Correlation of Metabolic Factors with Endometrial Atypical Hyperplasia and Endometrial Cancer: Development and Assessment of a New Predictive Nomogram

Abstract Purpose: This study aimed to investigate the association of metabolic factors with endometrial atypical hyperplasia and endometrial cancer, and to develop a Nomogram model to predict the risk of developing endometrial cancer.Patients and methods: A total of 205 patients with 102 cases of endometrial atypical hyperplasia and 103 cases of endometrial carcinoma treated by the Department of Gynecological Oncology, Beijing Obstetrics and Gynecology Hospital, Capital Medical University, from January 1, 2010, to December 31, 2015 were collected as the study group. And 205 patients with simple endometrial hyperplasia or polyp hyperplasia in the same period were selected as the control group using age-matched method. Laboratory results of metabolic factors such as blood pressure (BP), glucose (GLU), triglycerides (TC), and high-density lipoprotein (HDL) were retrieved from the clinical data of two groups of patients. Multivariable logistic regression analysis was used to determine the risk factors associated with endometrial malignant hyperplasia and to develop a nomogram prediction model of risk factors associated with endometrial malignant hyperplasia. Discrimination, calibration, and clinical usefulness of the predicting model were assessed using the C-index, calibration plot, and decision curve analysis. Internal validation was assessed using the bootstrapping validation.Results: Predictors included in the Nomogram prediction model included hypertension, diabetes, BMI, uric acid, hyperlipidemia and CA199. The model had a C-index of 0.782 (95% confidence interval 0.738-0.826) with good discrimination and good calibration. A high C-index value of 0.771 could still be reached in the interval validation. Decision curve analysis showed that it is meaningful to use this Nomogram for patient interventions when the threshold probability is within 22-86%.Conclusion: The development of endometrial malignant hyperplasia is significantly associated with metabolic factors. BMI>25, hyperuricemia, and hyperlipidemia are the main risk factors for the development of endometrial malignant hyperplasia. Hypertension, hyperglycemia and elevated CA199 were also associated with the development of endometrial malignant hyperplasia in our study. The Nomogram prediction model based on physical examination and laboratory testing developed in this study can be used as a rapid method for predicting the risk of endometrial malignancy development and screening for risk factors in a population of women with metabolism-related high-risk factors.

Download Full-text

Deep learning model for classifying endometrial lesions

Journal of Translational Medicine ◽

10.1186/s12967-020-02660-x ◽

2021 ◽

Vol 19 (1) ◽

Author(s):

YunZheng Zhang ◽

ZiHao Wang ◽

Jin Zhang ◽

CuiCui Wang ◽

YuShan Wang ◽

...

Keyword(s):

Endometrial Cancer ◽

Endometrial Hyperplasia ◽

Histogram Equalization ◽

Atypical Hyperplasia ◽

Endometrial Polyps ◽

Submucous Myoma ◽

Objective Model ◽

Medical University ◽

Deep Learning Model ◽

Better Than

Abstract 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.

Download Full-text

Progesterone receptor (PROGINS) polymorphism and the risk of endometrial cancer development

International Journal of Gynecological Cancer ◽

10.1111/j.1525-1438.2006.00767.x ◽

2007 ◽

Vol 17 (1) ◽

pp. 229-232 ◽

Cited By ~ 18

Author(s):

M. G. Junqueira ◽

I. D.C.G. Da Silva ◽

N. C. Nogueira-De-Souza ◽

C. V. Carvalho ◽

D. B. Leite ◽

...

Keyword(s):

Endometrial Cancer ◽

Progesterone Receptor ◽

Receptor Gene ◽

Population Based ◽

Cancer Development ◽

Control Group ◽

Cancer Group ◽

Increased Risk ◽

Progesterone Receptor Gene ◽

Risk Modifier

The progesterone receptor gene (PROGINS) has been identified as a risk modifier for benign and malignant gynecological diseases. The present case-control study is to evaluate the role of the PROGINS polymorphisms, as risk factor, for endometrial cancer development and to investigate the association between these genetics variants and clinical/pathologic variables of endometrial cancer. PROGINS polymorphism was examined in a total of 121 patients with endometrial cancer and 282 population-based control subjects, all located at the same area in São Paulo, SP, Brazil. The genotyping of PROGINS polymorphism was determined by polymerase chain reaction. The frequencies of PROGINS polymorphism T1/T1, T1/T2, and T2/T2 were 82.6%, 14.9%, and 2.5% in the endometrial cancer patients and 78.4%, 21.6%, and 0% in the controls, respectively. The χ2 test showed a higher incidence of the T2/T2 genotype in the endometrial cancer group subjects, these results were statistically different (P= 0.012). However, due to the fact that there were no women in the control group showing homozygosis for the allele T2, the correct evaluation of odds ratio could not be properly calculated. Regarding the clinical and pathologic findings observed within the group of patients with endometrial cancer, there was significant correlation between T1/T2 genotype and the presence of myoma (P= 0.048). No correlations were observed among the other variables. These data suggest that the PROGINS polymorphism T2/T2 genotype might be associated with an increased risk of endometrial cancer.

Download Full-text