RESUMEN
Objective To explore the role of an artificial intelligence(AI)model based on real-time object detection network in fetal facial ultrasound examination.Methods With the normal fetal facial ultrasound standard plane(FFUSP)at 20-24 weeks of gestation as the research object,a FFUSP recognition model based on real-time object detection network was constructed.The recognition accuracy of the model for FFUSP and the anatomical structures were analyzed,and the clinical value was evaluated by analyzing its performance in identifying FFUSP in 119 cases of fetal ultrasound images.Results The overall precision,recall rate,mAP@.5 and mAP@.5:.95 of the AI model were 97.8%,98.5%,98.1%and 61.0%,respectively.The clinical validation showed that the AI model had a sensitivity,specificity,positive predictive value,negative predictive value and accuracy of 100.0%,98.5%,87.4%,100.0%and 98.7%for facial anatomy recognition,and the results were highly consistent with the classification of fetal ultrasound experts(k=0.925,P<0.001).The recognition accuracy of the model for 3 types of standard planes reached 100%;and the average speed of dynamic video detection was 33.93 frames per second.Conclusion The FFUSP recognition model based on real-time object detection network exhibits excellent performance,and it can be applied to real-time ultrasound diagnosis,teaching and intelligent quality evaluation.
RESUMEN
Objective To study the hemodynamic characteristics of ductus venosus,and its relationship to inflammatory cytokines in ovine fetus with systemic inflammatory response syndrome.Methods Ten near-term fetal sheep radomly divided into two groups.Five of them were in experimental group,and five of them were in control group.All of the animals underwent abdominal cordocentesis guided by ultrasound at the term of 120-130 days,with a LPS injection at a dosage of 10 μg/kg of fetal weight in experimental group,and the same quantity of 0.9% NaCl solution in control.Doppler echocardiography were performed to determine hemodynamics changes of ductus venosus at 0.5 hour before the LPS injection,and at 1 hour,3 hours,6 hours after LPS injection.Meanwhile,fetal umbilical vein blood was sampled for ELISA essay of serum TNF-α and IL-6 at each of the above time points.Results In experimental group,the ductus venosus waveform PI values(DVPI),maximum velocity during cardiac ventricle systole(S)and during cardiac ventricle diastole(D),ductus venosus index(DVI),ductus venosus blood flow(DVQ),the ratio of S and ductus venous maximum velocity during atrial contracton(S/A),(S-A)/D increased with the time after LPS injection,and still significantly increased as compared with the control animals(all P＜0.05).A decreased with the time after LPS injection,and still significantly changed as compared with the controls(P＜0.05).And the ductus venosus diameter(DVD)had not obvious change(P＞0.05).There were significantly positive correlations between DVPI and TNF-α,IL-6(all P＜0.05),negative corelations between A and TNF-α,IL-6(all P＜0.05),and positive correlations between S wave,DVI,DVQ,D wave,S/A,(S-A)/D and IL-6(all P＜0.05),but not obvious relationships between S wave,DVI,DVQ,D wave,S/A,(S-A)/D and TNF-a(all P＞0.05).Condusions DVPI and A might be easy and useful quantitative parameters in the evaluation of fetal systemic inflammatory respome syndrome with LPS injection.