Association between in-stent neointimal characteristics and native coronary artery disease progression

Deep learning model DeepNeo predicts neointimal tissue characterization using optical coherence tomography

BACKGROUND

Accurate interpretation of optical coherence tomography (OCT) pullbacks is critical for assessing vascular healing after percutaneous coronary intervention (PCI). Manual analysis is time-consuming and subjective, highlighting the need for a fully automated solution.

METHODS

In this study, 1148 frames from 92 OCT pullbacks were manually annotated to classify neointima as homogeneous, heterogeneous, neoatherosclerosis, or not analyzable on a quadrant level. Stent and lumen contours were annotated in 305 frames for segmentation of the lumen, stent struts, and neointima. We used these annotations to train a deep learning algorithm called DeepNeo. Performance was further evaluated in an animal model (male New Zealand White Rabbits) of neoatherosclerosis using co-registered histopathology images as the gold standard.

RESULTS

DeepNeo demonstrates a strong classification performance for neointimal tissue, achieving an overall accuracy of 75%, which is comparable to manual classification accuracy by two clinical experts (75% and 71%). In the animal model of neoatherosclerosis, DeepNeo achieves an accuracy of 87% when compared with histopathological findings. For segmentation tasks in human pullbacks, the algorithm shows strong performance with mean Dice overlap scores of 0.99 for the lumen, 0.66 for stent struts, and 0.86 for neointima.

CONCLUSIONS

To the best of our knowledge, DeepNeo is the first deep learning algorithm enabling fully automated segmentation and classification of neointimal tissue with performance comparable to human experts. It could standardize vascular healing assessments after PCI, support therapeutic decisions, and improve risk detection for cardiac events.

Relationship between stress hyperglycemia ratio and progression of non target coronary lesions: a retrospective cohort study

BACKGROUND

Stress hyperglycemia ratio is a novel indicator of acute coronary synthesis (ACS), which is closely related to the severity and complications of ACS and other cardiovascular diseases. However, its relationship with the progression of non target coronary lesions remains unclear. The purpose of this paper is to explore the relationship between stress hyperglycemia ratio and the progression of non target coronary lesions.

METHODS

This study retrospectively enrolled patients diagnosed with acute coronary syndrome who underwent stent implantation and follow-up evaluations by coronary angiography at Zhongda Hospital between January 2019 and January 2024. Patients were classified into progression and non progression groups based on follow-up angiography findings. Logistic regression models, restricted cubic spline analysis, and machine learning algorithms (LightGBM, decision tree, and XGBoost) were utilized to analyse the relationship of stress hyperglycemia ratio and non target lesion progression.

RESULTS

A total of 1,234 ACS patients were included; 29.1% experienced non target lesions progression. Logistic regression analysis showed that stress hyperglycemia ratio (SHR) was a risk factor for non target disease progression (P < 0.001), and after adjusting for other variables, SHR was still independently associated with non target disease progression (OR = 2.12, 95% CI: 1.30-3.44, p = 0.003). RCS analysis revealed a near-linear relationship between SHR and nontarget lesions progression (P = 0.14). With the increase of SHR, the risk of non target lesions progression continued to increase, and the risk was significant when the SHR was greater than 0.96, but tended to be stable when the SHR was greater than 1.36 (p = 0.0047). A hybrid model combining logistic regression and XGBoost yielded the best predictive performance, with an AUC of 0.78 (95% CI: 0.72-0.85), incorporating SHR, number and stenosis severity of non target lesions (NTLs), hypertension and high-density lipoprotein cholesterol (HDL-c). Subgroup analysis showed that elevated SHR was a stronger predictor of NTL progression in non-diabetic patients (OR = 3.76, p = 0.007) compared with diabetic patients (OR = 1.69, p = 0.083).

CONCLUSION

Stress hyperglycemia ratio is closely related to the progression of non target lesions. This study provides a novel insight for optimizing the long-term management of non target lesions after PCI.

Non-target lesion progression: Unveiling critical predictors and outcomes in patients with in-stent restenosis

BACKGROUND

Percutaneous coronary intervention (PCI) has become the primary treatment for coronary artery disease. However, while PCI effectively addresses severe stenosis or occlusive lesions in target vessels, the progression of non-target vessel plaque remains a critical determinant of long-term patient prognosis.

AIMS

The purpose of this study was to investigate the impact of non-target vascular plaque progression on prognosis after PCI for ISR.

