Automated telehealth system for fetal growth detection and approximation of ultrasound images

One of the most profound use of ultrasound imaging is fetal growth monitoring. Conventionally, physicians will perform manual measurements of several parameters of the ultrasound images to draw some conclusion of the fetal condition by manually annotating the fetal images on the ultrasound device interface. However, performing manual annotation of fetal images will require significant amount of time considering the number of patients an obstetrician can have. In this paper, an integrated automatic system for fetal growth monitoring and detection is proposed. This system will be able to automatically measuring the parameters of fetal head, abdomen, femur, and humerus. In addition to automated image detection, we also propose an integrated telehealth monitoring system to provide better access of ultrasound monitoring for patients that lives in rural areas. A new approach of fetal image detection is also proposed by using AdaBoost. MH boosting algorithm that is combined with an improved efficient Hough Transform for detecting ellipse-like organs such as head and abdomen. Experiments of the method are tested on real ultrasound image dataset. The detection was applied on 2D ultrasound images to perform fetal object measurement to approximate the Head Circumference (HC) and Biparietal Diameter (BPD), Femur Length (FL), and Humerus Length (HL).