Abstract
This study aimed to identify the existence of uterine micro-peristalsis (UMP) by dynamic ultrasound features and evaluate the feasibility of UMP as a tool to distinguish pregnant and non-pregnant infertility patients undergoing in vitro fertilization-embryo transfer (IVF-ET), using clinical pregnancy results as a benchmark. Fifty-one women, including 29 pregnant and 22 non-pregnant patients were recruited. Also, ultrasound videos were collected before embryo transfer. First of all, undiscoverable uterine micro-peristalsis was magnified by video magnification. Then, the dynamic features of UMP were characterized by a novel index termed histogram entropy based on the micro-peristalsis feature selection by entropy weight (HEMEW), which was generated by combining frame difference and volume local phase quantization. Finally, a comparative experiment of HEMEW between non-pregnant and pregnant patients, logistic regression analysis for HEMEW and other independent clinical characteristics, and receiver operating characteristic (ROC) analysis were performed. The magnified uterine video clearly exhibited UMP, which was invisible in the original ultrasound video. Further, there existed a significant difference in HEMEW between pregnant patients and non-pregnant patients after micro-motion magnification (p = 0.003, n = 51). The logistic regression result showed that HEMEW (p = 0.006) was significantly associated with clinical pregnancy outcome, while other independent variables had no significant effect on it. The ROC performance of HEMEW was 72.6% accuracy (AUC = 0.774, 95% CI: 0.644-0.905). The proposed micro-motion magnification and characterization strategy identified the existences of uterine micro-peristalsis, and verified that UMP has the feasibility to distinguish the outcomes of IVF-ET.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.