Plaque Erosion Research Articles

Kounis Syndrome: A Comprehensive Review of Pathophysiology, Clinical Manifestations, Diagnostic Challenges, and Therapeutic Strategies

Kounis syndrome, also known as allergic angina or allergic myocardial infarction, is a rare but potentially life-threatening condition characterized by the acute onset of chest pain, myocardial infarction, or sudden cardiac death in the setting of allergic or hypersensitivity reactions. The syndrome encompasses a spectrum of acute coronary syndromes triggered by various allergic insults, including medications, insect stings, food allergens, and environmental exposures. The pathophysiology involves the activation of mast cells and platelets, leading to coronary artery spasm, atheromatous plaque erosion or rupture, and subsequent myocardial ischemia or infarction. Diagnosis can be challenging due to the diverse clinical presentations and the need for a high index of suspicion. Management includes the identification and avoidance of triggers, along with the use of standard therapies for acute coronary syndromes. This review aims to provide a comprehensive overview of Kounis syndrome, focusing on its pathophysiology, clinical manifestations, diagnostic considerations, and therapeutic strategies.

The relationship between complement C1q and coronary plaque vulnerability based on optical coherence tomography analysis

To determine the association between complement C1q and vulnerable plaque morphology among coronary artery disease (CAD) patients. We conducted a retrospective observational study of 221 CAD patients admitted to The Second Affiliated Hospital of Xi’an Jiaotong University. Intravascular optical coherence tomography was utilized to describe the culprit plaques’ morphology. Using logistic regression analysis to explore the correlation between C1q and vulnerable plaques, and receiver operator characteristic (ROC) analysis assess the predictive accuracy. As reported, the complement C1q level was lower in ACS patients than CCS patients (18.25 ± 3.88 vs. 19.18 ± 4.25, P = 0.045). The low complement-C1q-level group was more prone to develop vulnerable plaques. In lipid-rich plaques, the complement C1q level was positively correlated with the thickness of fibrous cap (r = 0.480, P = 0.041). Univariate and multivariate logistic regression analyses suggested that complement C1q could be an independent contributor to plaques’ vulnerability. For plaque rupture, erosion, thrombus, and cholesterol crystals, the areas under the ROC curve of complement C1q level were 0.873, 0.816, 0.785, and 0.837, respectively (P < 0.05 for all). In CAD patients, the complement C1q could be a valuable indicator of plaque vulnerability.

The Impact of Flow-Mediated Vasodilatation on Mechanism and Prognosis in Patients with Acute Coronary Syndrome: A FMD and OCT Study.

Endothelial dysfunction, characterized by impaired flow-mediated vasodilation (FMD), is associated with atherosclerosis. However, the relationship between FMD, plaque morphology, and clinical outcomes in patients with acute coronary syndrome (ACS) remains underexplored. This study aims to investigate the influence of FMD on the morphology of culprit plaques and subsequent clinical outcomes in patients with ACS. This study enrolled 426 of 2482 patients who presented with ACS and subsequently underwent both preintervention FMD and optical coherence tomography (OCT) between May 2020 and July 2022. Impaired FMD was defined as an FMD% less than 7.0%. Major adverse cardiac events (MACEs) included cardiac death, nonfatal myocardial infarction, revascularization, or rehospitalization for angina. Within a one-year follow-up, 34 (8.0%) patients experienced MACEs. The median FMD% was 4.0 (interquartile range 2.6-7.0). Among the patients, 225 (52.8%) were diagnosed with plaque rupture (PR), 161 (37.8%) with plaque erosion (PE), and 25 (5.9%) with calcified nodules (CN). Impaired FMD was found to be associated with plaque rupture (odds ratio [OR] = 4.22, 95% confidence interval [CI]: 2.07-6.72, p = 0.012) after adjusting for potential confounding factors. Furthermore, impaired FMD was linked to an increased incidence of MACEs (hazard ratio [HR] = 3.12, 95% CI: 1.27-6.58, p = 0.039). Impaired FMD was observed in three quarters of ACS patients and can serve as a noninvasive predictor of plaque rupture and risk for future adverse cardiac outcomes.

