基于专用深度学习方法的CT血管成像中健康与病变主动脉的自动分割与定量
回顾性纳入191例2015至2018年主动脉CTA,训练3D U-Net分割主动脉并与人工分割比较;测试组41例DSC 0.95、MSD 0.76,定量测量ICC>0.9(p<0.05),作者认为自动分割可行且即使在血管结构因病改变时也能准确量化主动脉管腔。
要点
- 3D U-Net自动分割主动脉与人工分割高度一致,测试组DSC 0.95、MSD 0.76。
- 八个解剖标志点及动脉瘤最大面积处的直径与面积定量ICC均>0.9(p<0.05)。
- 升主动脉最大径绝对误差最大为0.8±1.5 mm,腹腔干处面积绝对误差为-30.0±81.6 mm²。
核心结论
- 使用深度学习算法在CTA数据上自动分割主动脉是可行的,并且即使血管结构因病改变,也能准确量化主动脉管腔。
研究设计与样本
- 回顾性研究,从影像存档中识别2015至2018年191例患者(68.1±14岁,128例男性)的主动脉CTA,由两名研究者手动分割,按7:1:2分为训练、验证和测试组,测试组41例比较手动与自动分割,统计包括误差计算、组内相关系数和Bland-Altman分析。
关键影像表现/征象
- 自动与手动分割的Dice相似系数为0.95 [0.94; 0.95],平均表面距离为0.76 [0.06; 0.99],Hausdorff表面距离为8.00 [4.47; 10.00]。
- 最大绝对误差位于升主动脉最大径(0.8±1.5 mm)和腹腔干处面积(-30.0±81.6 mm²)。
- 动脉瘤(n=14)处最大径绝对误差为-0.5±2.3 mm,有效直径绝对误差为0.3±1.6 mm,面积绝对误差为64.9±114.9 mm²。
诊断标准与关键数值
- Dice相似系数0.95 [0.94; 0.95]、平均表面距离0.76 [0.06; 0.99]提示两种分割高度一致。
- 定量测量(最大径、有效直径、面积)的组内相关系数>0.9(p<0.05),提示一致性极好。
临床应用与阅片要点
- 该算法可在CTA上自动分割主动脉,即使血管结构因病改变,量化结果也多在临床可接受误差范围内。
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
OBJECTIVES: To develop and validate a deep learning-based algorithm for segmenting and quantifying the physiological and diseased aorta in computed tomography angiographies.
METHODS: CTA exams of the aorta of 191 patients (68.1 ± 14 years, 128 male), performed between 2015 and 2018, were retrospectively identified from our imaging archive and manually segmented by two investigators. A 3D U-Net model was trained on the data, which was divided into a training, a validation, and a test group at a ratio of 7:1:2. Cases in the test group (n = 41) were evaluated to compare manual and automatic segmentations. Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff surface distance (HSD) were extracted. Maximum diameter, effective diameter, and area were quantified and compared between both segmentations at eight anatomical landmarks, and at the maximum area of an aneurysms if present (n = 14). Statistics included error calculation, intraclass correlation coefficient, and Bland-Altman analysis.
RESULTS: A DSC of 0.95 [0.94; 0.95] and an MSD of 0.76 [0.06; 0.99] indicated close agreement between segmentations. HSD was 8.00 [4.47; 10.00]. The largest absolute errors were found in the ascending aorta with 0.8 ± 1.5 mm for maximum diameter and at the coeliac trunk with - 30.0 ± 81.6 mm2 for area. Results for absolute errors in aneurysms were - 0.5 ± 2.3 mm for maximum diameter, 0.3 ± 1.6 mm for effective diameter, and 64.9 ± 114.9 mm2 for area. ICC showed excellent agreement (> 0.9; p < 0.05) between quantitative measurements.
CONCLUSIONS: Automated segmentation of the aorta on CTA data using a deep learning algorithm is feasible and allows for accurate quantification of the aortic lumen even if the vascular architecture is altered by disease.
KEY POINTS: • A deep learning-based algorithm can automatically segment the aorta, mostly within acceptable margins of error, even if the vascular architecture is altered by disease. • Quantifications performed in the segmentations were mostly within clinically acceptable limits, even in pathologically altered segments of the aorta.
引用
- Sieren MM, Widmann C, Weiss N, et al. Automated segmentation and quantification of the healthy and diseased aorta in CT angiographies using a dedicated deep learning approach. Eur Radiol. 2021. PMID: 34170365. doi:10.1007/s00330-021-08130-2
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。