颈动脉超声横切面斑块分割的深度学习区域特异性评估
本研究基于人群队列VIPVIZA的6年随访横切面颈动脉超声图像,评估六种深度学习模型在斑块分割中的表现。比较全视野分割与基于感兴趣区分割两种方案,发现基于感兴趣区的方法显著提高性能。不同解剖区域最优模型不同,颈动脉分叉处U-Net++ Dice达0.87。
要点
- 横切面斑块分割时,使用动脉中心感兴趣区引导可显著提升分割准确度。
- 颈总动脉区域U-Net最优,颈动脉球部YOLOv8最优,分叉处U-Net++最优。
- 全视野分割时DeepLabV3综合表现最佳,Dice为0.65。
核心结论
- 基于感兴趣区的分割方案显著优于全视野直接分割,解剖引导对提高横切面颈动脉斑块分割性能至关重要。
- 不同解剖区域需匹配不同网络架构,无单一模型在所有区域均表现最优。
- DeepLabV3与Transformer类模型在全视野分割中潜力较大,U-Net类架构在感兴趣区引导下仍高度有效。
研究设计与样本
- 基于人群队列VIPVIZA的6年随访横切面颈动脉超声图像。
- 六种深度学习架构:YOLOv8、U-Net、Attention U-Net、U-Net++、Swin U-Net、DeepLabV3。
- 所有图像经强度归一化和对比度受限自适应直方图均衡化预处理以增强边界可见性。
- 两种分割配置:Case 1全视野直接分割,Case 2以手动标注生成的动脉中心感兴趣区引导分割。
- 三个解剖区域分别评估:颈总动脉、颈动脉球部、颈动脉分叉处。
关键影像表现/征象
- 横切面超声图像中颈动脉斑块表现为血管壁附近的局灶性异常回声区,全视野下边界常不清晰。
- 管腔与斑块边界在对比度受限自适应直方图均衡化处理后显示更清晰。
- 颈动脉球部与分叉处解剖结构复杂,血管走行与管腔形态变化影响分割难度。
诊断标准与关键数值
- 全视野配置(Case 1)中DeepLabV3 Dice最高为0.65,Swin U-Net为0.64,U-Net++为0.62。
- 全视野配置中YOLOv8与Attention U-Net Dice均为0.61。
- 感兴趣区配置(Case 2)中颈总动脉U-Net Dice最高为0.73。
- 感兴趣区配置中颈动脉球部YOLOv8 Dice最高为0.66。
- 感兴趣区配置中颈动脉分叉处U-Net++ Dice最高为0.87,DeepLabV3为0.86,Attention U-Net为0.84。
临床应用与阅片要点
- 日常阅片时对颈动脉分叉处与球部的斑块评估应比颈总动脉更谨慎,因其分割难度更高。
- 采用颈动脉横切面筛查斑块时,优先先定位血管中心再对周围区域进行斑块判读,模拟感兴趣区引导思路。
- 自动分割结果中分叉处与球部区域需人工复核,全视野直接分割在这些区域精度有限。
局限性
- 针对特定人群队列VIPVIZA随访数据,结果的跨人群泛化性尚不明确。
- 感兴趣区的分割结果依赖手动标注生成,实际临床自动化流程中可能缺乏该引导信息。
- 六种模型在不同区域的性能排序不一致,尚无统一的最优架构选择策略。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: Detection of atherosclerotic plaque in the carotid arteries is essential for early cardiovascular risk assessment. While B-mode ultrasound is the standard imaging modality, most deep learning studies focus on longitudinal views of the common carotid artery, with limited investigation of cross-sectional imaging and other clinically relevant regions such as the carotid bulb and split. To the best of our knowledge, this study presents the first region-specific evaluation of plaque segmentation using deep learning models in cross-sectional carotid ultrasound images.
METHODS: Cross-sectional carotid ultrasound images from the 6 y follow-up of the population-based VIPVIZA cohort were analyzed. Two segmentation configurations were investigated: Case 1, where plaque segmentation was performed directly on the full field of view, and Case 2, where segmentation was guided by artery-centered regions of interest (ROIs) derived from manual ground truth annotations. Six deep learning architectures were evaluated: YOLOv8, U-Net, Attention U-Net, U-Net++, Swin U-Net and DeepLabV3. All images were pre-processed using intensity normalization and contrast-limited adaptive histogram equalization to enhance boundary visibility.
RESULTS: In the full field of view configuration (Case 1), DeepLabV3 achieved the highest overall Dice score (0.65), followed by Swin U-Net (Dice = 0.64) and U-Net++ (Dice = 0.62), while YOLOv8 and Attention U-Net showed comparable performance (Dice = 0.61). In the ROI-based configuration (Case 2), U-Net achieved the highest segmentation performance in the common carotid artery (Dice = 0.73), while YOLOv8 achieved the best performance in the carotid bulb (Dice = 0.66). In the carotid split region, U-Net++ achieved the highest Dice score (0.87), followed closely by DeepLabV3 (Dice = 0.86) and Attention U-Net (Dice = 0.84).
CONCLUSION: Region-specific results from this study support the development of automated plaque segmentation in cross-sectional carotid ultrasound imaging. The findings highlight the importance of anatomical guidance and demonstrate that ROI-based approaches substantially improve segmentation performance. DeepLabV3 and transformer-based models show strong potential in full-image settings, while U-Net-based architectures remain highly effective at ROI-based segmentation.
引用
- Saboori, Nygård, Jonzén, et al. Region-Specific Evaluation of Plaque Segmentation in Cross-sectional Projections of Carotid Ultrasound Images Using Deep Learning Models in a Sub-clinical Atherosclerosis Cohort. Ultrasound Med Biol. 2026. PMID: 42379905. doi:10.1016/j.ultrasmedbio.2026.05.029
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。