Predictive value of the serum uric acid to high-density lipoprotein cholesterol ratio for culprit plaques in patients with acute coronary syndrome

BackgroundHyperuricemia and low level of high-density lipoprotein cholesterol (HDL-C) are both risk factors for coronary artery disease (CAD). The uric acid to HDL-C ratio (UHR) has recently been identified as a new inflammatory and metabolic biomarker. However, the relationship between the UHR and coronary culprit plaques has not been fully investigated in patients with acute coronary syndrome (ACS).MethodsA total of 346 patients with ACS were enrolled in this study. Culprit lesion characteristics were assessed by optical coherence tomography (OCT). Logistic regression and linear correlation analyses were performed to assess the association between the UHR and culprit plaques. The predictive value of the UHR was investigated by receiver operating characteristic (ROC) curve analysis.ResultsThe percentages of typical culprit plaques, including ruptures, erosions and thrombi, were greater in the high-UHR subgroup than those in the low-UHR subgroup. A positive relationship was also found between the UHR and diameter stenosis (r = 0.160, P = 0.003) and between the UHR and area stenosis (r = 0.145, P = 0.007). The UHR was found to be independently associated with plaque rupture, erosion and thrombus. Furthermore, ROC analysis suggested that the UHR had a better predictive value than low-density lipoprotein cholesterol.ConclusionsAn elevated UHR level was independently related to the occurrence rate of culprit plaques. The UHR is a simple and easily acquired parameter for detecting culprit plaques in patients with ACS.

Pathological Characteristics and Classification of Unstable Coronary Atherosclerotic Plaques.

Important forensic diagnostic indicators of sudden death in coronary atherosclerotic heart disease, such as acute or chronic myocardial ischemic changes, sometimes make it difficult to locate the ischemic site due to the short death process, the lack of tissue reaction time. In some cases, the deceased died of sudden death on the first-episode, resulting in difficulty for medical examiners to make an accurate diagnosis. However, clinical studies on coronary instability plaque revealed the key role of coronary spasm and thrombosis caused by their lesions in sudden coronary death process. This paper mainly summarizes the pathological characteristics of unstable coronary plaque based on clinical medical research, including plaque rupture, plaque erosion and calcified nodules, as well as the influencing factors leading to plaque instability, and briefly describes the research progress and technique of the atherosclerotic plaques, in order to improve the study on the mechanism of sudden coronary death and improve the accuracy of the forensic diagnosis of sudden coronary death by diagnosing different pathologic states of coronary atherosclerotic plaques.

Biosensing Platforms for Cardiac Biomarker Detection.

Myocardial infarction (MI) is a cardiovascular disease that occurs when there is an elevated demand for myocardial oxygen as a result of the rupture or erosion of atherosclerotic plaques. Globally, the mortality rates associated with MI are steadily on the rise. Traditional diagnostic biomarkers employed in clinical settings for MI diagnosis have various drawbacks, prompting researchers to investigate fast, precise, and highly sensitive biosensor platforms and technologies. Biosensors are analytical devices that combine biological elements with physicochemical transducers to detect and quantify specific compounds or analytes. These devices play a crucial role in various fields including healthcare, environmental monitoring, food safety, and biotechnology. Biosensors developed for the detection of cardiac biomarkers are typically electrochemical, mass, and optical biosensors. Nanomaterials have emerged as revolutionary components in the field of biosensing, offering unique properties that significantly enhance the sensitivity and specificity of the detection systems. This review provides a comprehensive overview of the advancements and applications of nanomaterial-based biosensing systems. Beginning with an exploration of the fundamental principles governing nanomaterials, we delve into their diverse properties, including but not limited to electrical, optical, magnetic, and thermal characteristics. The integration of these nanomaterials as transducers in biosensors has paved the way for unprecedented developments in analytical techniques. Moreover, the principles and types of biosensors and their applications in cardiovascular disease diagnosis are explained in detail. The current biosensors for cardiac biomarker detection are also discussed, with an elaboration of the pros and cons of existing platforms and concluding with future perspectives.

