%0 Journal Article
%T Trabecular Bone Image Segmentation Using Wavelet and Marker-Controlled Watershed Transformation
%A Wafa Abid Fourati
%A Mohamed Salim Bouhlel
%J Chinese Journal of Engineering
%D 2014
%R 10.1155/2014/891950
%X This paper presents a new strategy for the segmentation of trabecular bone image. This kind of image is acquired with microcomputed tomography (micro-CT) to assess bone microarchitecture based chiefly on bone mineral density (BMD) measurements to improve fracture risk prediction. Disease osteoporosis can be predicted from features of CT image where a bone region may consist of several disjoint pieces. It relies on a multiresolution representation of the image by the wavelet transform to compute the multiscale morphological gradient. The coefficients of detail found at the different scales are used to determine the markers and homogeneous regions that are extracted with the watershed algorithm. The method reduces the tendency of the watershed algorithm to oversegment and results in closed homogeneous regions. The performance of the proposed segmentation scheme is presented via experimental results obtained with a broad series of images. 1. Introduction Osteoporosis is a metabolic bone disease [1]. The disease is defined by low bone mass and microarchitectural deterioration of bone tissues leading to enhanced bone fragility. Clinically, osteoporosis is associated with an increased risk of fractures of the vertebral bone. The exact clinical estimation of bone strength and fracture risk is important for the treatment of bone diseases such as osteoporosis. It designates a major health problem in industrialized countries. This is a silent disease without any symptoms. After the age of 50, the number of osteoporotic people clearly raises [2]. A hip fracture is costly for a system of health care. Vertebral fractures are associated with a higher risk of mortality and also having another fracture in the first months following a fracture. Segmentation of bone structures from computed tomography (CT) images (shown in Figure 1) is to extract osseous tissue on the surface of bones (cortical bone, the trabecular network) from the interior region of bones (cancellous bone, space medullar). Figure 1: Trabecular bone image. The trabecular network detection is a very important task to help diagnose diseases such as trabecular bone loss in osteoporotic patients or in animal models of osteoporosis [1¨C3]. The low contrast images of the trabecular bone acquired with the sky-scan X-ray microcomputed tomography make their analysis a challenging task. Additionally, throughout acquisition, it is required to establish a high number of parameters that result in the presence of noise, nonhomogeneous illumination, and fuzzy contours. Such segmentations can be very challenging to
%U http://www.hindawi.com/journals/cje/2014/891950/