Robust x-ray image segmentation by spectral clustering and active shape model

Abstract

, "Robust x-ray image segmentation by spectral clustering and active shape model," Abstract. Extraction of bone contours from x-ray radiographs plays an important role in joint space width assessment, preoperative planning, and kinematics analysis. We present a robust segmentation method to accurately extract the distal femur and proximal tibia in knee radiographs of varying image quality. A spectral clustering method based on the eigensolution of an affinity matrix is utilized for x-ray image denoising. An active shape model-based segmentation method is employed for robust and accurate segmentation of the denoised x-ray images. The performance of the proposed method is evaluated with x-ray images from the public-use dataset(s), the osteoarthritis initiative, achieving a root mean square error of 0.48 AE 0.13 mm for femur and 0.53 AE 0.18 mm for tibia. The results demonstrate that this method outperforms previous segmentation methods in capturing anatomical shape variations, accounting for image quality differences and guiding accurate seg-mentation.