Directionlet transform based sharpening and enhancement of mammographic X-ray images

Anisotropic Discrete Dual-Tree Wavelet Transform for Improved Classification of Trabecular Bone

This paper deals with a new anisotropic discrete dual-tree wavelet transform (ADDTWT) to characterize the anisotropy of bone texture. More specifically, we propose to extend the conventional discrete dual-tree wavelet transform (DDTWT) by using the anisotropic basis functions associated with the hyperbolic wavelet transform instead of isotropic spectrum supports. A texture classification framework is adopted to assess the performance of the proposed transform. The generalized Gaussian distribution is used to model the distribution of the sub-band coefficients. The estimated vector of parameters for each image is then used as input for the support vector machine classifier. Experiments were conducted on synthesized anisotropic fractional Brownian motion fields and on a real database composed of osteoporotic patients and control cases. Results show that the ADDTWT outperforms most of the competing anisotropic transforms with an area under curve rate of 93%.

Medical Image Enhancement Using Edge Information-Based Methods

Medical image enhancement improves the quality and facilitates diagnosis. This chapter investigates three methods of medical image enhancement by exploiting useful edge information. Since edges have higher perceptual importance, the edge information based enhancement process is always of interest. But determination of edge information is not an easy job. The edge information is obtained from various approaches such as differential hyperbolic function, Haar filters and morphological functions. The effectively determined edge information is used for enhancement process. The retinal image enhancement method given in this chapter improves the visual quality of the vessels in the optic region. X-ray image enhancement method presented here is to increase the visibility of the bones. These algorithms are used to enhance the computer tomography, chest x-ray, retinal, and mammogram images. These images are obtained from standard datasets and experimented. The performance of these enhancement methods are quantitatively evaluated.

Non-linear polynomial filters for edge enhancement of mammogram lesions

BACKGROUND AND OBJECTIVES

Computer aided analysis of mammograms has been employed by radiologists as a vital tool to increase the precision in the diagnosis of breast cancer. The efficiency of such an analysis is dependent on the employed mammogram enhancement approach; as its major role is to yield a visually improved image for radiologists.

METHODS

Non-linear Polynomial Filtering (NPF) framework has been explored previously as a robust approach for contrast improvement of mammographic images. This paper presents the extension of NPF framework for sharpening and edge enhancement of mammogram lesions. Proposed NPF serves to provide enhancement of edges and sharpness of the lesion region (region-of-interest) in mammograms, in a manner to minimize the dependencies on pre-selected thresholds. In the present work, Logarithmic Image Processing (LIP) model has been employed for the purpose of improvement in visualization of mammograms based on Human Visual System (HVS) characteristics.

RESULTS

The proposed NPF filtering framework yields mammograms with significant improvement in contrast, edges as well as sharpness of the lesion region. The performance of the proposed approach has been validated using state-of-art objective evaluation measures (of mammogram enhancement) like Contrast Improvement Index (CII), Peak Signal-to-Noise Ratio (PSNR), Average Signal-to-Noise Ratio (ASNR) and Combined Enhancement Measure (CEM); as well as subjective evaluation by radiologists' opinions.

CONCLUSIONS

The proposed NPF provides a robust solution to perform noise controlled contrast as well as edge enhancement using a single filtering model. This leads to a better visualization of the fine lesion details predictive of their severity. The applicability of single filtering methodology for carrying out denoising, contrast and edge enhancement improves the worth of the overall framework.

A fusion method of Gabor wavelet transform and unsupervised clustering algorithms for tissue edge detection

This paper proposes two edge detection methods for medical images by integrating the advantages of Gabor wavelet transform (GWT) and unsupervised clustering algorithms. The GWT is used to enhance the edge information in an image while suppressing noise. Following this, the k-means and Fuzzy c-means (FCM) clustering algorithms are used to convert a gray level image into a binary image. The proposed methods are tested using medical images obtained through Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) devices, and a phantom image. The results prove that the proposed methods are successful for edge detection, even in noisy cases.

Directionlets using in-phase lifting for image representation

Directionlets allow a construction of perfect reconstruction and critically sampled multidirectional anisotropic basis, yet retaining the separable filtering of standard wavelet transform. However, due to the spatially varying filtering and downsampling direction, it is forced to apply spatial segmentation and process each segment independently. Because of this independent processing of the image segments, directionlets suffer from the following two major limitations when applied to, say, image coding. First, failure to exploit the correlation across block boundaries degrades the coding performance and also induces blocking artifacts, thus making it mandatory to use deblocking filter at low bit rates. Second, spatial scalability, i.e., minimum segment size or the number of levels of the transform, is limited due to independent processing of segments. We show that, with simple modifications in the block boundaries, we can overcome these limitations by, what we call, in-phase lifting implementation of directionlets. In the context of directionlets using in-phase lifting, we identify different possible groups of downsampling matrices that would allow the construction of a multilevel transform without forcing independent processing of segments both with and without any modifications in the segment boundary. Experimental results in image coding show objective and subjective improvements when compared with the directionlets applied independently on each image segment. As an application, using both the in-phase lifting implementation of directionlets and the adaptive directional lifting, we have constructed an adaptive directional wavelet transform, which has shown improved image coding performance over these adaptive directional wavelet transforms.