Developing and validating ultrasound‐based machine‐learning models incorporating radiomics features to predict malignancy in adnexal masses

Key Points

• The aim is to investigate the effectiveness of radiomics analysis in distinguishing benign from malignant adnexal masses.
• Development of machine learning models using radiomics features from ultrasound images.
• Assessment of model performance in predicting malignancy of adnexal masses.
• Consideration of using multiple images per tumor for improved accuracy.
• Recommendation for external validation to ensure model generalizability.
• Initial results support the potential of radiomics in differentiating malignancy from benign conditions.
• Future studies should expand to larger populations for comprehensive validation.