Department of Internal Medicine, MedStar Washington Hospital Center, Washington, DC, USA.
Department of Interventional Cardiology, MedStar Washington Hospital Center, Washington, DC, USA.
Cardiovasc Revasc Med. 2024 Jan;58:79-87. doi: 10.1016/j.carrev.2023.07.003. Epub 2023 Jul 16.
To assess the reproducibility of coronary tissue characterization by an Artificial Intelligence Optical Coherence Tomography software (OctPlus, Shanghai Pulse Medical Imaging Technology Inc.).
74 patients presenting with multivessel ST-segment elevation myocardial infarction (STEMI) underwent optical coherence tomography (OCT) of the infarct-related artery at the end of primary percutaneous coronary intervention (PPCI) and during staged PCI (SPCI) within 7 days thereafter in the MATRIX (Minimizing Adverse Hemorrhagic Events by Transradial Access Site and angioX) Treatment-Duration study (ClinicalTrials.gov, NCT01433627). OCT films were run through the OctPlus software. The same region of interest between either side of the stent and the first branch was identified on OCT films for each patient at PPCI and SPCI, thus generating 94 pairs of segments. 42 pairs of segments were re-analyzed for intra-software difference. Five plaque characteristics including cholesterol crystal, fibrous tissue, calcium, lipid, and macrophage content were analyzed for various parameters (span angle, thickness, and area).
There was no statistically significant inter-catheter (between PPCI and SPCI) or intra-software difference in the mean values of all the parameters. Inter-catheter correlation for area was best seen for calcification [intraclass correlation coefficient (ICC) 0.86], followed by fibrous tissue (ICC 0.87), lipid (ICC 0.62), and macrophage (ICC 0.43). Some of the inter-catheter relative differences for area measurements were large: calcification 9.75 %; cholesterol crystal 74.10 %; fibrous tissue 5.90 %; lipid 4.66 %; and macrophage 1.23 %. By the intra-software measurements, there was an excellent correlation (ICC > 0.9) for all tissue types. The relative differences for area measurements were: calcification 0.64 %; cholesterol crystal 5.34 %; fibrous tissue 0.19 %; lipid 1.07 %; and macrophage 0.60 %. Features of vulnerable plaque, minimum fibrous cap thickness and lipid area showed acceptable reproducibility.
The present study demonstrates an overall good reproducibility of tissue characterization by the Artificial Intelligence Optical Coherence Tomography software. In future longitudinal studies, investigators may use discretion in selecting the imaging endpoints and sample size, accounting for the observed relative differences in this study.
评估人工智能光学相干断层扫描软件（OctPlus，上海脉搏医疗影像技术有限公司）对冠状动脉组织特征进行重现的能力。
74 名多支血管 ST 段抬高型心肌梗死（STEMI）患者在首次经皮冠状动脉介入治疗（PPCI）结束时和之后的 7 天内行光学相干断层扫描（OCT）检查，在 MATRIX（经桡动脉入路和 angioX 最小化不良出血事件）治疗时间研究（ClinicalTrials.gov，NCT01433627）中进行分期经皮冠状动脉介入治疗（SPCI）。OCT 图像通过 OctPlus 软件运行。对每位患者 PPCI 和 SPCI 时支架两侧和第一个分支之间的相同感兴趣区域进行分析，从而生成 94 对节段。对 42 对节段进行了软件内差异的重新分析。分析了 5 种斑块特征，包括胆固醇晶体、纤维组织、钙、脂质和巨噬细胞含量，以获得各种参数（跨度角、厚度和面积）。
所有参数的平均数值在不同导管（PPCI 和 SPCI 之间）或软件内均无统计学显著差异。钙化的面积的相关性最好（组内相关系数（ICC）0.86），其次是纤维组织（ICC 0.87）、脂质（ICC 0.62）和巨噬细胞（ICC 0.43）。一些节段的面积测量的相对差异较大：钙化 9.75%；胆固醇晶体 74.10%；纤维组织 5.90%；脂质 4.66%；巨噬细胞 1.23%。通过软件内测量，所有组织类型的相关性均非常好（ICC>0.9）。面积测量的相对差异为：钙化 0.64%；胆固醇晶体 5.34%；纤维组织 0.19%；脂质 1.07%；巨噬细胞 0.60%。易损斑块、最小纤维帽厚度和脂质面积等特征具有可接受的重现性。
本研究表明人工智能光学相干断层扫描软件对组织特征的总体重现性良好。在未来的纵向研究中，研究人员可以根据本研究中观察到的相对差异，慎重选择成像终点和样本量。
