Challenges in Atherosclerotic Plaque Characterization With Intravascular Ultrasound (IVUS): From Data Collection to Classification

Abstract

In vivo plaque characterization is an important research field in interventional cardiology. We will study the realistic challenges to this goal by deploying 40 MHz single-element, mechanically rotating transducers. The intrinsic variability among the transducers' spectral parameters as well as tissue signals will be demonstrated. Subsequently, we will show that global data normalization is not suited for data calibration, due to the aforementioned variations as well as the stringent characteristics of spectral features. We will describe the sensitivity of an existing feature extraction algorithm based on eight spectral signatures (integrated backscatter coefficient, slope, midband-fit (MBF), intercept, and maximum and minimum powers and their relative frequencies) to a number of factors, such as the window size and order of the autoregressive (AR) model. It will be further demonstrated that the variations in the transducer's spectral parameters (i.e., center frequency and bandwidth) cause inconsistencies among extracted features. In this paper, two fundamental questions are addressed: 1) what is the best reliable way to extract the most informative features? and 2) which classification algorithm is the most appropriate for this problem? We will present a full-spectrum analysis as an alternative to the eight-feature approach. For the first time, different classification algorithms, such as k-nearest neighbors (k-NN) and linear Fisher, will be employed and their performances quantified. Finally, we will explore the reliability of the training dataset and the complexity of the recognition algorithm and illustrate that these two aspects can highly impact the accuracy of the end result, which has not been considered until now.

Multiple k-Nearest Neighbor Classifier and Its Application to Tissue Characterization of Coronary Plaque

“…The spectral analysis of the RF signal is a representative approach [10], [11], [14]. In this analysis, the Fourier spectra of the RF signal are used as a feature vector for the classification of the tissues of coronary plaque.…”

“…In this analysis, the Fourier spectra of the RF signal are used as a feature vector for the classification of the tissues of coronary plaque. In [11], the feature vectors are classified by using a k-nearest neighbor (kNN) classifier [15], [16]. This method, however, cannot perform a precise characterization of plaque because the distribution of the feature vectors of each tissue heavily overlaps each other in the feature space.…”

Intravascular near-infrared fluorescence catheter with ultrasound guidance and blood attenuation correction

“…7 While these approaches have demonstrated potential for systematically characterizing the structural components of atherosclerotic plaque, they often fail to provide insight into physiological and biochemical processes that may be precursors to plaque rupture. [8][9][10][11][12] To address this deficiency, fluorescence, photoacoustic, and spectroscopic catheters have been developed to optically detect the molecular signatures of vulnerable plaque. [13][14][15][16] Plaque characterization, via these optical techniques, relies on the detection of endogenous molecules within the plaque or exogenous probes that are either targeted to extracellular ligands or are activated by physiological processes within the vessel wall.…”

Automated Characterization of Atheromatous Plaque in Intravascular Ultrasound Images Using Neuro Fuzzy Classifier

“…Semi-automatic methods require human intervention before it is given to the computer for processing. Amin Katouzian et al [2] described the realistic challenges in atherosclerotic plaque characterization. They explored the best reliable way to extract the most informative features and the classification algorithm which is most appropriate for this problem.…”