A PC-based Vision System For Bone Measurement

In recent years, computer vision techniques have been widely used in medical systems. This paper presents a new computer vision algorithm which is designed for measurement of skeletal growth. In practice, the overall system was fully developed on an IBM-PC. It has the advantages of eliminating the subjective variations resulted from the instability of human visual judgement and detecting children's abnormal skeletal growth in a short period of time. Two standard radiographs, taken from the same child at two time instants, were used in these analyses. This system consists of three stages: preprocessing, segmentation , and measurement. In the first stage, histogram equalization and autothresholding techniques were utilized to normalize the input radiograph and stretch the contrast. The segmentation determines the contour of each bone of interest. The measurement stage provides the necessary information for clinical diagnosis.