Diagnosis of Malignant Endometrial Lesions from Ultrasound Radiomics Features and Clinical Variables Using Machine Learning Methods

Background: The prognosis of patients with early diagnosis of malignant endometrial lesions is good. We aimed to identify benign and malignant lesions in endometrial tissue, explore effective methods for assisting diagnosis, and improve the accuracy and precision of identifying endometrial lesions.Methods: 1142 ultrasound radiomics and 18 clinical features from 1254 patients were analyzed, from which 36 features were selected for machine learning. We sketched the region of interest (ROI) of the abnormalities on the ultrasound images. Then, the radiomics features were extracted. Six common machine learning algorithms, including Support Vector Machine (SVM), Logistic Regression, Decision Tree, Random Forest, Gradient Boosting Tree, and k-Nearest Neighbors, were employed to identify benign and malignant changes in endometrial tissue. Cross-validation and grid search techniques for hyperparameter tuning were utilized to obtain the best model performance. Accuracy, precision, sensitivity, F1-scores, area under the curve (AUC), cross-validation average score and bootstrap average accuracy were also used to evaluate algorithm performance, classification accuracy, and generalization capability.Results: We combined 21 ultrasound characteristics and 15 clinical characteristics to develop and validate six common machine learning algorithms. After internal validation, the best models were the Random Forest models, with accuracy of 89%, precision of 93%, sensitivity of 97%, F1-score of 95%, and AUC of 95%, as well as a 10-fold cross-validation average score of 95% and bootstrap average accuracy of 94%, implying flawless classification in the test set.Conclusions: We identified the clinical and ultrasound features in the early diagnosis of benign or malignant lesions in endometrial tissue. And Random Forest model algorithms have demonstrated excellent performance in identifying benign and malignant changes in endometrial tissue. This is significant for enhancing early diagnostic accuracy and improving treatment outcomes and long-term management.