Title :
Multiscale texture analysis of cervical tissue for labor induction
Author :
Vasquez Obando, Pablo ; Nestor Arana, A. ; Izaguirre, Alberto ; Arana, Itziar ; Burgos, Jorge
Author_Institution :
Signal Theor. & Commun. Dept., Mondragon Univ., Mondragon, Spain
Abstract :
Labor induction is defined as the artificial onset of labor for the purpose of vaginal birth. Cesarean section is one of the potential risk of labor induction as it occur in about 20% of the inductions. A ripe cervix (soft and distensible) is needed for a successful labor. During the ripening cervical tissues experience micro structural changes: collagen becomes disorganized and water content increases. These changes 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. Texture analysis can be used to analyze these variations and provide a means to evaluate cervical ripening in a non-invasive way. In this paper we try two different multiscale transforms for cervical texture classification.
Keywords :
biological tissues; image classification; image texture; medical image processing; artificial onset; cervical texture classification; cervical tissue; cesarean section; echographic image; gray level intensity variations; labor induction; micro structural; multiscale texture analysis; ripe cervix; ripening cervical tissues; vaginal birth; water content; Feature extraction; Image segmentation; Pregnancy; Support vector machines; Ultrasonic imaging; Wavelet transforms;
Conference_Titel :
Electronics, Control, Measurement, Signals and their Application to Mechatronics (ECMSM), 2015 IEEE International Workshop of
Conference_Location :
Liberec
Print_ISBN :
978-1-4799-6970-8
DOI :
10.1109/ECMSM.2015.7208707
