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.

A Systematic Review and Meta-analysis of Telephone-Based Therapy Targeting Depressive Symptoms Among Low-Income People Living with HIV.

People living with human immunodeficiency virus (PLWH) has been reported to have a high prevalence of depressive symptoms. Low-income populations account for a large proportion of PLWH, hence indicating a high level of depressive symptoms in low-income PLWH. Telephone-based therapy has been shown to be effective for treating PLWH's depressive symptoms, but its effects among low-income PLWH remain unclear. The purpose of this meta-analysis was to evaluate the effects of telephone-based therapy targeting depressive symptoms among low-income PLWH. Six databases (PubMed, EMBASE, Web of Science, China National Knowledge Infrastructure, VIP Database and Wanfang Data) were searched until May 2020 using search terms related to telephone-based therapy, depressive symptoms, and PLWH. Eight studies were included in the meta-analysis. Both postintervention effects (primary outcome) and long-term effects (secondary outcome) were evaluated using a random effects model. The meta-analysis revealed a small to moderate effect size (g = - 0.29, 95% CI - 0.51, - 0.06) on reducing depressive symptom scores (Z = 2.51, p = 0.01) in telephone-based intervention group compared with the control group at postintervention. However, there was no statistically significant long-term effects (Z = 0.77, p = 0.44) at follow-up. For postintervention effects, calculation of the I2 index indicated moderate heterogeneity (I2 = 50%); sensitivity analysis and subgroup analysis were performed to explore the source of heterogeneity. Ethnic group was classified into minority and majority which refers to most of the population were ethnic minority and majority respectively. Between-group differences were found across ethnic groups. The results suggested that there was a slightly stronger effect of telephone-based therapy in low-income PLWH than among PLWH in general, but its long-term effect requires future investigation. The effects of the intervention were better among the ethnic majority subgroups of low-income PLWH. Treatment format and intervention duration might also influence the intervention effects. However, the overall quality of evidence was low and directly impacted on the interpretation of our results, suggesting that more high-quality random controlled trial (RCT)/longitudinal studies with less selection and detection bias, less inconsistency and less indirectness are needed when applying telephone-based therapy to low-income PLWH with depressive symptoms in further studies.

RESUMEN: Se ha informado de que las personas con el virus de la inmunodeficiencia humana (PLWH) tienen un alto riesgo de síntomas depresivos, y las personas de bajos ingresos ocupan una gran proporción de PLWH. El objetivo de este análisis es evaluar los efectos de la terapia telefónica para los síntomas depresivos en personas con PLWH de bajos ingresos. Se realizaron búsquedas en seis bases de datos hasta mayo de 2020, incluidos ocho estudios. En comparación con el grupo de control, el análisis reveló que en el grupo de intervención telefónica contaba con un efecto pequeño a moderado (g = -0.29, IC 95% -0.51, -0.06) en la reducción de las puntuaciones de síntomas depresivos (Z = 2.51, p = 0.01). Sin embargo, no hubo efectos estadísticamente significativos a largo plazo (Z = 0.77, p = 0.44) en el seguimiento. Se encontraron diferencias entre grupos desde los grupos étnicos. Los resultados mostraron que el efecto de la terapia telefónica era levemente más fuerte que el de PLWH general en las PLWH de bajos ingresos, pero la evidencia general de baja calidad impactó en la interpretación de nuestros resultados.

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.