METHODS

This study included 195 patients diagnosed with ISR and multivessel disease who underwent successful PCI with drug-eluting stent (DES) placement, along with intraoperative optical coherence tomography (OCT) assessment of the culprit stent. Subsequent rechecked coronary angiography categorized eligible patients into non-target lesion progression (N-TLP) and no-N-TLP groups. We evaluated the baseline morphological characteristics of N-TLP by OCT and investigated the relationship between N-TLP, non-culprit vessel-related major adverse cardiovascular events (NCV-MACE), and pan-vascular disease-related clinical events (PVD-CE) incidence.

RESULTS

Multivariate logistic regression analysis revealed that diabetes mellitus (OR 3.616, 95% CI: 1.735-7.537; P = 0.001), uric acid level (OR 1.005, 95% CI: 1.001-1.009; P = 0.006), in-stent neoatherosclerosis (ISNA) (OR 1.334, 95% CI: 1.114-1.985; P = 0.047) and heterogeneous neointima morphology (OR 2.48, 95% CI: 1.18-5.43; P = 0.019) were independent predictors for N-TLP. Furthermore, N-TLP was associated with a high incidence of NCV-MACE (19.4% vs 6.9%, P = 0.009) and PVD-CE (83.9% [95% CI: 79.7%-88.3%] vs 93.1% [95% CI: 88.4%-98.0%], P = 0.038) after PCI in ISR patients.

CONCLUSION

Diabetes, uric acid levels, ISNA, and heterogeneous neointima are predictive factors for subsequent rapid plaque progression, with N-TLP exacerbating the incidence of NCV-MACE and PVD-CE after PCI.

Optical Coherence Tomography Findings in Patients Presenting With In-Stent Restenosis: A Prospective Observational Study of Patterns of Neointimal Hyperplasia and Associated Risk Factors

Introduction Morphological features of neointimal tissue play a pivotal role in the pathophysiology of in-stent restenosis (ISR) after percutaneous coronary intervention (PCI). This study was designed to qualitatively and quantitatively assess neointimal characteristics of lesions using optical coherence tomography (OCT) in patients presenting with ISR.  Methods This was a single-center, prospective, observational study performed at a tertiary-care center in India. Patients diagnosed with stable angina and acute coronary syndrome with post-procedural angiographically documented restenosis (>50%) were included. Results A total of 34 patients with ISR were studied. Neointimal hyperplasia was classified as (i) homogenous group (n = 18) and (ii) non-homogenous group (n = 16). Fourteen (77.8%) diabetics belonged to the homogenous group. Predominant plaque characteristics such as neoatherosclerosis, cholesterol crystals, and calcium were documented in 14 (77.8%), 12 (66.7%), and 11 (61.1%) patients in the homogenous group and 10 (62.5%), 10 (62.5%), and 9 (56.2%) patients in the non-homogenous group, respectively. Unexpanded stent struts were identified in 11 (61.1%) and 11 (68.8%) patients in the homogenous and non-homogenous groups, respectively. Mean strut thickness was 93.73 ± 31.03 µm and 83.54 ± 18.0 µm, ISR was 72.50 ± 15.93% and 65.37 ± 21.69%, the neointimal thickness was 588.06 ± 167.82 μm and 666.25 ± 218.05 μm, and neointimal hyperplasia was 54.54 ± 11.23% and 59.26 ± 8.86% in the homogenous and non-homogenous groups, respectively. Conclusion Neoatherosclerosis and stent underexpansion were predominantly observed in our study and only diabetes was found to be significantly associated with homogenous neointimal hyperplasia.

Advantages and prospects of optical coherence tomography in interventional therapy of coronary heart disease (Review)

Coronary heart disease is the leading cause of mortality among all diseases globally. Percutaneous coronary intervention (PCI) is a key method for the treatment of coronary heart disease. Optical coherence tomography (OCT) is an optical diagnostic technology with a resolution of up to 10 µm, which is able to accurately assess the composition of the coronary arterial wall and determine the characteristics of atherosclerotic lesions. It is also highly consistent with pathological examinations, optimizing the effect of stent implantation and evaluation of the long-term effectiveness and safety of the stent, which has irreplaceable value in the field of precision and optimization of coronary intervention. The innovative OCT technology may help provide more comprehensive clinical research evidence. The application of OCT in clinical and basic research of coronary atherosclerosis, selection of treatment strategies for acute coronary syndromes, optimization of interventional treatment efficacy, evaluation of novel stents, intimal stent coverage and selection of dual antiplatelet drugs has become more widely used, affecting the current coronary interventional treatment strategies to a certain extent. The aim of the present review was to discuss the role of OCT in evaluating preoperative plaque characteristics, guiding PCI and evaluating the effects of postoperative stents or drug treatments.