Purpose
Combined with ultrasound-based radiomics, our research team has successfully developed a novel model that enables the evaluation of placental function in rats with pre-eclampsia.
Material and Methods
We have developed a rat model of preeclampsia induced by L-NAME and evaluated placental dysfunction through the analysis of microstructural alterations and immunoprotein levels in placental tissue. After feature extraction of ultrasound images, the Boruta feature selection method was employed to determine the most effective combination of features, and a ten-fold cross-validation method was utilized to establish the optimal model for classifying placental dysfunction. The accuracy, sensitivity, specificity, and AUC were employed to assess the efficacy of the developed model.
Results
In pregnant rats with preeclampsia, significant changes were observed in the microstructure of placental tissue and the expression of the angiogenic factor in the tissue. Ultrasound images of the placenta yielded a total of 558 radiomics features based on high-throughput mining of quantitative image features. After assessment of impaired placental function, an evaluation model was successfully constructed for assessing placental function in pregnant rats. The evaluation model had an AUC of 0.95, with high sensitivity, specificity, accuracy, positive predictive value, and negative predictive value, reaching 88.7%, 91.5%, 90.2%, 90.4%, and 90.0%, respectively.
Conclusion
Ultrasound-based radiomics could effectively identify abnormal placental features in pregnant rats with preeclampsia, and exhibiting high performance in evaluating normal and poor placental function.