Logistic regression analysis of imaging characteristics of transvaginal ultrasonography for predicting severe endometriosis by r-ASRM classification via laparoscopy

Background:To explore the relation between results of transvaginal ultrasonography and the revised American Society for Reproductive Medicine (r-ASRM) staging based on laparoscopy in patients with endometriosis (EMT) and to establish a prediction model for risk of severe endometriosis based on the imaging characteristics of transvaginal ultrasonography.Materials and Methods: A retrospective study was performed between April 2022 and May 2023 on women with EMT.The laparoscopic surgery results were used as the golden standard.Patients were divided into the minimal-to-moderate endometriosis (stage I-III) and severe endometriosis (stage IV) groups based on r-ASRM classification.The transvaginal ultrasonography imaging characteristics were extracted to establish a logistic regression model.Results: Among 200 patients with endometriosis, there were 78 cases of minimal-to-moderate endometriosis (stage I-III) and 122 cases of severe endometriosis (stage IV).Multivariate analysis showed that the maximum diameter of endometriomas in the right ovary, occurrence of unilateral or bilateral ovarian endometriomas, and degree of obliteration of the rectouterine pouch were independent predictors for the r-ASRM stage of endometriosis.The logistic regression model established using the above three variables had a sensitivity of 82.0%, a specificity of 93.6%, an accuracy of 86.5%, and an area under the curve of 0.933 (standard error 0.016, P < 0.005, 95% confidence interval: 0.901, 0.965).Conclusion: Based on laparoscopic visualization, the radiomic features of preoperative transvaginal ultrasonography in patients with endometriosis were correlated with the endometriotic stage.The established model using these characteristics accurately predicted the r-ASRM stage of endometriosis after laparoscopic surgery.