Automatic fetal organs detection and approximation in ultrasound image

This paper proposed a system for detecting and approximating of a fetus in an ultrasound image. The fetal organs in the ultrasound image are detected using Multi Boundary Classifier based Adaboost. MH. The results of the fetal detection is then approximated Randomized Hough Transform and the whole showed a mean accuracy of 95.80%. The mean of the Hamming Error 0.019 and the Kappa coefficient value reaches 0.890.The proposed method has the best performancefor fetal organ detection. This is proven by the Hamming Error, the accuracy, and tthe Kappa Coefficient. The hitrate for fetal's head, fetal's femur, fetal's humerus, and fetal's abdomen are 95%, 97%, 97%, and 93% respectively. From the Experiment result, it is concluded that using detection by only usig the approximation method could not perform better than the previous methods.