Deep learning model for classifying endometrial lesions.

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.

LncRNA MONC suppresses the malignant phenotype of Endometrial Cancer Stem Cells and Endometrial Carcinoma Cells by regulating the MiR-636/GLCE axis.

BACKGROUND: Emerging evidence shows that abnormal expression of long non-coding RNA is involved in the occurrence and development of various tumors. LncRNA MONC is abnormally expressed in head and neck squamous cell carcinoma, lung cancer, colorectal cancer, and acute megakaryocytic leukemia, but the biological function and potential regulatory mechanism of MONC in endometrial cancer stem cells (ECSCs) and endometrial cancer cells (ECCs) have not been studied. In this study, we aimed to explore the tumor suppressive effect and mechanism of MONC in regulating ECSCs and ECCs. METHODS: We used qRT-PCR to detect the expression of MONC, miR-636 and GLCE in normal human endometrial tissues and endometrial carcinoma (EC) tissues. Luciferase assay was used to verify the binding sites between MONC and miR-636 and between miR-636 and GLCE. Double fluorescence in situ hybridization was used to locate MONC and miR-636 in cells. ECSCs were obtained by flow cytometry sorting assay. Sphere formation assay, CCK-8 assay, transwell invasion assay, cell cycle analysis and apoptosis assay were used to detect the effects of MONC/miR-636/GLCE axis on the malignant biological behavior of ECSCs and ECCs. The effect of MONC on the epithelial-to-mesenchymal transition (EMT) process was detected using western blot. Finally, we conducted in vivo verification through Tumor xenografts in BALB/C nude mice. RESULTS: In this study, we found MONC is low expression in endometrial carcinoma (EC) and patients in the MONC high-expression group had a better prognosis. MONC and miR-636 are relatively co-localized in the cytoplasm. MONC directly inhibits the malignant biological behavior of ECSCs and ECCs by directly inhibiting miR-636. Simultaneously, miR-636 may indirectly reduce the expression of MONC. Down-regulation of miR-636 may promote GLCE expression by targeting the 3'-untranslated region (UTR) of the downstream gene GLCE, thereby inhibiting the progression of ECSCs. MONC combined with miR-636 inhibited tumor epithelial-to-mesenchymal transition (EMT) process. In addition, we verified the tumor suppressive effect of MONC in nude mice, miR-636 can rescue the tumor suppressive effect of overexpressing MONC. CONCLUSIONS: In conclusion, this study showed that MONC inhibits the malignant phenotypes of ECSCs and ECCs by regulating the miR-636/GLCE axis. Thus the MONC/miR-636/GLCE axis may provide novel treatment avenues for human EC.

BTG1 inhibits malignancy as a novel prognosis signature in endometrial carcinoma.

BACKGROUND: Endometrial carcinoma (EC) is one of the three major malignant tumors of the female reproductive system. In recent years, the incidence and mortality rate of EC have increased. B-cell translocation gene 1 (BTG1) is an anti-proliferation gene that regulates the occurrence and development of a variety of tumors, but there is no research regarding this gene in EC. METHODS: Based on The Cancer Genome Atlas (TCGA) database, we used a variety of bioinformatics tools and databases to explore the expression and prognosis of BTG1. We verified expression and prognosis of BTG1 in EC using qRT-PCR and analyzed the relevant clinicopathological parameters. We functionally enriched BTG1 and related genes in EC patients through the bioinformatics website and analyzed miRNA targets of BTG1 and interacting protein networks. Cell proliferation, wound healing, transwell invasion, and cell apoptosis assays were used to detect the effects of BTG1 on the malignant biological behavior of endometrial carcinoma cells (ECCs). The effect of BTG1 on the epithelial-to-mesenchymal transition (EMT) process was detected using western blot. RESULTS: We analyzed the expression and prognosis of BTG1 based on TCGA and found that low expression of BTG1 was associated with poor EC prognosis. The qRT-PCR suggested that BTG1 had low expression in EC. BTG1 expression was significantly correlated with overall survival (OS) shortening. Clinicopathological analysis suggested that expression of BTG1 was related to invasion depth and the International Federation of Gynecology and Obstetrics (FIGO) stage. EC pathological tissue type, fertility history, lymphatic metastasis, menopause, estrogen receptor (ER), progesterone receptor (PR), and age of diagnosis were not related. Functional enrichment analysis showed that BTG1 plays an important role in regulating embryonic development, tumorigenesis, apoptosis, and cell cycle. Biological behavior experiments suggest that BTG1 inhibits proliferation, migration, and invasion of ECCs, and promotes apoptosis of ECCs. Western blot indicated that BTG1 inhibited the EMT process of ECCs. CONCLUSIONS: BTG1, as a tumor suppressor gene, plays an important role in the occurrence and development of EC. We believe that BTG1 can be used as a potential prognostic biomarker for EC.

