基于深度学习的颈动脉斑块B型超声图像分割
本研究用改良U-Net从纵向颈动脉超声图像自动分割斑块以生成总斑块面积(TPA),共纳入144例患者的510个斑块,采用蒙特卡洛交叉验证按2/3与1/3随机划分训练与测试,两个观察者分别手动勾画作为参考标准。两个模型分割与手动分割的Pearson相关系数分别为r=0.989(p<0.0001)和r=0.987(p<0.0001),平均TPA差异分别为0.05±7.13 mm²(95%CI 14.02-13.02 mm²)和0.8±8.7 mm²(17.85-16.25 mm²),单个斑块分割时间仅8.3±3.1 ms,提示该方法可测量TPA并监测颈动脉粥样硬化的进展和消退。
要点
- 改良U-Net可从纵向颈动脉超声图像自动分割斑块并生成总斑块面积(TPA)。
- 两个模型自动分割与手动分割的TPA高度一致(r=0.989、r=0.987,均p<0.0001)。
- 单个斑块分割平均耗时仅8.3±3.1 ms,有望替代耗时的手动勾画。
核心结论
- 基于深度学习的自动斑块分割方法具有足够准确性且计算时间短,算法与手动TPA测量高度一致,提示该方法可用于测量TPA并监测颈动脉粥样硬化的进展和消退。
研究设计与样本
- 使用改良U-Net训练分割模型生成TPA,共纳入144例患者的510个斑块,采用蒙特卡洛交叉验证将数据集随机按2/3与1/3分为训练集与测试集,由两名受过训练的观察者分别手动勾画510个斑块作为参考标准,并据此训练两个U-Net模型(M1和M2)。
诊断标准与关键数值
- 两个模型自动分割与对应手动分割的Pearson相关系数分别为r=0.989(p<0.0001)和r=0.987(p<0.0001);U-Net与手动分割的平均TPA差异分别为0.05±7.13 mm²(95%CI 14.02-13.02 mm²)和0.8±8.7 mm²(95%CI 17.85-16.25 mm²);本数据集TPA范围为4.7至312.8 mm²;单个斑块平均分割时间8.3±3.1 ms。
临床应用与阅片要点
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
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
Carotid ultrasound measurement of total plaque area (TPA) provides a method for quantifying carotid plaque burden and monitoring changes in carotid atherosclerosis in response to medical treatment. Plaque boundary segmentation is required to generate the TPA measurement; however, training of observers and manual delineation are time consuming. Thus, our objective was to develop an automated plaque segmentation method to generate TPA from longitudinal carotid ultrasound images. In this study, a deep learning-based method, modified U-Net, was used to train the segmentation model and generate TPA measurement. A total of 510 plaques from 144 patients were used in our study, where the Monte Carlo cross-validation was used by randomly splitting the data set into 2/3 and 1/3 for training and testing. Two observers were trained to manually delineate the 510 plaques separately, which were used as the ground-truth references. Two U-Net models (M1 and M2) were trained using the two different ground-truth data sets from the two observers to evaluate the accuracy, variability and sensitivity on the ground-truth data sets used for training our method. The results of the algorithm segmentations of the two models yielded strong agreement with the two manual segmentations with the Pearson correlation coefficient r = 0.989 (p < 0.0001) and r = 0.987 (p < 0.0001). Comparison of the U-Net and manual segmentations resulted in mean TPA differences of 0.05 ± 7.13 mm2 (95% confidence interval: 14.02-13.02 mm2) and 0.8 ± 8.7 mm2 (17.85-16.25 mm2) for the two models, which are small compared with the TPA range in our data set from 4.7 to 312.8 mm2. Furthermore, the mean time to segment a plaque was only 8.3 ± 3.1 ms. The presented deep learning-based method described has sufficient accuracy with a short computation time and exhibits high agreement between the algorithm and manual TPA measurements, suggesting that the method could be used to measure TPA and to monitor the progression and regression of carotid atherosclerosis.
引用
- Zhou R, Azarpazhooh MR, Spence JD, et al. Deep Learning-Based Carotid Plaque Segmentation from B-Mode Ultrasound Images. Ultrasound Med Biol. 2021. PMID: 34217560. doi:10.1016/j.ultrasmedbio.2021.05.023
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。