利用序列低剂量CT扫描的影像组学强化学习改善肺癌基线筛查中的早期诊断
本研究从国家肺癌筛查试验中回顾性随机选取1951名参与者,利用其中1404名参与者的序列低剂量CT扫描(随访至3年)训练和验证影像组学强化学习(RRL)模型(S-RRL),并与仅用基线扫描训练的B-RRL模型及Brock模型比较。在547名独立测试集中,S-RRL模型的AUC为0.88(95%CI: 0.85, 0.91),显著高于Brock模型(AUC 0.84,95%CI: 0.81, 0.88,P=0.02)和B-RRL模型(AUC 0.86,95%CI: 0.83, 0.90,P=0.02),且风险分层较Lung CT Screening Reporting and Data System(NRI 0.29,P<0.001)和Brock模型(NRI 0.12,P=0.008)显著改善。
要点
- 序列LDCT影像组学强化学习模型S-RRL在基线筛查中诊断肺癌的AUC为0.88,高于Brock模型和仅用基线扫描的B-RRL模型。
- S-RRL模型较Lung CT Screening Reporting and Data System风险分层NRI为0.29(P<0.001),较Brock模型NRI为0.12(P=0.008)。
- B-RRL模型与Brock模型AUC差异无统计学显著(0.86 vs 0.84,P=0.02为S-RRL与Brock比较,原文未报告B-RRL与Brock直接比较)。
核心结论
- S-RRL模型在基线筛查中展现出较B-RRL模型和临床模型改善肺癌早期诊断和风险分层的潜力。
研究设计与样本
- 回顾性研究,从国家肺癌筛查试验2002年8月至2004年4月间随机选取1951名参与者(女性822名,中位年龄61岁[范围55-74岁];男性1129名,中位年龄62岁[范围55-74岁]),其中1404名参与者(372例肺癌)的2525份可用序列LDCT扫描(随访至3年)用于训练和验证S-RRL模型,547名保留个体(150例肺癌)作为独立测试集评估性能,以AUC和NRI评估模型对筛查检出结节的分类性能。
诊断标准与关键数值
- S-RRL模型在保留基线扫描测试集上AUC为0.88(95%CI: 0.85, 0.91),显著高于Brock模型AUC 0.84(95%CI: 0.81, 0.88),P=0.02。
- S-RRL模型AUC显著高于B-RRL模型AUC 0.86(95%CI: 0.83, 0.90),P=0.02。
- S-RRL模型较Lung CT Screening Reporting and Data System风险分层NRI为0.29(P<0.001)。
- S-RRL模型较Brock模型风险分层NRI为0.12(P=0.008)。
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
Purpose To evaluate the feasibility of leveraging serial low-dose CT (LDCT) scans to develop a radiomics-based reinforcement learning (RRL) model for improving early diagnosis of lung cancer at baseline screening. Materials and Methods In this retrospective study, 1951 participants (female patients, 822; median age, 61 years [range, 55-74 years]) (male patients, 1129; median age, 62 years [range, 55-74 years]) were randomly selected from the National Lung Screening Trial between August 2002 and April 2004. An RRL model using serial LDCT scans (S-RRL) was trained and validated using data from 1404 participants (372 with lung cancer) containing 2525 available serial LDCT scans up to 3 years. A baseline RRL (B-RRL) model was trained with only LDCT scans acquired at baseline screening for comparison. The 547 held-out individuals (150 with lung cancer) were used as an independent test set for performance evaluation. The area under the receiver operating characteristic curve (AUC) and the net reclassification index (NRI) were used to assess the performances of the models in the classification of screen-detected nodules. Results Deployment to the held-out baseline scans showed that the S-RRL model achieved a significantly higher test AUC (0.88 [95% CI: 0.85, 0.91]) than both the Brock model (AUC, 0.84 [95% CI: 0.81, 0.88]; P = .02) and the B-RRL model (AUC, 0.86 [95% CI: 0.83, 0.90]; P = .02). Lung cancer risk stratification was significantly improved by the S-RRL model as compared with Lung CT Screening Reporting and Data System (NRI, 0.29; P < .001) and the Brock model (NRI, 0.12; P = .008). Conclusion The S-RRL model demonstrated the potential to improve early diagnosis and risk stratification for lung cancer at baseline screening as compared with the B-RRL model and clinical models. Keywords: Radiomics-based Reinforcement Learning, Lung Cancer Screening, Low-Dose CT, Machine Learning © RSNA, 2024 Supplemental material is available for this article.
引用
- Wang Y, Zhou C, Ying L, et al. Leveraging Serial Low-Dose CT Scans in Radiomics-based Reinforcement Learning to Improve Early Diagnosis of Lung Cancer at Baseline Screening. Radiol Cardiothorac Imaging. 2024. PMID: 38752718. doi:10.1148/ryct.230196
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。