Hyperhomocysteinemia in polycystic ovary syndrome: decreased betaine-homocysteine methyltransferase and cystathionine ß-synthase-mediated homocysteine metabolism.

RESEARCH QUESTION: What are the metabolic characteristics of homocysteine in polycystic ovary syndrome (PCOS)? DESIGN: Homocysteine concentrations were determined in serum samples from non-obese and obese control subjects and PCOS patients. Homocysteine metabolism was studied in a rat model of PCOS established using dehydroepiandrosterone (DHEA) or DHEA in combination with a high-fat diet (HFD). RESULTS: It was shown that (i) serum homocysteine concentrations were greater in PCOS patients than in control subjects in the obese group (P < 0.05) and serum homocysteine concentrations were significantly higher in the obese group than in the non-obese group, regardless of PCOS status (both P < 0.05); (ii) serum homocysteine concentrations were significantly increased in DHEA + HFD-induced rats compared with controls (P < 0.05); (iii) when compared with the control group, mRNA concentrations of homocysteine metabolic enzymes Bhmt and Cbs were significantly reduced in the liver tissues of DHEA + HFD-induced rats (both P < 0.0001); (iv) when compared with the control group, there was a significant decrease in the methylation concentrations of the Cbs (P < 0.05) and Bhmt (P < 0.05 and P < 0.0001) promoter in the DHEA + HFD group. The methylation patterns, together with previous data, indicate that hypomethylated promoter-mediated transcriptional activation of Bhmt and Cbs might be a defence mechanism against PCOS-related hyperhomocysteinemia. CONCLUSIONS: These findings indicate that decreased liver Bhmt and Cbs-mediated homocysteine metabolism might have a role in hyperhomocysteinemia in PCOS and provides further evidence for a potential role of decreased liver function in PCOS.

Preliminary identification of endometrial cancer stem cells in vitro and in vivo.

Stem cells play a critical role in endometrial cancer progression. However, the current methodologies used to isolate endometrial cancer stem cells (ECSCs) remain unsatisfactory. The ECSCs were isolated by serumfree suspension cultivation. The stem cells-related genes CD44, CD133, Oct4, Sox2 and Nanog were analyzed, and the biological behaviour of ECSCs was evaluated in vitro and vivo. The results suggest that (i) serumfree suspension cultivation is non-toxic and a convenient way for isolating the ECSCs, and is not limited to specific surface markers; (ii) Ishikawa cells can be used as an effective source of ECSCs, and the obtained ECSCs expressing the pluripotent stem cells markers CD44, CD133, Oct4, Sox2, and Nanog; (iii) ECSCs originated from Ishikawa cells showed an increased ability to invasion and metastasis in vitro, and exhibited a high proliferative capacity and pluripotency in vivo and vitro. These findings indicate that serumfree suspension cultivation is an effective method for isolating ECSCs from Ishikawa cells, and the obtained ECSCs are tumorigenic and display stem cell-like properties.

Bioinformatics Identification of the Expression and Clinical Significance of E2F Family in Endometrial Cancer.

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.

LINC01016 promotes the malignant phenotype of endometrial cancer cells by regulating the miR-302a-3p/miR-3130-3p/NFYA/SATB1 axis.

