Abstract
OBJECTIVES: This study aimed to develop a nomogram for predicting intrauterine pregnancy after an in vitro frozen embryo transfer cycle using endometrial ultrasound radiomics. METHODS: A total of 211 patients who underwent ultrasound examination on the day of endometrial transformation before the frozen embryo transfer cycle were enrolled. The patients were divided into an intrauterine pregnancy group and a pregnancy failure group based on ultrasound results. Clinical characteristics and radiomic features were analyzed using univariate and multivariate logistic regression analyses. A nomogram prediction model was established based on radiomic signatures and significant clinical factors. The model's robustness was assessed in training and external validation cohorts. RESULTS: Nine radiomic features were selected using least absolute shrinkage and selection operator (LASSO), and the radiomics score (Rad-score) was calculated as the sum of each feature multiplied by the nonzero coefficient from LASSO. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve based on the Rad-score was 0.72, 0.65, and 0.69 in the training, validation, and combined cohorts, respectively. To improve diagnostic efficiency, the Rad-score was further integrated with clinical factors to form a novel predictive nomogram. The results indicated that the AUC increased to 0.81, 0.67, and 0.77 in the training, validation, and combined cohorts, respectively. Decision curve analysis showed that the radiomics nomogram was clinically useful. CONCLUSION: The radiomics and clinical predictive nomogram can effectively predict intrauterine pregnancy after in vitro frozen embryo transfer and can be further applied in clinical strategy.