在低剂量CT肺癌基线筛查数据集中使用两种不同结节分割算法进行结节体积分类的比较
研究在NELCIN-B3低剂量CT肺癌筛查队列的300名参与者基线扫描中,由两名放射科医师独立使用两种软件算法(Syngo.via VB30A与AVIEW v1.1.39.14)按NELSON2.0方案进行结节体积分类,软件间一致性几乎完美(κ=0.88),两种算法在参与者/扫描水平上表现相当,作者认为需进一步研究在其他低剂量CT肺癌筛查项目中确认结果。
要点
- 按NELSON2.0方案,实性成分≥100 mm3的结节分类为不确定-阳性,其余结节分类为阴性。
- 两种软件算法间一致性几乎完美,κ=0.88(95%CI:0.83-0.93)。
- 读者1/软件A的阴性预测值为99.6%(95%CI:98.9%-100.0%),读者2/软件B为98.9%(95%CI:97.7%-100.0%)。
核心结论
- 两种软件算法(Syngo.via VB30A和AVIEW v1.1.39.14)在参与者/扫描水平的肺结节体积分类上表现相当;需进一步研究在其他低剂量CT肺癌筛查项目中确认结果。
研究设计与样本
- 研究纳入2017年6月至2018年7月连续NELCIN-B3参与者的合格低剂量CT基线扫描,共300名参与者;由读者1使用软件A(Syngo.via VB30A)、读者2使用软件B(AVIEW v1.1.39.14)独立评估,分类不一致时由三名资深放射科医师共识解决,并以此作为参考标准识别阳性误分类和阴性误分类。
诊断标准与关键数值
- 依据NELSON2.0方案,实性成分≥100 mm3的结节分类为不确定-阳性,所有其他结节分类为阴性;软件间一致性κ=0.88(95%CI:0.83-0.93);读者1/软件A阴性预测值99.6%(95%CI:98.9%-100.0%),读者2/软件B阴性预测值98.9%(95%CI:97.7%-100.0%)。
临床应用与阅片要点
- 作者结论认为两种软件算法在参与者/扫描水平的肺结节体积分类上表现相当,并指出需进一步研究在其他低剂量CT肺癌筛查项目中确认结果。
局限性
- 原文结论指出需进一步研究在其他低剂量CT肺癌筛查项目中确认结果。
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
OBJECTIVES: To investigate the performance of two segmentation algorithms for nodule volumetric classification at participant/scan level in the NELCIN-B3 cohort (Netherlands and China Big-3), a lung cancer screening program (LCS) using low-dose CT (LDCT).
METHODS: Baseline scans with qualified LDCT images from consecutive NELCIN-B3 participants were included from June 2017 to July 2018. Performance of two software algorithms were independently evaluated by two radiologists: software A (Syngo.via VB30A) by reader 1 and software B (AVIEW v1.1.39.14) by reader 2. According to the NELSON2.0 protocol, nodules with a solid component ≥ 100 mm3 were classified as indeterminate-positive, while all other nodules were classified as negative. Disagreements in classification were resolved by consensus with three senior radiologists. These results served as a reference standard for identifying positive misclassifications (PM) and negative misclassifications (NM).
RESULTS: In total, 300 participants were evaluated comprising 159 women (53.0 %) and 193 (64.3 %) never smokers, with a mean ± standard deviation age of 61.2 ± 7.1 years. There were disagreements in 17 cases: in 11 (11/300, 3.7 %), this was due to differences in nodule selection and nodule type classification between readers; and in 6 (6/300, 2.0 %), this was due to variations in nodule volume metrics between algorithms. Inter-software agreement was almost perfect (κ = 0.88 [95 %CI: 0.83-0.93]). In the consensus read, reader 1/software A generated 12 misclassifications (11 PM, 1 NM), giving a negative predictive value of 99.6 % (95 % CI: 98.9 %-100.0 %). Reader 2/software B generated 5 misclassifications (2 PM, 3 NM), giving a negative predictive value of 98.9 % (95 % CI: 97.7 %-100.0 %).
CONCLUSION: Two software algorithms (Syngo.via VB30A and AVIEW v1.1.39.14) showed comparable performance for lung nodule volumetric classification at participant/scan level. Further research is needed to confirm the results in other LDCT LCS programs.
引用
- Mao Y, Lancaster HL, Heuvelmans MA, et al. Comparison of nodule volumetric classification by using two different nodule segmentation algorithms in an LDCT lung cancer baseline screening dataset. Eur J Radiol. 2025. PMID: 40684711. doi:10.1016/j.ejrad.2025.112290
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。