Texture Image Analysis for Osteoporosis Detection with Morphological Tools

Abstract

Abstract. Osteoporosis is due to the following two phenomena: a reduction bone mass and a degradation of the microarchitecture of bone tissue. In this paper, we propose a method for extracting morphological information enabling the description of bone structure from radiological images of the calcaneus. Our main contribution relies on the fact that we provide bone descriptors close to classical 3D-morphological bone parameters. The first step of the proposed method consists in extracting the grey-scale skeleton of the microstructures contained in the underlying images. After an appropriate processing, the resulting skeleton provides discriminant features between osteoporotic patients and control patients. Statistical tests corroborate this discrimination property.

Graph Structuring of Skeleton Object for Its High-Level Exploitation

“…Concerning the characterization of bone microarchitecture, studies has shown that bone changes from a healthy person to a person with osteoporosis [4] or osteoarthritis [3]. These changes are quantified using morphometric parameters of bone microarchitecture such as the number of pixels of the skeleton, the halfwidth and the length of trabeculae, the number of trabeculae and the number of nodes and ends.…”

“…Skeletonization is used in various applications such as biometrics [1,2], medical imaging [3,4,5] and character recognition [6] since it provides features that enables user to access high-level analysis of the image objects. In fact, object matching methods based on skeleton features are used in biometric identification through minutiae comparison of hand vein [1] or digital fingerprint [2], in bronchial airway trees monitoring [5], in symbols identification [7] and in character recognition [6].…”

“…In fact, object matching methods based on skeleton features are used in biometric identification through minutiae comparison of hand vein [1] or digital fingerprint [2], in bronchial airway trees monitoring [5], in symbols identification [7] and in character recognition [6]. In addition, classification methods using morphometric features extracted from skeleton helps diagnose osteoporosis [4] and osteoarthritis [3] diseases. Graph-based representation of the skeleton is widely investigated for matching issues since the correspondence between skeleton branches with graph edges and nodes with its vertices is natural and intuitive.…”

Distributed Intelligent Medical Assistant for Osteoporosis Detection

“…The foreground is obtained by a thresholding step [1]: we compare the original image (in this case a calcaneum image, figure 1(a)) to its local ppercentile computed on a sliding window of size w. Then two thinning methods are proposed: a classical binary skeletonization and a grey thinning close to the Mersal algorithm [2]. The latter consists in two steps.…”

“…The most challenging task is to characterize bone micro architecture by parameters that can be automatically estimated from images and that can accurately detect and quantify alterations of bones. For this, we have developed an original approach using morphological tools to extract characteristic features of trabecular bone images [1]. To make such an approach operational for medical diagnosis, it is necessary to determine an "image protocol" adapted to bone types (e.g.…”