School of Information & Electrical Engineering, Zhejiang University City College, Hangzhou, China.
Key Laboratory of Biomedical Engineering of Ministry of Education, Zhejiang University, Hangzhou, China.
Ultrason Imaging. 2019 Mar;41(2):78-93. doi: 10.1177/0161734618820112. Epub 2018 Dec 16.
The detection of the media-adventitia (MA) border in intravascular ultrasound (IVUS) images is essential for vessel assessment and disease diagnosis. However, it remains a challenging task, considering the existence of plaque, calcification, and various artifacts. In this article, an effective method based on classification is proposed to extract the MA border in IVUS images. First, a novel morphologic feature describing the relative position of each structure relative to the MA border, called RPES for short, is proposed. Then, the RPES feature and other features are employed in a multiclass extreme learning machine (ELM) to classify IVUS images into nine classes including the MA border and other structures. At last, a modified snake model is employed to effectively detect the MA border in the rectangular domain, in which a modified external force field is constructed on the basis of local border appearances and classification results. The proposed method is evaluated on a public dataset with 77 IVUS images by three indicators in eight situations, such as calcification and a guide wire artifact. With the proposed RPES feature, detection performances are improved by more than 39 percent, which shows an apparent advantage in comparative experiments. Furthermore, compared with two other existing methods used on the same dataset, the proposed method achieves 18 of the best indicators among 24, demonstrating its higher capability in detecting the MA border.
血管内超声（IVUS）图像中血管中层-外膜（MA）边界的检测对于血管评估和疾病诊断至关重要。然而，考虑到斑块、钙化和各种伪影的存在，这仍然是一项具有挑战性的任务。本文提出了一种基于分类的有效方法，用于提取 IVUS 图像中的 MA 边界。首先，提出了一种新的形态特征 RPES，用于描述每个结构相对于 MA 边界的相对位置。然后，将 RPES 特征和其他特征应用于多类极端学习机（ELM）中，将 IVUS 图像分为包括 MA 边界和其他结构在内的九类。最后，在矩形域中使用改进的蛇模型，根据局部边界外观和分类结果构建改进的外部力场，有效地检测 MA 边界。该方法在一个包含 77 张 IVUS 图像的公共数据集上进行了评估，在八种情况下（如钙化和导丝伪影）使用三个指标进行评估。通过引入所提出的 RPES 特征，检测性能提高了 39%以上，在对比实验中具有明显的优势。此外，与在同一数据集上使用的另外两种现有方法相比，所提出的方法在 24 个指标中获得了 18 个最佳指标，表明其在检测 MA 边界方面具有更高的能力。
