Estimation of Fetal Weight by Artificial Neural Network Using Symphysis-Fundus Height
Estimation of fetal weight (EFW) is an important component of pregnancy care management, for example in counseling, differential diagnoses and planning the mode of birth. The object of present study was to determine using SFH as a clinical parameter within computerized artificial neural network (ANN) model could improve ultrasound (US) estimation of fetal weight. At First, as the training group, we performed IIS examinations on 467 healthy singleton fetuses after 24 weeks within 3 days of delivery. Five input variables were used to construct the ANN model: Abdominal circumference (AC), Head Circumference (HC), femur length (FL), symphysis-fundus height (SFH) and gestational age (GA). The AC, HC, FL, GA parameters were measured by 2-D US and SFH parameter measure clinically. Then, a total of 205 fetuses were assessed subsequently as the validation group. In validation group, the mean absolute error and the mean absolute percent error between estimated fetal weight and actual fetal weight was 162.79 g and 5.81％, respectively. Results show that, the SFH in this artificial neural network (ANN) model can provide better US estimation of fetal weight.
component ultrasound fetal weight estimation artificial neural network symphysis-fundus height
Hanieh Mohammadi Zohreh Allahmoradi Mercedeh Jahanseir Maryam Parhizkar Farzaneh Samiee
Dept. Biomedical Engineering Science and research Branch, Islamic Azad University Tehran, Iran Dept. Biomedical Engineering Science and research Branch,Islamic Azad University Tehran, Iran
国际会议
2010 International Conference on Measurement and Control Engineering(2010年IEEE测量与控制工程国际会议 ICMCE2010)
成都
英文
598-602
2010-11-16（万方平台首次上网日期，不代表论文的发表时间）