Endometrial cancer is a ubiquitous gynecological disease with increasing global incidence. Therefore, despite the lack of an established screening technique to date, early diagnosis of endometrial cancer assumes critical importance. This paper presents an artificial-intelligence-based system to detect the regions affected by endometrial cancer automatically from hysteroscopic images. In this study, 177 patients (60 with normal endometrium, 21 with uterine myoma, 60 with endometrial polyp, 15 with atypical endometrial hyperplasia, and 21 with endometrial cancer) with a history of hysteroscopy were recruited. Machine-learning techniques based on three popular deep neural network models were employed, and a continuity-analysis method was developed to enhance the accuracy of cancer diagnosis. Finally, we investigated if the accuracy could be improved by combining all the trained models. The results reveal that the diagnosis accuracy was approximately 80% (78.91–80.93%) when using the standard method, and it increased to 89% (83.94–89.13%) and exceeded 90% (i.e., 90.29%) when employing the proposed continuity analysis and combining the three neural networks, respectively. The corresponding sensitivity and specificity equaled 91.66% and 89.36%, respectively. These findings demonstrate the proposed method to be sufficient to facilitate timely diagnosis of endometrial cancer in the near future.

Endometrial cancer is one of the most frequently diagnosed gynecological malignancies worldwide. However, its prognosis in advanced stages is poor, and there are only few available treatment options when it recurs. Epigenetic changes in gene function, such as DNA methylation, histone modification, and non-coding RNA, have been studied for the last two decades. Epigenetic dysregulation is often reported in the development and progression of various cancers. Recently, epigenetic changes in endometrial cancer have also been discussed. In this review, we give the main points of the role of DNA methylation and histone modification in endometrial cancer, the diagnostic tools to determine these modifications, and inhibitors targeting epigenetic regulators that are currently in preclinical studies and clinical trials.

Endometrioid endometrial carcinoma, commonly known as type 1 endometrial cancer, accounts for >80% of endometrial carcinomas and is dependent on estrogen. We recently reported on the prognostic significance of the BIRC5 survivin gene in endometrial cancer. Estradiol induces survivin expression in estrogen receptor-positive, but not in estrogen receptor-negative, cancer cells. Kaempferol, a bioflavonoid, reportedly inhibits estrogen receptor-alpha (ER alpha) in hormone receptor-positive breast cancer cells. However, whether kaempferol-mediated inhibition of ER alpha suppresses survivin and induces cell death in endometrial cancer remains unclarified. The present study evaluated the antitumor effects of kaempferol on endometrial cancer cells. Cell viability assays, flow cytometry analysis, western blotting and annexin V analyses were used to analyze the antitumor effects of kaempferol. The results demonstrated that kaempferol successfully suppressed the viability of two ER-positive endometrial cancer cell lines, with IC50 values of 83 and 65 mu M. In addition, kaempferol induced sub-G1 cell accumulation and apoptotic cell death (P<0.01) in a dose-dependent manner. Treatment of cells with estradiol significantly induced co-expression of nuclear ER alpha and survivin proteins (P<0.001). Further evaluation revealed that kaempferol causes apoptotic cell death largely by suppressing ER alpha, survivin and Bcl-2 protein. Therefore, the results of the present study suggested that targeting ER alpha and survivin with kaempferol may be a novel therapeutic option against endometrial carcinoma.

Previous studies have suggested that histone methylation can modulate carcinogenesis and cancer progression. For instance, the histone methyltransferase SET and MYND domain containing 2 (SMYD2) is overexpressed in several types of cancer tissue. The aim of the present study was to determine whether SMYD2 could serve a therapeutic role in ovarian clear cell carcinoma (OCCC). Reverse transcription‑quantitative PCR was used to examine SMYD2 expression in 23 clinical OCCC specimens. Moreover, OCCC cell proliferation and cell cycle progression were also examined following small interfering RNA‑mediated SMYD2 silencing or treatment with a selective SMYD2 inhibitor. SMYD2 was significantly upregulated in clinical OCCC specimens, compared with normal ovarian tissue. In addition, SMYD2 knockdown decreased cell viability as determined via a Cell Counting Kit‑8 assay. Moreover, the proportion of cells in the sub‑G₁ phase increased following SMYD2 knockdown, suggesting increased apoptosis. Treatment with the SMYD2 inhibitor LLY‑507 suppressed OCCC cell viability. These results suggested that SMYD2 could promote OCCC viability, and that SMYD2 inhibition induced apoptosis in these cells. Thus, SMYD2 inhibitors may represent a promising molecular targeted approach for OCCC treatment.