Vasospastic angina, plaque erosion, ischemia, and cardiac arrest: Four of a kind or a straight?

Vasospastic angina, plaque erosion, ischemia, and cardiac arrest: Four of a kind or a straight?

The Role of Fluid Mechanics in Coronary Atherosclerotic Plaques: An Up-to-Date Review.

Most acute coronary syndromes are due to a sudden luminal embolism caused by the rupturing or erosion of atherosclerotic plaques. Prevention and treatment of plaque development have become an effective strategy to reduce mortality and morbidity from coronary heart disease. It is now generally accepted that plaques with thin-cap fibroatheroma (TCFA) are precursors to rupturing and that larger plaques and high-risk plaque features (including low-attenuation plaque, positive remodeling, napkin-ring sign, and spotty calcification) constitute unstable plaque morphologies. However, plaque vulnerability or rupturing is a complex evolutionary process caused by a combination of multiple factors. Using a combination of medicine, engineering mechanics, and computer software, researchers have turned their attention to computational fluid mechanics. The importance of fluid mechanics in pathological states for promoting plaque progression, inducing plaque tendency to vulnerability, or even rupture, as well as the high value of functional evaluation of myocardial ischemia has become a new area of research. This article reviews recent research advances in coronary plaque fluid mechanics, aiming to describe the concept, research implications, current status of clinical studies, and limitations of fluid mechanic's characteristic parameters: wall shear stress (WSS), axial plaque shear (APS), and fractional flow reserve (FFR). Previously, most computational fluid dynamics were obtained using invasive methods, such as intravascular ultrasound (IVUS) or optical coherence tomography (OCT). In recent years, the image quality and spatial resolution of coronary computed tomography angiography (CCTA) have greatly improved, making it possible to compute fluid dynamics by noninvasive methods. In the future, the combination of CCTA-based anatomical stenosis, plaque high-risk features, and fluid mechanics can further improve the prediction of plaque development, vulnerability, and risk of rupturing, as well as enabling noninvasive means to assess the degree of myocardial ischemia, thereby providing an important aid to guide clinical decision-making and optimize treatment.

A Personalized Approach for Patients with Myocardial Infarction with Non-Obstructive Coronary Arteries.

Myocardial infarction with non-obstructive coronary arteries (MINOCA) includes coronary embolism, dissection, spasm and microvascular dysfunction, as well as plaque rupture or erosion (causing 50% stenosis). In the most recent studies, events that can be classified as MINOCA account for approximately 6-8% of all diagnoses of acute myocardial infarction (AMI). Clinical suspect may suggest the need for additional diagnostic procedures beyond the usual coronary angiography, such as cardiac imaging or provocative tests. Cardiac magnetic resonance (CMR) is essential for both validating the diagnosis and ruling out other conditions with a comparable clinical presentation. The prognosis is not as good as previously believed; rather, it is marked by morbidity and mortality rates comparable to those of other types of AMI. Identification of the underlying causes of MINOCA is recommended by current guidelines and consensus documents in order to optimize treatment, enhance prognosis, and encourage prevention of recurrent myocardial infarction. In this narrative review, we have outlined the various causes of MINOCA and their specific therapies in an attempt to identify a personalized approach to its treatment.

Macrophage mediators and mechanisms in cardiovascular disease.

Macrophages are major players in myocardial infarction (MI) and atherosclerosis, two major cardiovascular diseases (CVD). Atherosclerosis is caused by the buildup of cholesterol-rich lipoproteins in blood vessels, causing inflammation, vascular injury, and plaque formation. Plaque rupture or erosion can cause thrombus formation resulting in inadequate blood flow to the heart muscle and MI. Inflammation, particularly driven by macrophages, plays a central role in both atherosclerosis and MI. Recent integrative approaches of single-cell analysis-based classifications in both murine and human atherosclerosis as well as experimental MI showed overlap in origin, diversity, and function of macrophages in the aorta and the heart. We here discuss differences and communalities between macrophages in the heart and aorta at steady state and in atherosclerosis or upon MI. We focus on markers, mediators, and functional states of macrophage subpopulations. Recent trials testing anti-inflammatory agents show a major benefit in reducing the inflammatory burden of CVD patients, but highlight a necessity for a broader understanding of immune cell ontogeny and heterogeneity in CVD. The novel insights into macrophage biology in CVD represent exciting opportunities for the development of novel treatment strategies against CVD.

