Background Colposcopy diagnosis and directed biopsy are the key components in cervical cancer screening programs. However, their performance is limited by the requirement for experienced colposcopists. This study aimed to develop and validate a Colposcopic Artificial Intelligence Auxiliary Diagnostic System (CAIADS) for grading colposcopic impressions and guiding biopsies. Methods Anonymized digital records of 19,435 patients were obtained from six hospitals across China. These records included colposcopic images, clinical information, and pathological results (gold standard). The data were randomly assigned (7:1:2) to a training and a tuning set for developing CAIADS and to a validation set for evaluating performance. Results The agreement between CAIADS-graded colposcopic impressions and pathology findings was higher than that of colposcopies interpreted by colposcopists (82.2% versus 65.9%, kappa 0.750 versus 0.516, p < 0.001). For detecting pathological high-grade squamous intraepithelial lesion or worse (HSIL+), CAIADS showed higher sensitivity than the use of colposcopies interpreted by colposcopists at either biopsy threshold (low-grade or worse 90.5%, 95% CI 88.9–91.4% versus 83.5%, 81.5–85.3%; high-grade or worse 71.9%, 69.5–74.2% versus 60.4%, 57.9–62.9%; all p < 0.001), whereas the specificities were similar (low-grade or worse 51.8%, 49.8–53.8% versus 52.0%, 50.0–54.1%; high-grade or worse 93.9%, 92.9–94.9% versus 94.9%, 93.9–95.7%; all p > 0.05). The CAIADS also demonstrated a superior ability in predicting biopsy sites, with a median mean-intersection-over-union (mIoU) of 0.758. Conclusions The CAIADS has potential in assisting beginners and for improving the diagnostic quality of colposcopy and biopsy in the detection of cervical precancer/cancer.

Vaginal paraganglioma is a rare and unusual tumor occurring in the vaginal wall. It is a solitary primary paraganglioma, especially in atypical sites. Herein, we report an unusual case of a 17-year-old woman who had not experienced vomiting, or hypertension. She was found to have an immobile solid mass in the right side of her vaginal wall. Positron emission tomography/computed tomography scans revealed a well-defined solid ovoid mass adjacent to the bladder and pelvic floor. Tumor markers were within the normal range. A transient blood pressure increase occurred during the biopsy. After oral administration of antihypertensive drugs, surgery was performed to completely remove the mass. Histopathological examination indicated that it was a paraganglioma of the vagina. Repeat computed tomography examination did not reveal any local recurrence or distant metastasis during the 12-month follow-up period.

BackgroundSIRT1 expression and Notch1 signaling have been implicated in tumorigenesis in many cancers, but their association with survival in breast cancer has not been determined. The purpose of this study was to assess the possible prognostic value of SIRT1, N1IC, and Snail expression in breast cancer patients.MethodsImmunohistochemistry was performed to examine the expression of SIRT1, N1IC, and Snail, and the combined expression of SIRT1 and N1IC, using tissue microarrays containing breast cancer tissue and matched adjacent normal breast tissue from 150 breast cancer patients. Survival analysis was carried out using the Kaplan-Meier method. Univariate and multivariate analysis were used to evaluate the prognostic value of SIRT1, N1IC, Snail and combined SIRT1/N1IC expression, in addition to other clinicopathological factors, including grade, lymph node status, disease stage, and estrogen, progesterone, and human epidermal growth factor receptor 2 receptor status in breast carcinoma patients.ResultsSIRT1, N1IC, and Snail were all found to be highly expressed and an inverse correlation between SIRT1 and N1IC in breast cancer tissue. The three markers significantly correlated with lymph node status. Patients with low SIRT1 expression exhibited shorter overall survival (OS) and disease-free survival (DFS), and patients with combined low expression of SIRT1 and high expression of N1IC had the worse OS and DFS. Univariate and multivariate survival analysis revealed that low expression of SIRT1 and SIRT1-low/N1IC-high expression were independent prognostic factors for poor survival.ConclusionsThese results suggest that low expression of SIRT1 or the combined low expression of SIRT1 and high expression of N1IC could be used as indicators of poor prognosis, and may represent novel therapeutic targets in breast cancer.Electronic supplementary materialThe online version of this article (doi:10.1186/s13046-014-0097-2) contains supplementary material, which is available to authorized users.

The breast cancer stem cells contribute to the initiation, progression, recurrence, metastasis as well as resistance of breast cancer. However, the mechanisms underlying the maintenance of breast cancer stemness have not been fully understood. Materials and methods: TCGA and GEO data were used for measuring miR-520b expression in breast cancer tissues. Kaplan-meier analysis was used for determining the relationship between miR-520b expression level and the prognosis of patients. Genetic manipulation was performed by lentivirus system and miR-520b inhibitor was used for knockdown of miR-520b. qRT-PCR and Western blot were employed to determine the mRNA and protein levels, respectively. The stemness and EMT (Epithelial to mesenchymal transition) were assessed by sphereformation and transwell assay as well as the expression of the related markers. The target genes of miR-520b were identified using the online database starBase V3.0. Results: miR-520b is upregulated in cancer tissues of breast cancer patients and predicts poor prognosis. Upregulation of miR-520b was found in breast cancer stem cells. Ectopic expression of miR-520b promotes the stemness of the breast cancer cells, conversely, depletion of miR-520b attenuates the stemness of these cells. miR-520b positively regulates Hippo/YAP signaling pathway and overexpression of LAST2 abolished the effect of miR-520b on the stemness of breast cancer cells. Conclusion: miR-520b promotes the stemness of breast cancer patients by activating Hippo/YAP signaling via targeting LATS2.