Optical Coherence Tomography and Coronary Plaque Characterization

Background: The morphological structure and tissue composition of a coronary atherosclerotic plaque determine its stability, which can be assessed by intravascular optical coherence tomography (OCT) imaging. However, plaque characterization relies on the interpretation of large datasets by well-trained observers. This study aims to develop a convolutional neural network (CNN) method to automatically extract tissue features from OCT images to characterize the main components of a coronary atherosclerotic plaque (fibrous, lipid, and calcification). The method is based on a novel CNN architecture called TwopathCNN, which is utilized in a cascaded structure. According to the evaluation, this proposed method is effective and robust in the characterization of coronary plaque composition from in vivo OCT imaging. On average, the method achieves 0.86 in F1-score and 0.88 in accuracy. The TwopathCNN architecture and cascaded structure show significant improvement in performance (p < 0.05). CNN with cascaded structure can greatly improve the performance of characterization compared to the conventional CNN methods and machine learning methods. This method has a higher efficiency, which may be proven to be a promising diagnostic tool in the detection of coronary plaques.

Download Full-text

106Plasma trimethylamine N-oxide is associated with culprit plaque characterization as assessed by optical coherence tomography in patients with acute myocardial infarction

European Heart Journal ◽

10.1093/eurheartj/ehz747.0034 ◽

2019 ◽

Vol 40 (Supplement_1) ◽

Author(s):

Z Sheng ◽

Y Tan ◽

H Yan

Keyword(s):

Myocardial Infarction ◽

Acute Myocardial Infarction ◽

Optical Coherence Tomography ◽

Plaque Rupture ◽

Demographic Data ◽

Coronary Plaque ◽

Optical Coherence ◽

Plaque Characterization ◽

Medical Sciences ◽

Laboratory Findings

Abstract Background Previous study have demonstrated that plasma trimethylamine N-oxide (TMAO) is associated with vulnerable plaque characteristics as assessed by optical coherence tomography (OCT) in patients with coronary artery disease. However, the relation between TMAO and the culprit plaque characteristics as assessed by OCT in patients with acute myocardial infarction (AMI) exhibiting plaque rupture at the site of the culprit stenosis is unknown. Objective To explore the relation between plasma TMAO and coronary culprit plaque characterization assessed by OCT in AMI patients exhibiting plaque rupture. Method We prospectively enrolled 90 AMI patients with plaque rupture identified by OCT and collected demographic data, risk factors, coronary angiography and OCT data, medical history and laboratory findings of all patients. Plasma TMAO levels were detected by stable isotope dilution liquid chromatography tandem mass spectrometry. Macrophage presence in coronary culprit plaque was quantified by normalized standard deviation (NSD). Result All patients were divided into two groups (high TMAO group and low TMAO group) according to the median plasma TMAO level (3.22uM). The culprit plaques in the high TMAO group exhibited a thinner fibrous cap thickness (60um [60–100um] versus 90um [70–110um], P=0.013]), higher frequency of thin-cap fibroatheroma (TCFA) (15.6% versus 55.6%, P<0.001), microvessel (24.4% versus 4.4%, P=0.014) and macrophage infiltration (66.7% versus 26.7%, P<0.001) compared with the low TMAO group. Moreover, the level of TMAO was significantly positively associated with NSD (Pearson's correlation coefficient: r=0.766, P<0.001). Conclusion Plasma TMAO levels are associated with coronary plaque vulnerability and inflammation in patients with AMI exhibiting plaque rupture. Acknowledgement/Funding Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences (2016-I2M-1-009)

Download Full-text