Background Deep learning has presented considerable potential and is gaining more importance in computer assisted diagnosis. As the gold standard for pathologically diagnosing cervical intraepithelial lesions and invasive cervical cancer, colposcopy-guided biopsy faces challenges in improving accuracy and efficiency worldwide, especially in developing countries. To ease the heavy burden of cervical cancer screening, it is urgent to establish a scientific, accurate and efficient method for assisting diagnosis and biopsy. Methods The data were collected to establish three deeplearning-based models. For every case, one saline image, one acetic image, one iodine image and the corresponding clinical information, including age, the results of human papillomavirus testing and cytology, type of transformation zone, and pathologic diagnosis, were collected. The dataset was proportionally divided into three subsets including the training set, the test set and the validation set, at a ratio of 8:1:1. The validation set was used to evaluate model performance. After model establishment, an independent dataset of high-definition images was collected to further evaluate the model performance. In addition, the comparison of diagnostic accuracy between colposcopists and models weas performed. Results The sensitivity, specificity and accuracy of the classification model to differentiate negative cases from positive cases were 85.38%, 82.62% and 84.10% respectively, with an AUC of 0.93. The recall and DICE of the segmentation model to segment suspicious lesions in acetic images were 84.73% and 61.64%, with an average accuracy of 95.59%. Furthermore, 84.67% of highgrade lesions were detected by the acetic detection model. Compared to colposcopists, the diagnostic system performed better in ordinary colposcopy images but slightly unsatisfactory in high-definition images. Implications The deep learning-based diagnostic system could help assist colposcopy diagnosis and biopsy for HSILs.

Paclitaxel is widely used as a first-line chemotherapeutic drug for patients with ovarian cancer and other solid cancers, but drug resistance occurs frequently, resulting in ovarian cancer still presenting as the highest lethality among all gynecological tumors. Here, using DIGE quantitative proteomics, we identified UBC13 as down-regulated in paclitaxel-resistant ovarian cancer cells, and it was further revealed by immunohistochemical staining that UBC13 low-expression was associated with poorer prognosis and shorter survival of the patients. Through gene function experiments, we found that paclitaxel exposure induced UBC13 down-regulation, and the enforced change in UBC13 expression altered the sensitivity to paclitaxel. Meanwhile, the reduction of UBC13 increased DNMT1 levels by attenuating its ubiquitination, and the up-regulated DNMT1 enhanced the CHFR promoter DNA methylation levels, leading to a reduction of CHFR expression, and an increased in the levels of Aurora A. Our findings revealed a novel function for UBC13 in regulating paclitaxel sensitivity through a DNMT1-CHFR-Aurora A pathway in ovarian cancer cells. UBC13 could potentially be employed as a therapeutic molecular drug for reversing paclitaxel resistance in ovarian cancer patients.

No abstract

No abstract