Correlation between pre-operative diagnosis and final pathological diagnosis of endometrial malignancies; impact on primary surgical treatment

Current challenges and emerging tools in endometrial cancer diagnosis

The diagnostic process of endometrial cancer includes imaging methods such as trans-vaginal ultrasound, along with procedures to obtain endometrial tissue for histologic evaluation. Common techniques for tissue sampling include Pipelle endometrial biopsy, hysteroscopy, and dilation and curettage, which are used to confirm the diagnosis, determine tumor histology, grade, and molecular profile. However, diagnostic algorithms for endometrial cancer differ significantly across countries, influenced by local resources, protocols, and the availability of diagnostic methods. These variations include differences in the endometrial thickness threshold for recommending a biopsy and the choice of the initial diagnostic test. Moreover, patients often have multiple tests and appointments before a definitive diagnosis, although only 5%-10% of women with post-menopausal bleeding are diagnosed with endometrial cancer. Current diagnostic techniques have limitations. Pipelle endometrial biopsy has a significant false-negative rate (10%-20%) and may fail to provide adequate diagnostic material in up to 30% of cases. Hysteroscopy, while useful, is associated with pain in up to 65% of patients and can delay diagnosis because of limited availability. Dilation and curettage is an invasive procedure requiring general anesthesia and has a higher complication rate. In response to these challenges, there is growing interest in developing new diagnostic tools that are less invasive and provide 1-step diagnoses, including liquid biopsies from urine, blood, cervico-vaginal and endometrial fluid samples by means of genomics and proteomics. This review will examine the current diagnostic algorithms in European and American guidelines, evaluate the sensitivity, specificity, and accuracy of current techniques, and explore new diagnostic tools under development.

Preoperative detection of occult endometrial malignancies in endometrial hyperplasia to improve primary surgical therapy: A scoping review of the literature

The risk of undertreating occult endometrial cancer is a problem faced by gynecologists when treating endometrial hyperplasia. The objective of this study is to highlight diagnostic adjuncts to endometrial sampling techniques to improve preoperative detection of co-existing cancer. A systematic search of databases till July 2021: PubMed, ISI-Clarivate Web of Science, Scopus, and CENTRAL. A search of the related literature was also carried out. Two authors screened potential studies. Studies were included if they examined the diagnostic performance of any predictors of concurrent cancer in patients diagnosed with endometrial hyperplasia. Authors charted variables related to literature characteristics (e.g., authors, year of publication), population characteristics (e.g., preoperative diagnoses), and variables related to our research questions (e.g., postoperative diagnoses, risk predictors). After screening 591 potential studies, 28 studies were included. Studies included the data of 7409 endometrial hyperplasia patients with 2377 concurrent endometrial cancer cases (32.1%). Forty potential predictors of concurrent cancer were investigated. We examined three categories of potential predictors: clinical (22 studies), histopathologic/imaging (16 studies), and molecular (six studies) predictors. The proposed predictors, age, menopausal status, diabetes, WHO and endometrial intraepithelial neoplasia histopathologic criteria, pelvic magnetic resonance imaging, and molecular profiling are promising diagnostic adjuncts.

Diagnosis and Prediction of Endometrial Carcinoma Using Machine Learning and Artificial Neural Networks Based on Public Databases

Endometrial carcinoma (EC), a common female reproductive system malignant tumor, affects thousands of people with high morbidity and mortality worldwide. This study was aimed at developing a prediction model for the diagnosis of EC in the general population. First, we obtained datasets GSE63678, GSE106191, and GSE115810 from the Gene Expression Omnibus (GEO) database, dataset GSE17025 from the GEO database, and the RNA sequence of EC from The Cancer Genome Atlas (TCGA) database to constitute the training, test, and validation groups, respectively. Subsequently, the 96 most significantly differentially expressed genes (DEGs) were identified and analyzed for function and pathway enrichment in the training group. Next, we acquired the disease-specific genes by random forest and established an artificial neural network for the diagnosis. Receiver operating characteristic (ROC) curves were utilized to identify the signature across the three groups. Finally, immune infiltration was analyzed to reveal tumor-immune microenvironment (TIME) alterations in EC. The top 96 DEGs (77 down-regulated and 19 up-regulated genes) were primarily enriched in the interleukin-17 signaling pathway, protein digestion and absorption, and transcriptional misregulation in cancer. Subsequently, 14 characterizing genes of EC were identified by random forest. In the training, test, and validation groups, the artificial neural network was constructed with high diagnostic accuracies of 0.882, 0.864, and 0.839, respectively, and areas under the ROC curve (AUCs) of 0.928, 0.921, and 0.782, respectively. Finally, resting and activated mast cells were found to have increased in TIME. We constructed an artificial diagnostic model with excellent reliability for EC and uncovered variations in the immunological ecosystem of EC through integrated bioinformatics approaches, which might be potential diagnostic targets for EC.