Background Hysteroscopy is a commonly used technique for diagnosing endometrial lesions. It is essential to develop an objective model to aid clinicians in lesion diagnosis, as each type of lesion has a distinct treatment, and judgments of hysteroscopists are relatively subjective. This study constructs a convolutional neural network model that can automatically classify endometrial lesions using hysteroscopic images as input. Methods All histopathologically confirmed endometrial lesion images were obtained from the Shengjing Hospital of China Medical University, including endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyps, and submucous myomas. The study included 1851 images from 454 patients. After the images were preprocessed (histogram equalization, addition of noise, rotations, and flips), a training set of 6478 images was input into a tuned VGGNet-16 model; 250 images were used as the test set to evaluate the model’s performance. Thereafter, we compared the model’s results with the diagnosis of gynecologists. Results The overall accuracy of the VGGNet-16 model in classifying endometrial lesions is 80.8%. Its sensitivity to endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyp, and submucous myoma is 84.0%, 68.0%, 78.0%, 94.0%, and 80.0%, respectively; for these diagnoses, the model’s specificity is 92.5%, 95.5%, 96.5%, 95.0%, and 96.5%, respectively. When classifying lesions as benign or as premalignant/malignant, the VGGNet-16 model’s accuracy, sensitivity, and specificity are 90.8%, 83.0%, and 96.0%, respectively. The diagnostic performance of the VGGNet-16 model is slightly better than that of the three gynecologists in both classification tasks. With the aid of the model, the overall accuracy of the diagnosis of endometrial lesions by gynecologists can be improved. Conclusions The VGGNet-16 model performs well in classifying endometrial lesions from hysteroscopic images and can provide objective diagnostic evidence for hysteroscopists.

Background Besides being one of the most prevalent cancers among women, incidence and mortality rates of endometrial cancer (EC) are still increasing. The E2F family of transcriptional factors is involved in cell differentiation, apoptosis, and inhibition of DNA damage response, thus affecting growth and invasion of tumor cells. Methods We used multiple bioinformatics tools to explore the role of E2F family in endometrial cancer. Results The expression of E2F1/2/3/7/8 was significantly upregulated in endometrial cancer tissues, converse to E2F4, which was downregulated. Methylation downregulates all E2Fs except for E2F2. Accordingly, E2F1/2/3/5/7/8 are potential diagnostic biomarkers for EC. In particular, EC patients displaying upregulated E2F1, and E2F3 expression had a worse overall survival and relapse-free survival. E2F8, E2F7, and E2F1 were the top three, most-frequently altered genes in endometrial cancer. E2F family activates apoptosis pathways, regulates cell cycle, and impairs DNA damage response pathways. Drug-sensitivity analysis demonstrated that the level of E2F2/3/8 negatively correlated with drug resistance. Meanwhile, immune infiltrations analysis revealed that E2F family is associated with recruitment of several immune cells. Enrichment analysis on its part revealed that the E2F family is mainly associated with cell cycle, sequence-specific DNA binding, nuclear transcription factor complex, PI3K-Akt signaling, and p53 signaling pathway. We also identified multiple E2Fs-associated miRNA and kinase targets in endometrial cancer. Conclusion Our study revealed the unique expression signature and clinical significance of E2F family in EC, demonstrating the potential clinical utility of these transcription factors (TF) in endometrial cancer.