Labor Induction failure prediction using Gabor filterbanks and Center Symmetric Local Binary Patterns

Abstract

Labor induction is defined as the artificial stimulation of uterine contractions aimed to induce vaginal birth. Occurring in about 20% of pregnancies labor induction has become one the most commonly practiced procedures in obstetrics. One of the risk related to labor induction is cesarean section which accounts about 20% of the inductions. A requirement for a successful labor is a ripe cervix (soft and distensible). Microestructural changes occurring in the cervix during the ripening process, will affect the interaction between cervical tissues and sound waves during ultrasound transvaginal scanning and will be perceived as gray level intensity variations in the echographic image. A non-invasive method using image processing of ultrasound images may help in predicting the outcome of labor induction. In this paper a set of echography images from labor induction patients is analyzed using a multiscale methodology based on Center Symmetric Local Binary Patterns and Gabor filters. Results show that it is feasible to predict the outcome of a labor induction procedure using this method with a good accuracy.