Allergic Acute Coronary Syndrome: A Case Report and Literature Review

Introduction: Kounis Syndrome was first described in 1991 by Kounis and Zavras as “the concurrence of chest pain during an allergic reaction, accompanied by clinical laboratory findings of classical angina pectoris caused by inflammatory mediators released during the allergic insult” [1].&#x0D; The mechanism of Kounis Syndrome most likely involves the release of cytokines through mast-cell degranulation, which leads to coronary vasospasm and atheromatous plaque erosion or rupture following the allergic reaction to an allergen.[2]&#x0D; The treatment is specific to acute coronary syndrome and anaphylaxis, with the added complication that the drugs used, while indicated in each of the two disorders separately, may present contradictions when administered jointly in one patient.[3]&#x0D; The purpose of this review is to briefly revise the existing literature regarding its overlooked diagnosis and contradictory joint management of anaphylaxis and acute coronary syndrome.&#x0D; We will conduct a brief review of the current literature on Kounis Syndrome while describing a suspected case of a female patient presented with both anaphylaxis symptoms and angina pectoris.&#x0D; Conclusions: Kounis syndrome is defined as the co-incidental occurrence of an acute coronary syndrome with hypersensitivity reactions following an allergic reaction. Treatment of allergic reactions may be sufficient in type I KS. In contrast, coronary intervention is needed in the other two types, accompanied by vasodilator drugs, including nitrates and calcium antagonists, each of which may have contradictory effects.

Differential culprit plaque morphology in acute coronary syndrome: a comparison between very young patients (≤35 years) and older counterparts using optical coherence tomography.

Underlying mechanisms responsible for acute coronary syndrome (ACS) in young patients compared with older counterparts are yet to be explored with optical coherence tomography (OCT). This study aims to explore underlying mechanisms of ACS in ≤35- (very young) and >35-year-old (older counterparts) ACS patients using OCT. This was a prospective, single-centre, investigational study. Patients were divided into groups according to age (≤35 and >35 years) and further subdivided according to the underlying mechanism i.e. plaque rupture (PR) and plaque erosion (PE). A total of 93 patients were analysed. Thin-cap fibroatheroma (TCFA) was significantly higher among older counterparts than very young patients for both PR (80.0% vs. 31.8%, P = 0.002) and PE (66.7% vs. 6.3%, P < 0.001) groups. Microchannels were also significantly more prevalent among older than very young patients for both PR (65.0% vs. 18.2%, P = 0.004) and PE groups (55.6% vs.12.5%, P = 0.013). Macrophages were significantly higher in older than very young patients for both PR (25.0% vs. 0%, P = 0.018) and PE (44.4% vs. 0%, P = 0.003) groups. In contrast, fibrous cap thickness was greater in very young than older patients for both PR (105.71 ± 48.02 vs. 58.00 ± 15.76 µm, P < 0.001) and PE (126.67 ± 48.22 vs. 54.38 ± 24.21 µm, P < 0.001) groups. Intimal thickness was greater in older than very young patients for both PR (728.00 ± 313.92 vs. 342.27 ± 142.02 µm, P < 0.001) and PE (672.78 ± 334.57 vs. 295.00 ± 99.60 µm, P < 0.001) groups. Frequency of TCFA, microchannels, macrophages, and intimal thickness was significantly higher in older ACS patients compared with very young patients. However, fibrous cap thickness was significantly greater in very young ACS patients compared with older patients.

Differential Proteoglycan Expression in Atherosclerosis Alters Platelet Adhesion and Activation.

