Colposcopy is widely used to detect cervical cancers, but experienced physicians who are needed for an accurate diagnosis are lacking in developing countries. Artificial intelligence (AI) has been recently used in computer-aided diagnosis showing remarkable promise. In this study, we developed and validated deep learning models to automatically classify cervical neoplasms on colposcopic photographs. Pre-trained convolutional neural networks were fine-tuned for two grading systems: the cervical intraepithelial neoplasia (CIN) system and the lower anogenital squamous terminology (LAST) system. The multi-class classification accuracies of the networks for the CIN system in the test dataset were 48.6 ± 1.3% by Inception-Resnet-v2 and 51.7 ± 5.2% by Resnet-152. The accuracies for the LAST system were 71.8 ± 1.8% and 74.7 ± 1.8%, respectively. The area under the curve (AUC) for discriminating high-risk lesions from low-risk lesions by Resnet-152 was 0.781 ± 0.020 for the CIN system and 0.708 ± 0.024 for the LAST system. The lesions requiring biopsy were also detected efficiently (AUC, 0.947 ± 0.030 by Resnet-152), and presented meaningfully on attention maps. These results may indicate the potential of the application of AI for automated reading of colposcopic photographs. Cervical cancer is the fourth most common cancer in women worldwide, and the second most common cancer among females in developing countries 1. Screening is the principal prevention method aimed at reducing mortality rates. Screening includes certain steps, including population-based Papanicolaou (Pap) testing, colposcopydirected biopsy of suspicious lesions, and the treatment of confirmed pre-cancer lesions 2,3. In women with low-grade intraepithelial lesions (LSIL) or high-grade intraepithelial lesions (HSIL), the risk of pre-cancer is medium to high, and immediate referral for colposcopy is necessary. However, referring all women with atypical squamous cells of undetermined significance (ASC-US) is considered inefficient, as the risk of such cases being pre-cancerous is lower 4. Screening programs have been successful in the developed countries, leading to an approximately 80% decrease in the cervical cancer incidence over the past 4 decades. In contrast, the increase in cervical cancer incidence reported in developing countries 5 has been attributed to the unsuccessful implementation of screening programs. This, has been attributed to logistics in health systems, infrastructural inadequacies, and the lack of expert physicians capable of introducing screening programs and follow-up 6 .

A large number of organic reactions feature post transition state bifurcations. Selectivities in such reactions are difficult to analyze because they cannot be determined by comparing the energies of competing transition states. Molecular dynamics approaches can provide answers but are computationally very expensive. We present an algorithm which predicts the major products in bifurcating organic reactions with negligible computational cost. The method requires two transition states, two product geometries and no additional information. The algorithm correctly predicts the major product for about 90% of the organic reactions investigated. For the remaining 10% of the reactions, the algorithm returns a warning indication that the conclusion may be uncertain. The method also reproduces the experimental and the molecular dynamics product ratios within 15% for more than 80% of the reactions. We have successfully applied the method to a trifurcating organic reaction, a carbocation rearrangement and solvent dependent Pummerer-like reactions, demonstrating the power of the algorithm to simplify and to help to understand highly complex reactions.

Background Exosomal miRNAs regulate gene expression and play important roles in several diseases. We used exosomal miRNA profiling to investigate diagnostic biomarkers of epithelial ovarian cancer (EOC). Methods In total, 55 individuals were enrolled, comprising healthy (n = 21) and EOC subjects (n = 34). Small mRNA (smRNA) sequencing and real-time PCR (RT-PCR) were performed to identify potential biomarkers. Receiver operating characteristic (ROC) curves were conducted to determine biomarker sensitivity and specificity. Results Using smRNA sequencing, we identified seven up-regulated (miR-4732-5p, miR-877-5p, miR-574-3p, let-7a-5p, let-7b-5p, let-7c-5p, and let-7f-5p) and two down-regulated miRNAs (miR-1273f and miR-342-3p) in EOC patients when compared with healthy subjects. Of these, miR-4732-5p and miR-1273f were the most up-regulated and down-regulated respectively, therefore they were selected for RT-PCR analysis. Plasma derived exosomal miR-4732-5p had an area under the ROC curve of 0.889, with 85.7% sensitivity and 82.4% specificity in distinguishing EOC patients from healthy subjects (p<0.0001) and could be a potential biomarker for monitoring the EOC progression from early stage to late stage (p = 0.018). Conclusions Plasma derived exosomal miR-4732-5p may be a promising candidate biomarker for diagnosing EOC.