Background and Aims: Coronary thin-cap fibroatheromas (TCFA) are associated with adverse outcome, but identification of TCFA requires expertise and is highly time-demanding. This study evaluated the utility of artificial intelligence (AI) for TCFA identification in relation to clinical outcome. Methods: The PECTUS-AI study is a secondary analysis from the prospective observational PECTUS-obs study, in which 438 patients with myocardial infarction underwent optical coherence tomography (OCT) of all fractional flow reserve-negative non-culprit lesions (i.e. target lesions). OCT images were analyzed for the presence of TCFA by an independent core laboratory (CL-TCFA) and OCT-AID, a recently developed and validated AI segmentation algorithm (AI-TCFA). The primary outcome was defined as the composite of death from any cause, non-fatal myocardial infarction or unplanned revascularisation at 2 years (±30 days), excluding procedural and stent-related events. Results: Among 414 patients, AI-TCFA and CL-TCFA were identified in 143 (34.5%) and 124 (30.0%) patients, respectively. AI-TCFA within the target lesion was significantly associated with the primary outcome [hazard ratio (HR) 1.99, 95% confidence interval (CI) 1.02–3.90, P = .04], while the HR for CL-TCFA was non-significant (1.67, 95% CI: .84–3.30, P = .14). When evaluating the complete pullback, AI-TCFA showed an even stronger association with the primary outcome (HR 5.50, 95% CI: 1.94–15.62, P < .001; negative predictive value 97.6%, 95% CI: 94.0%–99.3%). Conclusions: AI-based OCT image analysis allows standardized identification of patients at increased risk of adverse cardiovascular outcome, offering an alternative to manual image analysis. Furthermore, AI-assisted evaluation of complete imaged segments results in better prognostic discrimatory value than evaluation of the target lesion only.

Intracoronary optical coherence tomography (OCT) is a valuable tool for, among others, periprocedural guidance of percutaneous coronary revascularization and the assessment of stent failure. However, manual OCT image interpretation is challenging and time-consuming, which limits widespread clinical adoption. Automated analysis of OCT frames using artificial intelligence (AI) offers a potential solution. For example, AI can be employed for automated OCT image interpretation, plaque quantification, and clinical event prediction. Many AI models for these purposes have been proposed in recent years. However, these models have not been systematically evaluated in terms of model characteristics, performances, and bias. We performed a systematic review of AI models developed for OCT analysis to evaluate the trends and performances, including a systematic evaluation of potential sources of bias in model development and evaluation.

Aims: Intracoronary optical coherence tomography (OCT) provides detailed information on coronary lesions, but interpretation of OCT images is time-consuming and subject to interobserver variability. The aim of this study was to develop and validate a deep learning-based multiclass semantic segmentation algorithm for OCT (OCT-AID). Methods and results: A reference standard was obtained through manual multiclass annotation (guidewire artefact, lumen, side branch, intima, media, lipid plaque, calcified plaque, thrombus, plaque rupture, and background) of OCT images from a representative subset of pullbacks from the PECTUS-obs study. Pullbacks were randomly divided into a training and internal test set. An additional independent dataset was used for external testing. In total, 2808 frames were used for training and 218 for internal testing. The external test set comprised 392 frames. On the internal test set, the mean Dice score across nine classes was 0.659 overall and 0.757 on the true-positive frames, ranging from 0.281 to 0.989 per class. Substantial to almost perfect agreement was achieved for frame-wise identification of both lipid (κ=0.817, 95% CI 0.743–0.891) and calcified plaques (κ=0.795, 95% CI 0.703–0.887). For plaque quantification (e.g. lipid arc, calcium thickness), intraclass correlations of 0.664–0.884 were achieved. In the external test set, κ-values for lipid and calcified plaques were 0.720 (95% CI 0.640–0.800) and 0.851 (95% CI 0.794–0.908), respectively. Conclusion: The developed multiclass semantic segmentation method for intracoronary OCT images demonstrated promising capabilities for various classes, while having included difficult frames, such as those containing artefacts or destabilized plaques. This algorithm is an important step towards comprehensive and standardized OCT image interpretation.

Extensively calcified lesions are typically at low risk for lesion-level acute events, which may be related to less vulnerable plaques. This study sought to evaluate the lesion-level association between total calcification volume and plaque vulnerability. Data were derived from the prospective, observational PECTUS-obs study, in which patients with myocardial infarction underwent intracoronary optical coherence tomography (OCT) imaging of all fractional flow reserve-negative nonculprit lesions. OCT images were analyzed by a core laboratory for plaque vulnerability features (lipid-rich plaque, thin-cap fibroatheroma, layered plaque, macrophage accumulation, microvessel, and cholesterol crystal) and by a validated artificial intelligence algorithm (OCT-AID) for automated volumetric calcium quantification. Total calcium volume was indexed for lesion length and stratified by quartiles (Q1-Q4), from lowest to highest. Among 488 lesions from 414 patients, calcium plaques were identified in 470 (96.3%) lesions. The lesion-level median indexed total calcium volume ranged from 0.004 mm³/mm (IQR: 0.001-0.011) in Q1 to 0.83 mm³/mm (IQR: 0.63-1.18) in Q4. The lower quartiles demonstrated the highest prevalence of lipid-rich plaques, macrophage accumulation, and microvessels. Thin-cap fibroatheroma and layered plaques accumulated predominantly in the middle quartiles (Q2-Q3). Cholesterol crystals showed no significant differences between quartiles. Overall, Q1-Q3 lesions demonstrated a greater mean number of plaque vulnerability features than Q4 lesions (P < 0.001 for all). Most severely calcified nonculprit lesions demonstrate a significantly lower prevalence of plaque vulnerability features as compared to less calcified, more lipid-rich lesions, which may contribute to the lower lesion-level acute event rate observed in heavily calcified lesions.

An advection-diffusion solver was applied to assess how stent strut shape and position impact the development of a pro-thrombotic region within the stented human artery. Presented here is a suitably parameterised advection-diffusion equation with a source term that is spatially uniform within a certain sub-domain of interest to compute a “time concentration”. The latter will serve as a surrogate quantity for the “age” of fluid parcels, i.e., the time the fluid parcel has spent in the sub-domain. This is a particularly useful concept in the context of coronary artery haemodynamics, where “stasis of blood” (or residence time) is recognized as the most important factor in thrombotic initiation. The novel method presented in this work has a very straightforward and convenient single lattice Boltzmann simulation framework encapsulation. A residence time surrogate is computed, presented and correlated with a range of traditional haemodynamic metrics (wall shear stress, shear rate and re-circulation region shapes) and finally, the role of these data to quantify the risk of thrombus formation is assessed.

An advection-diffusion solver has been applied to assess how stent strut shape and position impact the development of a pro-thrombotic region within the stented human artery. We use a suitably parameterised advection-diffusion equation with a source term that is spatially uniform within a certain sub-domain of interest, to compute a ``time concentration''. The latter will serve as a surrogate quantity for ``age'' of fluid parcels, i.e., the time the fluid parcel has spent in the sub-domain. This is a particularly useful concept in the context of coronary artery haemodynamics, where blood stasis (or residence time) is recognised as the most important factor in thrombotic initiation. Our novel method has a very straightforward and convenient single lattice Boltzmann simulation framework encapsulation. We compute, present and correlate our residence time surrogate with a range of traditional haemodynamic metrics (wall shear stress, shear rate and re-circulation region shapes) and finally assess how these data can be used to quantify the risk of thrombus formation.