肺癌CT脏层胸膜侵犯预测:深度学习模型达到放射科医师水平并可根据临床需求调整敏感度与特异度
本研究回顾性开发并验证基于术前CT的深度学习模型预测早期肺癌脏层胸膜侵犯(VPI)。模型在时间验证集AUC为0.75(95%CI 0.67-0.84),与三位认证放射科医师(AUC 0.73-0.79)相当,且在高特异度区间(90-100%)标准化部分AUC优于医师。模型可通过高敏感度阈值(0.245,敏感度93.8%、特异度31.2%)或高特异度阈值(0.448,敏感度47.9%、特异度86.0%)适应不同临床需求。
要点
- 基于术前CT的深度学习模型预测早期肺癌脏层胸膜侵犯,AUC 0.75(95%CI 0.67-0.84),与认证放射科医师(AUC 0.73-0.79)相当。
- 模型在高特异度范围(90-100%)的标准化部分AUC高于放射科医师(均p<0.05)。
- 模型可通过选择高敏感度阈值(0.245)或高特异度阈值(0.448)来适应临床需求。
核心结论
- 基于术前CT的深度学习模型在预测早期肺癌脏层胸膜侵犯方面表现出放射科医师级性能,并可根据临床需求实现高敏感度或高特异度诊断。
研究设计与样本
- 回顾性研究;数据集1(训练、调参和内部验证)纳入2009至2015年间切除的676例临床IA期肺腺癌患者;数据集2(时间验证)纳入2017至2018年间切除的141例临床I期腺癌患者;开发基于CT的深度学习模型预测VPI,并进行判别与校准验证、观察者性能研究及多变量回归分析。
诊断标准与关键数值
- 模型AUC为0.75(95%CI 0.67-0.84),与认证放射科医师(AUC 0.73-0.79)相当(所有p>0.05)。
- 模型在特异度90-100%范围内的标准化部分AUC高于放射科医师(所有p<0.05)。
- 高敏感度阈值0.245对应敏感度93.8%、特异度31.2%;高特异度阈值0.448对应敏感度47.9%、特异度86.0%。
- 模型输出为VPI的独立预测因子(调整后比值比1.07;95%CI 1.03-1.11;p<0.001)。
临床应用与阅片要点
- 模型诊断性能与认证放射科医师相当,且在高特异度区间表现更优,可用于辅助VPI评估。
- 三位放射科医师中有两位提供了高敏感度(93.8%和97.9%)但非高特异度(48.4%和40.9%)的诊断,提示医师判读倾向于高敏感度。
- 可根据临床需求选择高敏感度阈值(0.245)或高特异度阈值(0.448)来应用模型输出。
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 preoperative CT-based deep learning model for the prediction of visceral pleural invasion (VPI) in early-stage lung cancer.
METHODS: In this retrospective study, dataset 1 (for training, tuning, and internal validation) included 676 patients with clinical stage IA lung adenocarcinomas resected between 2009 and 2015. Dataset 2 (for temporal validation) included 141 patients with clinical stage I adenocarcinomas resected between 2017 and 2018. A CT-based deep learning model was developed for the prediction of VPI and validated in terms of discrimination and calibration. An observer performance study and a multivariable regression analysis were performed.
RESULTS: The area under the receiver operating characteristic curve (AUC) of the model was 0.75 (95% CI, 0.67-0.84), which was comparable to those of board-certified radiologists (AUC, 0.73-0.79; all p > 0.05). The model had a higher standardized partial AUC for a specificity range of 90 to 100% than the radiologists (all p < 0.05). The high sensitivity cutoff (0.245) yielded a sensitivity of 93.8% and a specificity of 31.2%, and the high specificity cutoff (0.448) resulted in a sensitivity of 47.9% and a specificity of 86.0%. Two of the three radiologists provided highly sensitive (93.8% and 97.9%) but not specific (48.4% and 40.9%) diagnoses. The model showed good calibration (p > 0.05), and its output was an independent predictor for VPI (adjusted odds ratio, 1.07; 95% CI, 1.03-1.11; p < 0.001).
CONCLUSIONS: The deep learning model demonstrated a radiologist-level performance. The model could achieve either highly sensitive or highly specific diagnoses depending on clinical needs.
KEY POINTS: • The preoperative CT-based deep learning model demonstrated an expert-level diagnostic performance for the presence of visceral pleural invasion in early-stage lung cancer. • Radiologists had a tendency toward highly sensitive, but not specific diagnoses for the visceral pleural invasion.
引用
- Choi H, Kim H, Hong W, et al. Prediction of visceral pleural invasion in lung cancer on CT: deep learning model achieves a radiologist-level performance with adaptive sensitivity and specificity to clinical needs. Eur Radiol. 2020. PMID: 33125556. doi:10.1007/s00330-020-07431-2
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。