Comprehensive Assessment of High-Risk Plaques by Dual-Modal Imaging Catheter in Coronary Artery

Abstract

Coronary plaque destabilization involves alterations in microstructure and biochemical composition; however, no imaging approach allows such comprehensive characterization. Herein, the authors demonstrated a simultaneous microstructural and biochemical assessment of high-risk plaques in the coronary arteries in a beating heart using a fully integrated optical coherence tomography and fluorescence lifetime imaging (FLIm). It was found that plaque components such as lipids, macrophages, lipids+macrophages, and fibrotic tissues had unique fluorescence lifetime signatures that were distinguishable using multispectral FLIm. Because FLIm yielded massive biochemical readouts, the authors incorporated machine learning framework into FLIm, and ultimately, their approach enabled an automated, quantitative imaging of multiple key components relevant for plaque destabilization.

Keywords: FL, fluorescence lifetime; FLIm, fluorescence lifetime imaging; ICC, intraclass correlation coefficient; IR, intensity ratio; IVUS, intravascular ultrasound; MФ, macrophage; OCT, optical coherence tomography; RFC, random forest classifier; ROI, region of interest; SMC, smooth muscle cell; TCFA, thin-cap fibroatheroma; UV, ultraviolet; ch, channel; fluorescence lifetime imaging; high-risk plaque; inflammation; lipid; machine learning; optical coherence tomography.

Graphical abstract

Figure 1

In Vivo OCT-FLIm Images Obtained From an Atheroma and a Normal Artery (Upper panel) Three-dimensional longitudinal cutaway-view images color-coded with the ch.2 FL. (Lower panel: a, b, and c) OCT-FLIm cross sections at the corresponding locations. Boxedareas in a, b, and c are shown in higher magnification in the panels below. Arrowheads (a) denote typical signal-poor OCT regions of lipid-rich plaques, whereas fibrotic plaque (b) shows homogenous, signal-rich OCT regions. Scale bars indicate 1 mm. AU = arbitrary units; ch = channel; FL = fluorescence lifetime; FLIm = fluorescence lifetime imaging; OCT = optical coherence tomography.

Figure 2

Component-Specific FLIm Analyses (A) FLIm signatures according to the different plaque components. Each column consists of original and higher-magnified OCT-FLIm images and corresponding immunohistologies. Boxedareas in the top panels are shown in higher magnification in the panels immediately below. Scale bars indicate 1 mm, unless otherwise specified. Yellow arrowheads denote typical signal-poor, lipid-rich regions on OCT. Red arrowheads denote typical OCT bright spots, suggesting macrophage accumulation. (B) Comparisons of multispectral FLIm measurements according to the plaque components (∗P < 0.001 by the Kruskal-Wallis test). Boxplot center lines indicate the medians; box edges represent the interquartile ranges; and whiskers extend to the first or third quartile plus 1.5 times the interquartile range. The multiple comparison results all yielded P < 0.001, unless otherwise specified or indicated as nonsignificant (ns). MФ = macrophage; ORO = Oil Red O stain; other abbreviations as in Figure 1.

Figure 3

Machine Learning–Based Automated Biochemical Characterization (A) Dataset was assembled by obtaining biochemical FLIm readouts from the predetermined regions of interest (ROIs, arrowheads) labeled with the 5 different classes. In the training phase, each random forest classifier (RFC) decision tree was formulated using a randomly sampled training subset. (B) The trained classifier performance was evaluated using the confusion matrix and multiclass receiver operation characteristic curve analysis based on five-fold cross-validation. (C) Cross sections and volume-rendered images of the RFC-applied OCT-FLIm. This imaging approach enables intuitive visualization of the structural-biochemical characteristics of target plaques and quantitative composition analysis of the 5 different biochemical components. Abbreviations as in Figures 1 and 2.

Figure 4

Reliability and Reproducibility Validations (A) Scatter and Bland–Altman plots showing correlations of the multispectral FLIm measurements between the repeated imaging datasets. Bland-Altman graph: The differences between the repeated imaging datasets were plotted against their mean, and the 95% limits of agreement (dashed line) were calculated as the average difference ± 1.96 SD. (B) (Upper panel) Representative images of the paired frames showing similar classification results. (Lower panel) Stacked bar graphs showing the relative proportions of the RFC-determined plaque components. Each vertical bar along the horizontal axis represents a frame. Scale bars indicate 1 mm. ICC = intraclass correlation coefficient; IR = intensity ratio; other abbreviations as in Figures 1 to 3.

Figure 5

Macrophages Showing Various Morphological Features on OCT Yellow arrowheads indicate typical OCT bright spots without shadows; white arrowheads indicate only shadows in the absence of bright spots; and red arrowheads show typical OCT bright spots with shadowing. Boxedareas in the top panels are shown in higher magnification in the panels immediately below. The RFC-applied FLIm allowed highly sensitive and accurate detection of macrophage infiltrates. Scale bars indicate 1 mm. MФ = macrophage; other abbreviations as in Figures 1, 2, and 3.

Figure 6

Comparison Between the RFC-Determined Plaque Components and Those Quantitated From Immunohistochemistries (A) Flowchart describing the process of the immunohistochemistry (IHC) multiplexing. Inset (a higher-magnification image of the dashed-line boxed area), each green rectangle denotes the 200-μm–depth quadrangular ROI for morphometric quantitation. (B) Focal plaque showing extensive macrophage infiltration and thinning of the overlying SMC layer at the plaque shoulder (arrowheads, also refer to Supplemental Figure 10). (C) Comparison result of an atheroma section obtained from the animal whose imaging data were not used for RFC training. Boxed areas are displayed in high-magnification in neighboring images, accordingly. SMA = smooth muscle actin; SMC = smooth muscle cells; other abbreviations as in Figures 1, 2, and 3.