Proteoglycans are differentially expressed in different atherosclerotic plaque phenotypes, with biglycan and decorin characteristic of ruptured plaques and versican and hyaluronan more prominent in eroded plaques. Following plaque disruption, the exposure of extracellular matrix (ECM) proteins triggers platelet adhesion and thrombus formation. In this study, the impact of differential plaque composition on platelet function and thrombus formation was investigated. Platelet adhesion, activation and thrombus formation under different shear stress conditions were assessed in response to individual proteoglycans and composites representing different plaque phenotypes. The results demonstrated that all the proteoglycans tested mediated platelet adhesion but not platelet activation, and the extent of adhesion observed was significantly lower than that observed with type I and type III collagens. Thrombus formation upon the rupture and erosion ECM composites was significantly reduced (p < 0.05) compared to relevant collagen alone, indicating that proteoglycans negatively regulate platelet collagen responses. This was supported by results demonstrating that the addition of soluble biglycan or decorin to whole blood markedly reduced thrombus formation on type I collagen (p < 0.05). Interestingly, thrombus formation upon the erosion composite displayed aspirin sensitivity, whereas the rupture composite was intensive to aspirin, having implications for current antiplatelet therapy regimes. In conclusion, differential platelet responses and antiplatelet efficacy are observed on ECM composites phenotypic of plaque rupture and erosion. Proteoglycans inhibit thrombus formation and may offer a novel plaque-specific approach to limit arterial thrombosis.

Association between apolipoprotein B/A1 ratio and quantities of tissue prolapse on optical coherence tomography examination in patients with atherosclerotic cardiovascular disease

Atherosclerotic cardiovascular disease (ASCVD) continues to be a major health concern globally. Apolipoprotein (Apo) B/A1 ratio is a reliable predictor of ASCVD and an important factor in assessing the risk of myocardial infarction. Tissue prolapse (TP) is defined as the tissue extrusion into the lumen through the stent struts after implantation, which is a significant factor for poor short-term outcomes such as acute and subacute thrombosis, severe myocardial necrosis, and vulnerable plaque. Therefore, the aim of this study was to investigate the relationship between Apo B/A1, plaque vulnerability, and tissue prolapse on optical coherence tomography (OCT). This study enrolled 199 patients with atherosclerotic cardiovascular disease (ASCVD) who underwent percutaneous coronary intervention (PCI). Both pre- and post-procedural optical coherence tomography (OCT) examinations were conducted to assess TP volume and plaque morphology. Logistic regression analyses were performed to identify potential risk factors for tissue prolapse volume. Receiver operator characteristic (ROC) curve analysis was carried out to evaluate the value of the Apo B/A1 ratio for tissue prolapse volume. The high Apo B/A1 ratio group showed a larger TP volume (P = 0.001) and a higher percentage of plaque rupture and erosion in comparison to the low Apo B/A1 ratio group (P = 0.022 and P = 0.008). The high Apo B/A1 ratio group and the high TP volume group also had a higher proportion of thin-cap fibroatheroma (TCFA) (P = 0.046, P = 0.021). Multivariate logistic regression analysis revealed that both Apo B/A1 ratio (odds ratio [OR]: 1.041, 95% confidence interval [CI] 1.007–1.076; P = 0.019) and TCFA (OR: 3.199, 95%CI 1.133–9.031; 0.028) were significantly related to high TP volume. Furthermore, the area under the curve (AUC) for predictive value of TP volume was 0.635 for Apo B/A1 (95% CI 0.554–0.717, P = 0.002) compared to 0.615 for low density lipoprotein cholesterol (LDL-C) (95% CI 0.533–0.697, P = 0.008). The Apo B/A1 ratio is an independent predictor of TP volume on OCT and is related to plaque vulnerability.

