Fractal Dimension Based Carotid Plaque Characterization from Three-Dimensional Ultrasound Images

Abstract

Abstract:Carotid atherosclerotic lesions are a major cause of cerebrovascular disease (CVD). Identification and quantification of carotid plaques are important for categorizing the vulnerability of plaques for rupture and assessing the impact of treatments. The irregularity of plaque surface is associated with previous plaque rupture and plays an important role in the risk of stroke. Thus, the aim of this study is to develop and validate novel vulnerability biomarkers from three-dimensional ultrasound (3DUS) images by analyzing the surface morphological characterization of carotid plaque using fractal geometry features. 3D box-counting and 3D blanket are the two types of 3D fractal dimension that were employed to describe the smoothness of plaques. This fractal dimension analysis tool was used to evaluate the effect of atorvastatin using 3DUS carotid images, which were acquired from 6 patients treated with atorvastatin with 80 mg daily and 5 patients with placebo. The Student's T Test results showed that those two fractal features were effective for detecting the statin-related changes in carotid atherosclerosis with p<0.0068 and p<0.015 respectively, suggesting that 3D fractal dimension measurements can be used effectively to analyze the surface characteristics of carotid plaques, especially for evaluating the impact of the treatment.

On Multifractal Tissue Characterization in Ultrasound Imaging

“…Based on biological studies showing that certain tissues such as tumors have a multifractal behavior in space and time (e.g., [3]), several existing works proposed to extract the fractal or multifractal signature of the tissues from US images and to use it for segmentation, characterization or classification purpose (e.g., [4][5][6][7]). However, to the best of our knowledge, no theoretical or practical analysis of the good agreement be-tween the multifractal behavior of the tissues and the multifractal signature estimated from US images exists.…”

Semi Supervised Grading Model Using Syntactic Level Feature Selection Technique

“…[13]. Ran et al [31] developed and validated novel vulnerability biomarkers using fractal geometry features from three-dimensional ultrasound (3D) images. The contributions of the proposed work are briefly explained in the following sections.…”