 (55.7%) of 228 precancers (cervical intraepithelial neoplasia 2/cervical intraepithelial neoplasia 3/adenocarcinoma in situ [AIS]) diagnosed cumulatively in the entire adult population (ages 18–94 years) while referring 11.0% for management. Conclusions The results support consideration of automated visual evaluation of cervical images from contemporary digital cameras. If achieved, this might permit dissemination of effective point-of-care cervical screening.

Accurate surface anatomy is essential for safe clinical practice. Numerous inconsistencies in clinically important surface markings exist between and within anatomical reference texts. The aim of this study was to investigate key thoracic surface anatomical landmarks in vivo using computed tomographic (CT) imaging. High-resolution thoracic CT scans from 153 supine adults (mean age 63, range 19-89 years; 53% female) taken at end tidal inspiration were analyzed by dual consensus reporting to determine the surface anatomy of the sternal angle, central veins, heart, lungs, and diaphragm. Patients with kyphosis/scoliosis, distorting space-occupying lesions, or visceromegaly were excluded. The position of the cardiac apex, formation of the brachiocephalic veins, and vertebral levels of the sternal angle, xiphisternal joint, and aortic hiatus were consistent with commonly accepted surface markings although there was a wide range of normal variation. In contrast, common surface markings were markedly inaccurate for the following: the position of the tracheal bifurcation, aortic arch, and azygos vein termination (below the plane of the sternal angle at T5-T6 vertebral level in most individuals); the superior vena cava/right atrial junction (most often behind the fourth costal cartilage); the lower border of the lung (adjacent to T12 vertebra posteriorly); and the level at which the inferior vena cava and esophagus traverse the diaphragm (T11 in most). Surface anatomy must be reappraised using modern imaging in vivo if it is to be evidence based and fit for purpose. The effects of gender, age, posture, respiration, build, and ethnicity also deserve greater emphasis.

This meeting report presents the key findings and discussion points of a 1-day meeting entitled ‘Fake anti-malarials: start with the facts’ held on 28th May 2015, in Geneva, Switzerland, to disseminate the findings of the artemisinin combination therapy consortium’s drug quality programme. The teams purchased over 10,000 samples, using representative sampling approaches, from six malaria endemic countries: Equatorial Guinea (Bioko Island), Cambodia, Ghana, Nigeria, Rwanda and Tanzania. Laboratory analyses of these samples showed that falsified anti-malarials (<8 %) were found in just two of the countries, whilst substandard artemisinin-based combinations were present in all six countries and, artemisinin-based monotherapy tablets are still available in some places despite the fact that the WHO has urged regulatory authorities in malaria-endemic countries to take measures to halt the production and marketing of these oral monotherapies since 2007. This report summarizes the presentations that reviewed the public health impact of falsified and substandard drugs, sampling strategies, techniques for drug quality analysis, approaches to strengthen health systems capacity for the surveillance of drug quality, and the ensuing discussion points from the dissemination meeting.