Rapid Plaque Progression in a Patient with Non-ST-Segment Elevation Acute Coronary Syndrome: A Case Report

Acute coronary syndrome (ACS), diagnosed by optical coherence tomography (OCT), is caused primarily by plaque rupture, plaque erosion, and calcified nodules. Plaque erosion is more common in patients with non-ST-segment elevation myocardial infarction than ST-segment elevation myocardial infarction. This study reports the details of a case of ACS caused by massive thrombus formation due to plaque erosion. The factors associated with plaque erosion and thrombosis could not be confirmed on the basis of clinical examination findings and the physicians’ experience; therefore, the initial diagnosis of an ischemic event was replaced by a diagnosis of rapid plaque progression, as microscopically confirmed by OCT. Therefore, OCT examination must be performed for blurred or “rapidly progressing” lesions identified through angiography.

Lipid Content Distribution and its Clinical Implication in Patients with Acute Myocardial Infarction-Plaque Erosion: Results from the Prospective OCTAMI Study.

Plaque erosion (PE) is one of the main plaque phenotypes of acute coronary syndrome (ACS). However, the underlying plaque component and distribution have not been systematically analysed. This study aims to investigate the distribution of lipid and calcium content in culprit lesions assessed by optical coherence tomography (OCT) in patients with PE and explore its relationship with prognosis in a cohort of ST segment elevation myocardial infarction (STEMI) patients. A prospective cohort of 576 patients with STEMI was enrolled in our study. After exclusion, 152 PE patients with clear underlying plaque components were ultimately analysed. The culprit lesion was divided into the border zone, external erosion zone and erosion site in the longitudinal view. Each pullback of the culprit lesions was assessed by 3 independent investigators frame-by-frame, and the quantity and distribution of lipid and calcium components were recorded. Of the 152 PE patients, lipid and calcium contents were more likely to exist in the external erosion zone than in the other regions. In particular, a high level of lipid content proximal to the erosion site was significantly associated with plaque vulnerability and a higher incidence of MACEs. This study revealed that high level of lipid content in the proximal external erosion zone was related to high-risk plaque characteristics and poor prognosis, which provided a novel method for risk stratification and precise management in patients with plaque erosion.

Grasp of Fate: Determining the Prognosis of Plaque Erosion?

Grasp of Fate: Determining the Prognosis of Plaque Erosion?

A novel deep learning model for a computed tomography diagnosis of coronary plaque erosion

Patients with acute coronary syndromes caused by plaque erosion might be managed conservatively without stenting. Currently, the diagnosis of plaque erosion requires an invasive imaging procedure. We sought to develop a deep learning (DL) model that enables an accurate diagnosis of plaque erosion using coronary computed tomography angiography (CTA). A total of 532 CTA scans from 395 patients were used to develop a DL model: 426 CTA scans from 316 patients for training and internal validation, and 106 separate scans from 79 patients for validation. Momentum Distillation-enhanced Composite Transformer Attention (MD-CTA), a novel DL model that can effectively process the entire set of CTA scans to diagnose plaque erosion, was developed. The novel DL model, compared to the convolution neural network, showed significantly improved AUC (0.899 [0.841–0.957] vs. 0.724 [0.622–0.826]), sensitivity (87.1 [70.2–96.4] vs. 71.0 [52.0–85.8]), and specificity (85.3 [75.3–92.4] vs. 68.0 [56.2–78.3]), respectively, for the patient-level prediction. Similar results were obtained at the slice-level prediction AUC (0.897 [0.890–0.904] vs. 0.757 [0.744–0.770]), sensitivity (82.2 [79.8–84.3] vs. 68.9 [66.2–71.6]), and specificity (80.1 [79.1–81.0] vs. 67.3 [66.3–68.4]), respectively. This newly developed DL model enables an accurate CT diagnosis of plaque erosion, which might enable cardiologists to provide tailored therapy without invasive procedures.Clinical Trial Registration:http://www.clinicaltrials.gov, NCT04523194.

Atherosclerotic Autoantigen ALDH4A1 as a Novel Immunological Indicator for Plaque Erosion in Patients with ST Segment Elevated Myocardial Infarction.

