Abstract

BackgroundTo predict placental invasion (PI) and determine the subtype according to the degree of implantation, and to help physicians develop appropriate therapeutic measures, a prenatal prediction and typing of placental invasion method using MRI deep and radiomic features were proposed.MethodsThe placental tissue of abdominal magnetic resonance (MR) image was segmented to form the regions of interest (ROI) using U-net. The radiomic features were subsequently extracted from ROI. Simultaneously, a deep dynamic convolution neural network (DDCNN) with codec structure was established, which was trained by an autoencoder model to extract the deep features from ROI. Finally, combining the radiomic features and deep features, a classifier based on the multi-layer perceptron model was designed. The classifier was trained to predict prenatal placental invasion as well as determine the invasion subtype.ResultsThe experimental results show that the average accuracy, sensitivity, and specificity of the proposed method are 0.877, 0.857, and 0.954 respectively, and the area under the ROC curve (AUC) is 0.904, which outperforms the traditional radiomic based auxiliary diagnostic methods.ConclusionsThis work not only labeled the placental tissue of MR image in pregnant women automatically but also realized the objective evaluation of placental invasion, thus providing a new approach for the prenatal diagnosis of placental invasion.

Highlights

  • To predict placental invasion (PI) and determine the subtype according to the degree of implantation, and to help physicians develop appropriate therapeutic measures, a prenatal prediction and typing of placental invasion method using magnetic resonance imaging (MRI) deep and radiomic features were proposed

  • FN(False Negative) was the number of placenta pixels that were incorrectly identified as background and TN(True Negative) was the number of background pixels that were correctly identified as background

  • To optimize the extension size, we extended the placental region of the T2 weighted image (T2WI) MRI image to the surrounding area with 10, 20, 40, 60 pixels to form regions of interest (ROI) and extracted the radiomic features and deep features from the ROIs

Read more

Summary

Introduction

To predict placental invasion (PI) and determine the subtype according to the degree of implantation, and to help physicians develop appropriate therapeutic measures, a prenatal prediction and typing of placental invasion method using MRI deep and radiomic features were proposed. According to the degree of implantation, it can be divided into three types: placenta accrete (PA), placenta increta (PC), and placenta percreta (PP) [2]. It is called PA if the placental villi are directly attached to the myometrium and require manual placental dissection during delivery, and when the placental villi penetrate deep into the uterine myometrium, it is called PC. In the most severe case, if the placental villi can reach the serous layer, or even penetrate the serosa layer, to the bladder or rectum, it is called PP It may cause different degrees of damage to pregnant women according to the severity of placenta implantation.

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call