Background: Colposcopy is indispensable for the diagnosis of cervical lesions. However, its diagnosis accuracy for high‐grade squamous intraepithelial lesion (HSIL) is at about 50%, and the accuracy is largely dependent on the skill and experience of colposcopists. The advancement in computational power made it possible for the application of artificial intelligence (AI) to clinical problems. Here, we explored the feasibility and accuracy of the application of AI on precancerous and cancerous cervical colposcopic image recognition and classification.Methods: The images were collected from 6002 colposcopy examinations of normal control, low‐grade squamous intraepithelial lesion (LSIL), and HSIL. For each patient, the original, Schiller test, and acetic‐acid images were all collected. We built a new neural network classification model based on the hybrid algorithm. EfficientNet‐b0 was used as the backbone network for the image feature extraction, and GRU(Gate Recurrent Unit)was applied for feature fusion of the three modes examinations (original, acetic acid, and Schiller test).Results: The connected network classifier achieved an accuracy of 90.61% in distinguishing HSIL from normal and LSIL. Furthermore, the model was applied to “Trichotomy”, which reached an accuracy of 91.18% in distinguishing the HSIL, LSIL and normal control at the same time.Conclusion: Our results revealed that as shown by the high accuracy of AI in the classification of colposcopic images, AI exhibited great potential to be an effective tool for the accurate diagnosis of cervical disease and for early therapeutic intervention in cervical precancer.

To investigate the prognostic significance of 23 matrix metalloproteinase (MMP) genes in patients diagnosed with ovarian carcinoma. The prognostic significance of 23 MMP genes in patients diagnosed with ovarian carcinoma was investigated using the Kaplan–Meier plotter (KM plotter), which uses the gene expression data and overall survival information of patients with ovarian cancer that were downloaded from the Gene Expression Omnibus, Cancer Biomedical Informatics Grid and The Cancer Genome Atlas cancer datasets. The correlation between mRNA levels of individual MMPs (MMP2, MMP9, MMP10, MMP12, MMP13 and MMP25) and clinicopathological features (histological subtype, pathological grade and clinical stage) were investigated. The MMP protein level profiles in normal ovarian tissues and ovarian cancer tissues were examined using the Human Protein Atlas database. The results showed that high mRNA levels of MMP2 and MMP13 were associated with a worse overall survival in patients with ovarian cancer, whereas high mRNA levels of MMP9, MMP10, MMP12 and MMP25 were associated with a better overall survival. The protein levels of MMP2, MMP9, MMP10 and MMP25 in ovarian cancer tissues were elevated compared with normal ovarian tissues. This study demonstrated that MMPs can be a reliable prognostic biomarker for ovarian cancer.

Purpose: Although the mortality of elderly women with cervical cancer is high, their characteristics and prognosis have not attracted sufficient attention. This study aims to clarify the prognostic factors of cervical cancer patients aged ≥ 65. Patient and Methods: The incidences and characteristics of patients diagnosed with cervical cancer (aged ≥ 65 and < 65) during 2004– 2015 were obtained through the Surveillance, Epidemiology, and End Results Program (SEER) database. The differences of distributions of characteristics between two age groups were compared by chi-squared (χ²) test. Kaplan–Meier survival method, Log-rank test, Cox-regression and visual nomogram were utilized for survival analysis. Results: The annual incidences of two age groups with cervical cancer were (5.5– 7.5)/100,000 and (3.4– 3.9)/100,000, respectively, during 2004– 2015. The 1-year and 5-year cancer-specific survival rates of old patients were both lower than those of young patients (P < 0.001). The proportions of unmarried state and advanced International Federation of Gynecology and Obstetrics (FIGO) stage in old patients were higher than those in relatively young patients, and fewer elderly patients received surgery. Univariate and multivariate survival analysis showed non-squamous cell carcinoma, poor differentiation and late FIGO stage were independent poor prognostic factors for patients aged ≥ 65. Treatments improved the outcomes of elderly patients, and the effect of surgery was better than non-surgical treatment on elderly patients with FIGO I. Besides, geriatric score and survival probability could be accomplished by our nomogram with a c-index of 0.7945. Conclusion: Delayed diagnosis and insufficient treatment were two distinct features of elderly patients and correlated with their poor clinical outcomes. More attention and active treatments should be adopted in elderly women based on their general condition.

Background: There is urgent need for an accurate preoperative prediction of metastatic status to optimize treatment for patients with ovarian cancer (OC). The feasibility of predicting the metastatic status based on radiomics features from preoperative computed tomography (CT) images alone or combined with clinical factors were investigated.Methods: A total of 101 OC patients who underwent primary debulking surgery were enrolled. Radiomics features were extracted from the tumor volumes contoured on CT images with LIFEx package. Mann-Whitney U tests, least absolute shrinkage selection operator (LASSO), and Ridge Regression were applied to select features and to build prediction models. Univariate and regression analysis were applied to select clinical factors for metastatic prediction. The performance of models generated with radiomics features alone, clinical factors, and combined factors were evaluated and compared.Results: Nine radiomics features were screened out from 184 extracted features to classify patients with and without metastasis. Age and cancer antigen 125 (CA125) were the two clinical factors that were associated with metastasis. The area under curves (AUCs) for the radiomics signature, clinical factors model, and combined model were 0.82 (95% CI, 0.66-0.98; sensitivity = 0.90, specificity = 0.70), 0.83 (95% CI, 0.67-0.95; sensitivity = 0.71, specificity = 0.8), and 0.86 (95% CI, 0.72-0.99, sensitivity = 0.81, specificity = 0.8), respectively.Conclusions: Radiomics features alone or radiomics features combined with clinical factors are feasible and accurate enough to predict the metastatic status for OC patients.

Background: Cervical cancer became the third most common cancer among women, and genome characterization of cervical cancer patients has revealed the extensive complexity of molecular alterations. However, identifying driver mutation and depicting molecular classification in cervical cancer remain a challenge.Methods: We performed an integrative multi-platform analysis of a cervical cancer cohort from The Cancer Genome Atlas (TCGA) based on 284 clinical cases and identified the driver genes and possible molecular classification of cervical cancer.Results: Multi-platform integration showed that cervical cancer exhibited a wide range of mutation. The top 10 mutated genes were TTN, PIK3CA, MUC4, KMT2C, MUC16, KMT2D, SYNE1, FLG, DST, and EP300, with a mutation rate from 12 to 33%. Applying GISTIC to detect copy number variation (CNV), the most frequent chromosome arm-level CNVs included losses in 4p, 11p, and 11q and gains in 20q, 3q, and 1q. Then, we performed unsupervised consensus clustering of tumor CNV profiles and methylation profiles and detected four statistically significant expression subtypes. Finally, by combining the multidimensional datasets, we identified 10 potential driver genes, including GPR107, CHRNA5, ZBTB20, Rb1, NCAPH2, SCA1, SLC25A5, RBPMS, DDX3X, and H2BFM.Conclusions: This comprehensive analysis described the genetic characteristic of cervical cancer and identified novel driver genes in cervical cancer. These results provide insight into developing precision treatment in cervical cancer.