Aldehyde dehydrogenase 4A1 (ALDH4A1) was recently reported to be a novel autoantigen of atherosclerosis. However, its role in different phenotypes of acute coronary syndrome remains unclear. Herein, we planned to explore the circulating and regional expression of ALDH4A1 in patients with plaque rupture (PR) and plaque erosion (PE) determined by optical coherence tomography (OCT). After applying the inclusion and exclusion criteria, a prospective series of 312 patients with ST segment elevated myocardial infarction (STEMI), including 161 patients with PR and 151 patients with PE determined by OCT, were enrolled for plasma ALDH4A1 testing. In addition, ALDH4A1 was quantified using immunofluorescence in aspirated coronary thrombus samples obtained from 31 patients with PR and 25 patients with PE. In addition, we established an atherosclerosis mouse model and analyzed the distribution of ALDH4A1 expression in different mouse organs. Furthermore, we compared the level of ALDH4A1 in the spleen and carotid artery between Apoe-/- and C57 mice. The results showed that the plasma level of ALDH4A1 was significantly higher in STEMI patients with PE than in those with PR (4.6 ng/mL [2.2-8.7] vs. 3.5 ng/mL [1.6-5.6] p = 0.005). The expression of ALDH4A1 in aspirated coronary thrombi was also significantly higher in patients with PE than in those with PR (mean gray value: 32.0 [23.6-40.6] vs. 16.8 [14.0-24.5], p < 0.001). In animal models, the expression of ALDH4A1 is much higher in the spleen than in other organs, and the level of ALDH4A1 is significantly elevated in the spleen and carotid artery of Apoe-/- mice compared with C57 mice. The high levels of ALDH4A1 in the plasma and aspirated coronary thrombi independently correlated with PE in patients with STEMI. These results suggested that ALDH4A1 is involved in the mechanism of PE and serves as a promising biomarker and treatment target for patients with PE.

A novel deep learning model for a coronary computed tomography angiography diagnosis of plaque erosion

Abstract Background Plaque erosion is the underlying pathology in up to 50% of patients with non-ST-segment elevation acute coronary syndromes (ACS). Previous studies suggest that patients with erosion might be treated conservatively without stenting. Currently, a diagnosis of plaque erosion requires invasive intracoronary imaging. Purpose We sought to develop a deep learning (DL) model that enables an accurate diagnosis of plaque erosion using coronary computed tomography angiography (CTA). Methods A total of 532 coronary CTA scans (143 coronary CTA scans with plaque rupture, 113 with plaque erosion, and 276 with reference segment) from 395 patients were included to develop a model: 426 coronary CTA scans from 316 patients for training and internal validation, and 106 separate scans from 79 patients for test set validation. Among ACS patients, the diagnosis of plaque rupture or erosion identified by OCT was used as the ground truth, and the corresponding site on the CTA image matched with OCT image was determined to be the culprit lesion. A novel DL, Momentum Distillation Composite Transformer Attention (MD-CTA) model, was developed that can effectively process the whole CTA scans to diagnose plaque erosion. Results The novel DL model showed diagnostic performance in the five-fold cross-validation with an area under the receiver-operating characteristic curve (AUC) of 0.901 (0.873-0.930), a sensitivity of 81.2 (72.8-88.0), and a specificity of 86.6 (82.4-90.2), all of which were significantly higher than those of convolutional neural network (CNN) model with an AUC of 0.621 (0.567-0.675), the sensitivity of 59.8 (50.1-69.0), and specificity of 60.2 (54.5-65.7) in training validation. Similarly, in the test set validation, the AUC, sensitivity, and specificity of the MD-CTA model were 0.899 (0.841-0.957), 87.1 (70.2-96.4), and 85.3 (75.3-92.4), respectively, higher than those of 0.724 (0.622-0.826), 71.0 (52.0-85.8), and 68.0 (56.2-78.3) of the CNN model. At the slice level, the MD-CTA model was also superior in the five-fold cross-validation and the test set validation compared to the CCN model. This model significantly outperformed experienced cardiologists, especially for sensitivity. Conclusions The newly developed DL model enables an accurate CTA diagnosis of plaque erosion, which might enable the cardiologist to provide tailored therapy without invasive procedures. This algorithm might lead to a major shift in managing millions of patients with plaque erosion each year.Table 1Figure 1