基于CT纹理分析的列线图用于术前预测cT1N0M0肺腺癌脏层胸膜侵犯:一项外部验证队列研究
研究从两家机构收集含肺结节的胸部CT数据,所有手术切除结节按脏层胸膜侵犯有无进行病理分类,由人工智能软件自动分割并提取CT纹理特征,按机构分为训练队列与外部验证队列,开发并验证预测脏层胸膜侵犯的列线图。共纳入313例患者,其中63例诊断为脏层胸膜侵犯;三维CT长径、偏度、球形度及慢性阻塞性肺疾病为独立预测因子;列线图训练队列C-index为0.890(95%CI 0.867-0.914),外部验证队列为0.864(95%CI 0.817-0.911),校准良好。
要点
- 三维CT长径、偏度、球形度及慢性阻塞性肺疾病是cT1N0M0肺腺癌脏层胸膜侵犯的独立预测因子。
- 基于多变量逻辑回归的列线图训练队列C-index为0.890(95%CI 0.867-0.914),外部验证队列为0.864(95%CI 0.817-0.911)。
- 列线图校准良好,训练队列Brier评分为0.108,外部验证队列为0.100。
核心结论
- 所开发的列线图可计算cT1N0M0肺腺癌患者脏层胸膜侵犯的概率,具有良好的校准度和区分度,有潜力作为临床评估和决策的可靠工具。
研究设计与样本
- 研究从两家机构收集含肺结节的胸部CT数据集,所有手术切除结节按脏层胸膜侵犯有无进行病理分类,由人工智能软件自动分割并提取CT纹理特征,按机构分为训练队列与外部验证队列,开发并验证预测脏层胸膜侵犯的列线图;共纳入313例患者,其中63例诊断为脏层胸膜侵犯。
诊断标准与关键数值
- 多变量逻辑回归确定三维CT长径、偏度、球形度和慢性阻塞性肺疾病为脏层胸膜侵犯的独立预测因子;列线图训练队列C-index为0.890(95%CI 0.867-0.914),外部验证队列为0.864(95%CI 0.817-0.911);训练队列Brier评分为0.108,外部验证队列为0.100。
临床应用与阅片要点
- 原文结论指出列线图有潜力作为临床评估和决策的可靠工具。
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
AIM: To develop a nomogram based on computed tomography (CT) texture analysis for the preoperative prediction of visceral pleural invasion in patients with cT1N0M0 lung adenocarcinoma.
MATERIALS AND METHODS: A dataset of chest CT containing lung nodules was collected from two institutions, and all surgically resected nodules were classified pathologically based on the presence of visceral pleural invasion. Each nodule on the CT image was segmented automatically by artificial-intelligence software and its CT texture features were extracted. The dataset was divided into training and external validation cohorts according to the institution, and a nomogram for predicting visceral pleural invasion was developed and validated.
RESULTS: Of a total of 313 patients enrolled from two independent institutions, 63 were diagnosed with visceral pleural invasion. Three-dimensional (3D) CT long diameter, skewness, and sphericity, and chronic obstructive pulmonary disease were identified as independent predictors for visceral pleural invasion by multivariable logistic regression. The nomogram based on multivariable logistic regression showed great discriminative ability, as indicated by a C-index of 0.890 (95% confidence interval [CI]: 0.867-0.914) and 0.864 (95% CI: 0.817-0.911) for the training and external validation cohorts, respectively. Additionally, calibration of the nomogram revealed good predictive ability, as indicated by the Brier score (0.108 and 0.100 for the training and external validation cohorts, respectively).
CONCLUSIONS: A nomogram was developed that could compute the probability of visceral pleural invasion in patients with cT1N0M0 lung adenocarcinoma with good calibration and discrimination. The nomogram has potential as a reliable tool for clinical evaluation and decision-making.
引用
- Zuo, Li, Peng, et al. CT texture analysis-based nomogram for the preoperative prediction of visceral pleural invasion in cT1N0M0 lung adenocarcinoma: an external validation cohort study. Clin Radiol. 2021. PMID: 34916048. doi:10.1016/j.crad.2021.11.008
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。