Yang Jing, Li Xinze, Guo Yunbo, Song Peng, Lv Tiantian, Zhang Yingmei, Cui Yaoyao
IEEE Trans Ultrason Ferroelectr Freq Control. 2024 Nov;71(11):1440-1450. doi: 10.1109/TUFFC.2024.3475033. Epub 2024 Nov 27.
Intravascular ultrasound (IVUS) is the gold standard modality for in vivo visualization of coronary arteries and atherosclerotic plaques. Classification of coronary plaques helps to characterize heterogeneous components and evaluate the risk of plaque rupture. Manual classification is time-consuming and labor-intensive. Several machine learning-based classification approaches have been proposed and evaluated in recent years. In the current study, we develop a novel pipeline composed of serial classifiers for distinguishing IVUS images into five categories: normal, calcified plaque, attenuated plaque, fibrous plaque, and echolucent plaque. The cascades comprise densely connected classification models and machine learning classifiers at different stages. Over 100000 IVUS frames of five different lesion types were collected and labeled from 471 patients for model training and evaluation. The overall accuracy of the proposed classifier is 0.877, indicating that the proposed framework has the capacity to identify the nature and category of coronary plaques in IVUS images. Furthermore, it may provide real-time assistance on plaque identification and facilitate clinical decision-making in routine practice.
血管内超声（IVUS）是用于冠状动脉和动脉粥样硬化斑块体内可视化的金标准方法。冠状动脉斑块的分类有助于表征异质成分并评估斑块破裂的风险。手动分类既耗时又费力。近年来，已经提出并评估了几种基于机器学习的分类方法。在当前的研究中，我们开发了一种由串行分类器组成的新型管道，用于将IVUS图像分为五类：正常、钙化斑块、衰减斑块、纤维斑块和无回声斑块。这些级联包括不同阶段的密集连接分类模型和机器学习分类器。从471名患者中收集了超过100000帧五种不同病变类型的IVUS图像并进行标记，用于模型训练和评估。所提出的分类器的总体准确率为0.877，表明所提出的框架有能力识别IVUS图像中冠状动脉斑块的性质和类别。此外，它可能为斑块识别提供实时帮助，并有助于在常规实践中进行临床决策。
