Low-rank Modeling and its Applications in Medical Image Analysis.pdf

Low-rank Modeling and its Applications in Medical Image Analysis Xiaowei Zhou and Weichuan Yu? The Hong Kong University of Science and Technology, Hong Kong SAR, China ABSTRACT Computer-aided medical image analysis has been widely used in clinics to facilitate objective disease diagnosis. This facilitation, however, is often qualitative instead of quantitative due to the analysis challenges associated with medical images such as low signal-to-noise ratio, signal dropout, and large variations. Consequently, physi- cians have to rely on their personal experiences to make diagnostic decisions, which in turn is expertise-dependent and prone to individual bias. Recently, low-rank modeling based approaches have achieved great success in natural image analysis. There is a trend that low-rank modeling will find its applications in medical image analysis. In this review paper, we like to review the recent progresses along this direction. Concretely, we will first explain the mathematical background of low-rank modeling, categorize existing low-rank modeling approaches and their applications in natural image analysis. After that, we will illustrate some application examples of using low-rank modeling in medical image analysis. Finally, we will discuss some possibilities of developing more robust analysis methods to better analyze cardiac images. Keywords: Review, low-rank, computer vision, medical image analysis 1. INTRODUCTION In many areas of image analysis, the latent structure underlying image data is assumed to be a low-dimensional subspace. Multiple vectorized images will form a low-rank matrix. Specific examples include background images under different illuminations, dynamic textures with periodicity, a group of similar shapes, and 3-D trajectories of feature points on a rigid object. Therefore, relevant tools such as principal component analysis have been widely used in various problems to explore the low-rank structure of data. In early literatures, the low-rank pro