Abstract__Over the past decade, active shape models have gained increased popularity in medical image analysis. However, despite its widespread, it is now widely accepted that classical shape models using principle component analysis (PCA) is not able to faithfully model the wide range of variations that anatomical structures can undergo. In this paper, we present a new statistical shape model using wavelet transform and independent component analysis (ICA). In an attempt to benefit from the sparsification and approximation power of wavelets, we investigate constructing an ICA-based shape model in a compressed wavelet domain. In order to asses the efficiency of the proposed shape model; experiments were conducted using contours of human vertebrae from x-ray images
Statistical models of deformations are becoming crucial tools for a variety of computer vision applications such as regularization and validation of image registration and segmentation algorithms. In this article, we propose a new approach to effectively represent the statistical properties of high dimensional deformations. In particular, we propose techniques that use independent component analysis (ICA) in conjunction with wavelet packet decomposition. Two different architectures for ICA have been investigated; one treats the elastic deformations as random variables and the individual deformation field as outcomes and a second which treats the individual deformations as random variables and the elastic deformations as outcomes. The experiments were conducted using the Amsterdam Library of Images (ALOI), and the proposed algorithms were evaluated using the model generalization as a statistical measure. Experimental results show a significant improvement when compared to a recent deformation representation in the literature.
Abstract-Medical experts often examine hundreds of xray images searching for salient features that are used to detect pathological abnormalities.Inspired by our understanding of the human visual system, automated salient features detection methods have drawn much attention in the medical imaging research community. However, despite the efforts, detecting robust and stable salient features in medical images continues to constitute a challenging task. This is mainly attributed to the complexity of the anatomical structures of interest which usually undergo a wide range of rigid and non-rigid variations.In this paper, we present a novel appearance-based salient feature extraction and matching method based on sparse Contourlet-based representation. The multi-scale and directional capabilities of the Contourlets is utilized to extract salient points that are robust to noise, rigid and non-rigid deformations. Moreover, we also include prior knowledge about local appearance of the salient points of the structure of interest. This allows for extraction of robust stable salient points that are most relevant to the anatomical structure of interest.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.