人工智能与人工分割评估18F-氟化钠PET/CT全心动脉粥样硬化负荷的头对头比较
本研究在29名健康志愿者和20名心绞痛患者的18F-氟化钠PET/CT扫描中,比较卷积神经网络(CNN)自动心脏分割与人工分割评估全心动脉粥样硬化负荷的表现。结果显示两种方法所得Vol、SUVmean、SUVmax、SUVtotal均无显著差异,CNN方法耗时约1分钟而人工分割约30分钟,提示AI分割可作为更快、可重复性更高的替代方案。
要点
- CNN自动分割所得Vol、SUVmean、SUVmax、SUVtotal与人工分割结果无显著差异。
- CNN分割耗时约1分钟,人工分割通常需30分钟。
- AI分割同一扫描重复性为100%,人工再分割最大偏差为0%至1%。
核心结论
- CNN方法更快,所得Vol、SUVmean、SUVmax和SUVtotal与人工分割相当,可作为心脏人工分割的更可重复、更快速的替代方案。
研究设计与样本
- 采用训练好的卷积神经网络(CNN)对29名健康志愿者和20名心绞痛患者的18F-氟化钠PET/CT扫描进行心脏分割,并与人工分割头对头比较。
- 用Bland-Altman一致性界限分析分割体积(Vol)及SUVmean、SUVmax、SUVtotal;对25例随机选取的扫描进行人工再分割以评估重复性与可重复性。
主要发现
- 人工分割与CNN分割的均值(±SD)分别为:Vol 617.65±154.99 mL vs 625.26±153.55 mL(P=.21),SUVmean 0.69±0.15 vs 0.69±0.15(P=.26),SUVmax 2.68±0.86 vs 2.77±1.05(P=.34),SUVtotal 425.51±138.93 vs 427.91±132.68(P=.62)。
- 四项参数的一致性界限分别为-89.42至74.2、-0.02至0.02、-1.52至1.32、-68.02至63.21。
- 人工分割通常耗时30分钟,CNN方法约1分钟;AI分割同一扫描的重复性为100%。
- 人工再分割四项参数的最大偏差:同一操作者为0%至0.5%,不同操作者为0%至1%。
关键数值与推荐
- 人工分割与CNN分割的Vol、SUVmean、SUVmax、SUVtotal组间P值分别为.21、.26、.34、.62。
- Bland-Altman一致性界限:Vol -89.42至74.2 mL,SUVmean -0.02至0.02,SUVmax -1.52至1.32,SUVtotal -68.02至63.21。
- 人工分割耗时通常30分钟,CNN方法约1分钟;AI分割重复性100%。
- 人工再分割最大偏差同一操作者0%至0.5%,不同操作者0%至1%。
临床怎么用
- 在18F-氟化钠PET/CT评估全心动脉粥样硬化负荷时,可考虑用CNN自动分割替代耗时的人工心脏分割。
- AI分割可提升工作效率(约1分钟 vs 30分钟)并保持与人工分割相当的分割体积与摄取值。
- AI分割同一扫描重复性为100%,有助于减少操作者间差异。
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)。
原文
BACKGROUND: Artificial intelligence (AI) is known to provide effective means to accelerate and facilitate clinical and research processes. So in this study it was aimed to compare a AI-based method for cardiac segmentation in positron emission tomography/computed tomography (PET/CT) scans with manual segmentation to assess global cardiac atherosclerosis burden. METHODS: A trained convolutional neural network (CNN) was used for cardiac segmentation in 18F-sodium fluoride PET/CT scans of 29 healthy volunteers and 20 angina pectoris patients and compared with manual segmentation. Parameters for segmented volume (Vol) and mean, maximal, and total standardized uptake values (SUVmean, SUVmax, SUVtotal) were analyzed by Bland-Altman Limits of Agreement. Repeatability with AI-based assessment of the same scans is 100%. Repeatability (same conditions, same operator) and reproducibility (same conditions, two different operators) of manual segmentation was examined by re-segmentation in 25 randomly selected scans. RESULTS: Mean (± SD) values with manual vs. CNN-based segmentation were Vol 617.65 ± 154.99 mL vs 625.26 ± 153.55 mL (P = .21), SUVmean 0.69 ± 0.15 vs 0.69 ± 0.15 (P = .26), SUVmax 2.68 ± 0.86 vs 2.77 ± 1.05 (P = .34), and SUVtotal 425.51 ± 138.93 vs 427.91 ± 132.68 (P = .62). Limits of agreement were - 89.42 to 74.2, - 0.02 to 0.02, - 1.52 to 1.32, and - 68.02 to 63.21, respectively. Manual segmentation lasted typically 30 minutes vs about one minute with the CNN-based approach. The maximal deviation at manual re-segmentation was for the four parameters 0% to 0.5% with the same and 0% to 1% with different operators. CONCLUSION: The CNN-based method was faster and provided values for Vol, SUVmean, SUVmax, and SUVtotal comparable to the manually obtained ones. This AI-based segmentation approach appears to offer a more reproducible and much faster substitute for slow and cumbersome manual segmentation of the heart.
引用
- Piri R, Edenbrandt L, Larsson M, et al. "Global" cardiac atherosclerotic burden assessed by artificial intelligence-based versus manual segmentation in 18F-sodium fluoride PET/CT scans: Head-to-head comparison. J Nucl Cardiol. 2021. PMID: 34386861. doi:10.1007/s12350-021-02758-9
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。