Cardiac computed tomography radiomics: an emerging tool for the non-invasive assessment of coronary atherosclerosis

Abstract

In the last decades, significant advances have been made in the preventive approaches to cardiovascular disease. Even so, coronary artery disease remains one of the main causes of morbidity and mortality worldwide. Invasive imaging modalities, such as intravascular ultrasound or optical coherence tomography, have played a key role in the comprehension of the pathological processes underlying myocardial infarction and cerebrovascular disease. These imaging techniques have contributed greatly to the identification and phenotyping of the culprit lesion, the so-called vulnerable plaque. Coronary computed tomographic angiography (CCTA) has emerged in more recent years as the non-invasive modality of choice in the study of coronary atherosclerosis, showing in many studies a diagnostic yield comparable to invasive approaches. Moreover, being able to describe extra-luminal characteristics of the affected vessel, CCTA has greatly contributed towards shifting the attention of researchers from the mere quantification of luminal stenosis to the identification of adverse plaque features, which appear to have a stronger prognostic value.However, the identification of some of the hallmarks of vulnerable plaques is qualitative in nature and, therefore, subject to some degree of inter-reader variability. Moreover, CCTA is still unable to identify some fine markers of plaque vulnerability which can be detected by invasive techniques, such as neovascularization and plaque erosion, among others. Nonetheless, radiological images can be viewed as vast 3-D datasets which, via the use of recent technology, allow for the extraction of numerous quantitative features that may be used to accurately phenotype a given lesion. Radiomics is the process of extrapolating innumerable parameters from a given region of interest, with the goal of establishing correlations between quantitative variables and clinical data. These datasets can then be manipulated to create predictive models via the use of automated algorithms in a process called machine learning. As a result of these approaches, radiological images may offer information regarding the characterization of a plaque which can go much beyond the boundaries of what can be qualitatively asserted by the human eye, contributing to expanding the knowledge of the disease and ultimately assist clinical decisions. Thus far, radiomics has found its more consistent area of application in the field of oncology; to present date, the amount of clinical data regarding coronary artery disease is still relatively small, partly due to the technical difficulties associated with the implementation of such techniques to the study of a small and geometrically complex lesion such as the coronary plaque. The present review, after a summary of the imaging modalities most commonly used nowadays in the study of coronary plaques, will provide a perspective on the application of radiomic analysis to coronary artery disease.

Recent Trends in Artificial Intelligence-Assisted Coronary Atherosclerotic Plaque Characterization

“…With CCTA, the identification of vulnerable plaques and their quantification relies on expert interpretation and is dependent on the degree of the interobserver variability. In addition, CCTA cannot supplant invasive techniques for more subtle plaque characteristics such as erosion and neovascularization [ 31 ]. While 3D reconstruction of plaque using CT slices would alert the physician to the presence of coronary artery disease at an early stage, it is advantageous that the investigator concentrates on hybrid feature extraction techniques when characterizing plaques using CAD based on CCTA images.…”

“…Multi-slice CCTA has evolved in the past two decades to become the dominant non-invasive imaging technique for coronary artery disease diagnosis [ 28 , 29 ], which provides information on coronary anatomy, calcification, location of stenosis and occlusion, as well as plaque morphology [ 8 , 9 , 10 , 30 , 31 ]. While CCTA image acquisition relies on ionizing radiation, the dose requirement has gradually been reduced by 30–50% through use of prospective electrocardiography-gated dose-dependent acquisition protocols on contemporary scanners [ 32 ].…”

“…The results are displayed in color codes, which enhances visualization of pathology. Instead of sound waves, IVOCT exploits light waves to produce near-field plaque images with superior spatial resolution (approximately 15 um versus 150 um for Multi-slice CCTA has evolved in the past two decades to become the dominant noninvasive imaging technique for coronary artery disease diagnosis [28,29], which provides information on coronary anatomy, calcification, location of stenosis and occlusion, as well as plaque morphology [8][9][10]30,31]. While CCTA image acquisition relies on ionizing radiation, the dose requirement has gradually been reduced by 30-50% through use of prospective electrocardiography-gated dose-dependent acquisition protocols on contemporary scanners [32].…”

Developing a model for estimating infarction onset time based on computed tomography radiomics in patients with acute middle cerebral artery occlusion

“…By extrapolating quantitative information from conventional images, it can identify imaging biomarkers that have important contributions to the characteristics of diseases. This method has the potential to overcome the limitations of qualitative image interpretation, which is helpful for the diagnosis, prognosis and treatment decisions [ 20 ]. Radiomics analysis has provided an alternative way for the identification [ 21 , 22 ] and evaluation of cerebral infarction in recent years [ 11 , 13 , 23 ].…”

Site-specific Phenotype of Atherosclerotic Lesions According to Their Location Within the Coronary Tree – a CCTA-based Study of Vulnerable Plaques

“…A high-risk plaque is characterized by a thin-cap fibroatheroma, a large necrotic core (the CCTA correspondent of low-attenuation regions within the plaque), heterogeneous calcifications (identified on CCTA as spotty calcium), and outward vascular remodeling. [13][14][15] On the other hand, the landmark of plaque stabilization is a thick-cap fibroatheroma, dense calcium deposits, and inward vascular remodeling. 16,17 There are four known CCTA vulnerability markers that have been validated with invasive imaging studies as well as autopsy studies, which include: low-attenuation plaque (LAP), positive remodeling (PR), spotty calcifications (SC), and the napkin-ring sign (NRS).…”