基于小数据集训练的UNet++集成算法自动测量颈动脉血管壁体积
本研究开发了基于小数据集(5个数据集,共30名参与者)训练的UNet++集成算法,用于自动分割颈动脉超声图像中的中膜-外膜边界(MAB)和管腔-内膜边界(LIB),并量化血管壁体积(VWV)。在100名临床诊断冠心病并参与多中心CAIN试验的参与者中测试,算法VWV测量与手动分割相关(r=0.763-0.795,p<0.001),CoV为8.89%,且30人训练集的性能与150人训练集的U-Net和Voxel-FCN相似,表明小数据集训练可提供准确可重复的颈动脉VWV测量。
要点
- UNet++集成算法仅需30例训练数据即可自动分割颈动脉MAB和LIB并测量VWV。
- 算法与手动分割的VWV相关系数为0.763-0.795,重复性CoV为8.89%。
- 小数据训练性能与大数据训练的U-Net及Voxel-FCN相当,支持临床研究应用。
关键影像表现/征象
- 算法对MAB的DSC为91.07%-91.56%,ASSD为0.10-0.11 mm。
- 算法对LIB的DSC为87.53%-89.44%,ASSD为0.33-0.39 mm。
- 算法VWV测量与手动分割的Pearson相关系数r=0.763-0.795(p<0.001)。
- VWV的变异系数(CoV)为8.89%。
- 30人训练的UNet++集成性能与150人训练的U-Net和Voxel-FCN相似。
诊断标准与关键数值
- 分割准确性评价指标包括Dice相似系数(DSC)和平均对称表面距离(ASSD),对应对象为MAB和LIB。
- 一致性评价使用Pearson相关系数r、Bland-Altman图和变异系数CoV,对应对象为算法与手动分割的VWV测量。
临床应用与阅片要点
- 可基于小样本训练实现颈动脉VWV自动测量,减少手动分割工作量。
- 测量结果与手动分割相关性好、重复性可接受,可用于研究或临床试验中的动脉粥样硬化进展监测。
- 需注意训练数据来自5个小数据集,临床推广前应验证泛化性。
局限性
- 训练数据来自5个小数据集共30名参与者,样本量小。
- 测试集为临床诊断冠心病并参与CAIN试验的100名参与者,可能存在选择偏倚。
- 未报告多中心外部验证的详细分层结果。
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
Vessel wall volume (VWV) is a 3-D ultrasound measurement for the assessment of therapy in patients with carotid atherosclerosis. Deep learning can be used to segment the media-adventitia boundary (MAB) and lumen-intima boundary (LIB) and to quantify VWV automatically; however, it typically requires large training data sets with expert manual segmentation, which are difficult to obtain. In this study, a UNet++ ensemble approach was developed for automated VWV measurement, trained on five small data sets (n = 30 participants) and tested on 100 participants with clinically diagnosed coronary artery disease enrolled in a multicenter CAIN trial. The Dice similarity coefficient (DSC), average symmetric surface distance (ASSD), Pearson correlation coefficient (r), Bland-Altman plots and coefficient of variation (CoV) were used to evaluate algorithm segmentation accuracy, agreement and reproducibility. The UNet++ ensemble yielded DSCs of 91.07%-91.56% and 87.53%-89.44% and ASSDs of 0.10-0.11 mm and 0.33-0.39 mm for the MAB and LIB, respectively; the algorithm VWV measurements were correlated (r = 0.763-0.795, p < 0.001) with manual segmentations, and the CoV for VWV was 8.89%. In addition, the UNet++ ensemble trained on 30 participants achieved a performance similar to that of U-Net and Voxel-FCN trained on 150 participants. These results suggest that our approach could provide accurate and reproducible carotid VWV measurements using relatively small training data sets, supporting deep learning applications for monitoring atherosclerosis progression in research and clinical trials.
引用
- Zhou, Guo, Azarpazhooh, et al. Carotid Vessel-Wall-Volume Ultrasound Measurement via a UNet++ Ensemble Algorithm Trained on Small Data Sets. Ultrasound Med Biol. 2023. PMID: 36642588. doi:10.1016/j.ultrasmedbio.2022.12.005
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。