Ultrasound Estimation of Fetal Weight by Single Multiplicative Neuron Model in Normal Pregnancies
Obstetric management is often influenced by ultrasound estimations of fetal weight. Accurate prediction of birth weight is clinically important, especially when complicate with planning the mode of delivery or differential diagnoses and the detection of growth abnormalities. The aim of the present study was to evaluate the accuracy of using single multiplicative neuron (MNM) model for estimation of fetal weight after 12 weeks gestation. Five-hundred and fifty-six patients with a healthy, singleton pregnancy, whom fetal biometry measurements were routinely performed by ultrasound (US), considered as the training group. Seven input variables were used to construct single multiplic-ative neuron model: abdominal circumference (AC), biparietal diameter (BPD), gestational age (GA), Head circumference (HC), femur length (FL), crown coccyx length (CCL) and clavicle length (CL). Also a total of 209 fetuses were assessed subsequently as the validation group. In the validation group the mean absolute error and the mean absolute percent error was 160.26 g and 5.77％ respectively. In conclusion, using single multiplic-ative neuron model could provide acceptable US estima-tion of fetal weight.
component ultrasound fetal weight estimation single multiplicative neuron model
Hanieh Mohammadi Zohreh Allahmoradi Mercedeh Jahanseir Maryam Parhizgar Farzaneh Samiee
Dept. Biomedical Engineering University of Science And Research Azad Islamic 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
580-584
2010-11-16（万方平台首次上网日期，不代表论文的发表时间）