Hirano Gakuto, Teramoto Atsushi, Takai Hiroji, Sasaki Yutaka, Sugimoto Keiko, Matsumoto Shoji, Saito Kuniaki, Fujita Hiroshi
Graduate School of Health Sciences, Fujita Health University, Toyoake, Japan.
Canon Medical Systems Corporation, Otawara, Japan.
J Med Ultrason (2001). 2025 Apr 17. doi: 10.1007/s10396-025-01522-7.
Carotid plaque is a major risk factor for cerebral infarction. Ultrasonography (US) is extensively used for screening carotid plaque, but US images contain more noise than those of computed tomography and magnetic resonance imaging, and the edges of the plaque regions are unclear. In addition, B-mode echogenicity evaluation, which is important for plaque risk assessment, has challenges involving the subjectivity of the evaluator. Although previous studies on carotid plaque assessment have included plaque segmentation, most studies involved manual operations. In this study, we propose an automated scheme of plaque classification based on segmentation in carotid US images using the transformer approach, to resolve the issues of previous studies and to perform plaque echogenicity classification.
The B-mode video captured in the long-axis cross-section was converted to still images, and region extraction and echogenicity classification were performed using TransUNet. The results of the TransUNet output and US images were fed into the Vision Transformer (ViT) for classification into hypoechoic or isoechoic-hyperechoic plaques.
The Dice index, which indicates the accuracy of plaque region extraction, was 0.592. The Dice indices by echogenicity were 0.200, 0.493, and 0.542 for the hypoechoic, isoechoic, and hyperechoic regions, respectively. The balanced accuracy, which indicates the classification accuracy, was 79.6%. The correct classification rate for high-risk hypoechoic plaques was 95.2%.
These results suggest that the proposed method is useful for evaluating the echogenicity classification of carotid artery plaques.
颈动脉斑块是脑梗死的主要危险因素。超声检查（US）广泛用于筛查颈动脉斑块，但US图像比计算机断层扫描和磁共振成像的图像包含更多噪声，且斑块区域的边缘不清楚。此外，对斑块风险评估很重要的B模式回声性评估存在评估者主观性的挑战。尽管先前关于颈动脉斑块评估的研究包括斑块分割，但大多数研究涉及手动操作。在本研究中，我们提出了一种基于变压器方法对颈动脉US图像进行分割的斑块分类自动化方案，以解决先前研究的问题并进行斑块回声性分类。
将长轴横截面中捕获的B模式视频转换为静态图像，并使用TransUNet进行区域提取和回声性分类。将TransUNet输出的结果和US图像输入视觉变压器（ViT），以分类为低回声或等回声 - 高回声斑块。
表示斑块区域提取准确性的Dice指数为0.592。低回声、等回声和高回声区域的回声性Dice指数分别为0.200、0.493和0.542。表示分类准确性的平衡准确率为79.6%。高危低回声斑块的正确分类率为95.2%。
这些结果表明，所提出的方法可用于评估颈动脉斑块的回声性分类。
