Automatic recognition of fetal standard plane in ultrasound image

Abstract

Detection and recognition of standard plane automatically during the course of US examination is an effective method for diagnosis of fetal development. In this paper, an automatic algorithm is developed to address the issue of recognition of standard planes (i.e. axial, coronal and sagittal planes) in the fetal ultrasound (US) image. The dense sampling feature transform descriptor (DSIFT) with aggregating vector method (i.e. fish vector (FV)) is explored for feature extraction. The learning and recognition of the planes have been implemented by support vector machine (SVM) classifier. Experimental results on the collected data demonstrate that high recognition accuracy is obtained.