Segmentation of the Ilium and Femur Regions from Ultrasound Images for Diagnosis of Developmental Dysplasia of the Hip

Creative Commons License

Cevik K. K., Kocer H. E., Andaç S.

JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, vol.6, no.2, pp.449-457, 2016 (SCI-Expanded) identifier identifier


The objective of the study is to evaluate the efficiency of applying filters on ultrasound images in order to increase the success rate of segmentation in the diagnosis of Developmental Dysplasia of the Hip (DDH). This research consists of several steps, in which pure DDH images are formed. Seven different filters (Mean, Median, Gaussian, Wiener, Perona and Malik, Lee and Frost) are applied to the images and finally the output images are evaluated. Initially, a filter is applied to the raw images. To assess the resulting images peak signal to noise ratio (PSNR) and mean square error (MSE) values are used. In the next section of the study, those seven different filters are applied to the raw images and segmentation is carried out and then the results are evaluated. In the DDH diagnosis, the ilium and femoral regions are segmented by using Active Contour Models and Circular Hough Transform methods, respectively. The results of the study show that applying Wiener filter to the iliac region results in 100% success, while the filter also achieves 90% success rate in the femoral region. In conclusion, the examining PSNR and MSE values show that the degree of filter's success varies according to the type of noise contained in the image. When the segmentation process is analyzed, it is observed that the Wiener filters manage to increase the success rate due to their ability to remove speckle noise.