Classification of trabecular structure in magnetic resonance images based on morphological granulometries

Abstract

A new method of detecting structured changes in trabecular bone, such as those associated with osteoporosis, was evaluated on magnetic resonance images of the wrist. The method was based on gray-scale morphological granulometries which classify image texture by iteratively filtering an image and measuring the rate of change of structural diminution in a filtered-image sequence. A classification scheme capable of distinguishing structural changes in trabecular bone starting from normal trabeculae through sclerotic, cystic, and grossly porotic bone is presented. Results of the application of this technique to the evaluation of high resolution magnetic resonance images of the wrist are presented.

Support Vector Machines for Diagnosis of Breast Tumors on US Images

“…Many texture features have been proposed for texture analysis, and they can be classified in three main groups: models (16,17), mathematical morphology (18), and statistical methods (19). In this section, we briefly introduce autocorrelation and autocovariance coefficients.…”

A Constant-time Algorithm for Erosions/Dilations with Applications to Morphological Texture Feature Computation

“…Morphological granulometry is a multi-resolution tool for image analysis that is based on the popular geometric approach to image analysis called mathematical morphology [8,9]. Morphological granulometries were originally developed by Matheron for binary images, which was later extended to grayscale images as a tool for texture analysis by Chen et al [7,10].…”

“…In this case, pk ÈkÀÈk À 1 is a probability density function and is referred to as the pattern spectrum [17]. The moments of the pattern spectrum have been used as morphological texture features [6,7,10]. Normally, texture is regarded as a local property and any volume decrease is computed within a local window W placed around each pixel.…”

“…There is no universally agreed upon de®nition for image texture and dierent attributes have been used to quantify it, depending upon the application [1]. Most popular texture features are based on co-occurrence matrices [2±4], wavelet coecients [5], and morphological granulometries [6,7]. Morphological granulometry is a multi-resolution tool for image analysis that is based on the popular geometric approach to image analysis called mathematical morphology [8,9].…”

Linear granulometric moments of noisy binary images

“…Lower-order moments of the granulometric size distribution are used as pattern or texture descriptors. Granulometric image characterization has been applied to shape discrimination [3], [4] and to texture classification [5]- [8], including gray-scale textures [9]- [11].…”