Long noncoding RNAs (lncRNAs) have been implicated in tumorigenesis and cancer progression and are tightly associated with the phenotypes of numerous cancers. However, the functional roles underlying these effects are unknown. The expression levels of LINC01016, miR-302a-3p, miR-3130-3p, NFYA, and SATB1 were evaluated by quantitative real-time polymerase chain reaction (qRT-PCR) in 33 endometrial cancer tissues and 20 normal tissues. Bioinformatics analyses, luciferase reporter analyses, chromatin immunoprecipitation (ChIP) assays, and qRT-PCR assays were performed to verify potential binding sites. The qRT-PCR and western blot were used to identify the regulatory mechanisms of LINC01016 in cell biological behavior, which were also examined by cell counting kit -8 (CCK-8), 5-ethynyl-2'-deoxyuridine (EdU) assays, flow cytometry, wound healing assays, and transwell assays. LINC01016 was substantially upregulated in endometrial cancer tissues, and LINC01016 silencing abolished the malignant behavior of endometrial cancer cells. LINC01016 positively rescued the downstream gene nuclear factor YA (NFYA) by competitively "sponging" miR-302a-3p and miR-3130-3p. In turn, these two miRNAs could inhibit LINC01016 transcription, thus forming two reciprocal repression cycles, which influenced the biological behavior of endometrial cancer cells. MiR-302a-3p and miR-3130-3p could specifically bind with the 3'-UTR regions of NFYA, and NFYA could upregulate the expression of special AT-rich sequence-binding protein 1 (SATB1) as a transcriptional factor. This study was the first to show that the LINC01016-miR-302a-3p/miR-3130-3p/NFYA/SATB1 axis played a crucial role in the occurrence of endometrial cancer. These findings may provide relevant insights into the diagnosis and therapy of endometrial cancer.

MicroRNA 302b-3p/302c-3p/302d-3p inhibits epithelial-mesenchymal transition and promotes apoptosis in human endometrial carcinoma cells.

BACKGROUND: Studies have shown that the microRNA miR-302 can affect the proliferation, migration and cell cycle progression of endometrial carcinoma (EC). miR-302 clusters have been shown to play an important role in the proliferation and differentiation of cancer cells and in their tumorigenicity. SUBJECTS AND METHODS: In this study, we detected the expression of genes through quantitative reverse transcription polymerase chain reaction (qRT-PCR). We detected the expression of proteins through Western blot. The Annexin V-fluorescein isothiocyanate (FITC)/propidium iodide (PI) double-staining assay were used to detect the ability of miR-302b-3p/302c-3p/302d-3p to affect the cell apoptosis. The CCK-8 were used to detect the ability of miR-302b-3p/302c-3p/302d-3p to affect the cell proliferation. The Cell cycle analysis were used to detect the ability of miR-302b-3p/302c-3p/302d-3p to affect the cell cycle. Finally, the wound healing assay was used to detect the ability of miR-302b-3p/302c-3p/302d-3p to impact cell migration. RESULTS: We found that miR-302b-3p/302c-3p/302d-3p of the miR-302 cluster was downregulated in EC, and it altered the epithelial-mesenchymal transition (EMT) process in the EC cell lines Ishikawa and HEC-1A. Western blot and the Annexin V- FITC/PI double-staining assay were used to detect the ability of miR-302b-3p/302c-3p/302d-3p to promote the apoptosis of Ishikawa and HEC-1A cells. In addition, qRT-PCR results showed that overexpression of miR-302b-3p/302c-3p/302d-3p significantly inhibited the expression of ZEB1, suppressed the expression of Bcl-2 and promoted the expression of BAX. The overexpression of miR-302b-3p/302c-3p/302d-3p inhibited the proliferation and migration of Ishikawa and HEC-1A cells. Cell cycle analysis showed that miR-302b-3p/302c-3p/302d-3p arrested cell cycle progression in the G0/G1 phase. CONCLUSION: All results showed that miR-302b-3p/302c-3p/302d-3p can be used as a tumor suppressor in EC and is expected to be a new target for the treatment of EC.