Prediction of Failure of Induction of Labor from Ultrasound Images Using Radiomic Features
Induction of labor (IOL) is a very common procedure in current obstetrics; about 20% of women who undergo IOL at term pregnancy end up needing a cesarean section (C-section). The standard method to assess the risk of C-section, known as Bishop Score, is subjective and inconsistent. Thus, in this paper a novel method to predict the failure of IOL is presented, based on the analysis of B-mode transvaginal ultrasound (US) images. Advanced radiomic analyses from these images are combined with sonographic measurements (e.g. cervical length, cervical angle) and clinical data from a total of 182 patients to generate the predictive model. Different machine learning methods are compared, achieving a maximum AUC of 0.75, with 69% sensitivity and 71% specificity when using a Random Forest classifier. These preliminary results suggest that features obtained from US images can be used to estimate the risk of IOL failure, providing the practitioners with an objective method to choose the most personalized treatment for each patient.
KeywordsRadiomics Ultrasound Induction of labor Machine learning
- 2.Baños, N., Perez-Moreno, A., Julià, C., Murillo-Bravo, C., Coronado, D., Gratacós, E., Deprest, J., Palacio, M.: Quantitative analysis of cervical texture by ultrasound in mid-pregnancy and association with spontaneous preterm birth: cervical texture associated with spontaneous preterm birth. Ultrasound Obstet. Gynecol. 51(5), 637–643 (2018)CrossRefGoogle Scholar
- 10.Obando, V.P., Arana, A.N., Izaguirre, A., Burgos, J.: Labor induction failure prediction based on B-mode ultrasound image processing using multiscale local binary patterns. In: International Conference on Optoelectronics and Image Processing, pp. 25–29 (2016)Google Scholar
- 11.Obando, V.P., Arana, A.N., Izaguirre, A., Burgos, J.: Labor induction failure prediction using Gabor filterbanks and center symmetric local binary patterns. In: IEEE 37th Central America and Panama Convention, pp. 1–5 (2017)Google Scholar