Sybil:基于单次低剂量胸部计算机断层扫描预测未来肺癌风险的已验证深度学习模型
研究开发了仅需单次低剂量CT(LDCT)即可预测个体未来肺癌风险的深度学习模型Sybil,在NLST、MGH和CGMH三个独立数据集上验证,1年肺癌预测AUC分别为0.92、0.86和0.94,6年一致性指数分别为0.75、0.81和0.80,结论认为Sybil能准确预测未来肺癌风险以助力个性化筛查,但需未来研究理解其临床应用。
要点
- Sybil仅需一次LDCT即可预测未来肺癌风险,无需临床数据或放射科医生标注。
- 在NLST、MGH和CGMH外部验证集上,1年肺癌预测AUC分别为0.92、0.86和0.94。
- 6年一致性指数在NLST、MGH和CGMH分别为0.75、0.81和0.80。
核心结论
- Sybil能通过单次LDCT准确预测个体未来肺癌风险,以进一步实现个性化筛查;未来研究需理解Sybil的临床应用。
研究设计与样本
- 研究使用美国国家肺癌筛查试验(NLST)的LDCT开发了深度学习模型Sybil,仅需一次LDCT,无需临床数据或放射科医生标注,可在放射科阅片站后台实时运行。
- Sybil在三个独立数据集上验证:NLST参与者留出的6,282次LDCT、麻省总医院(MGH)的8,821次LDCT、长庚纪念医院(CGMH)的12,280次LDCT(含从不吸烟者等不同吸烟史人群)。
主要发现
- 1年肺癌预测的受试者工作特征曲线下面积:NLST为0.92(95%CI 0.88至0.95),MGH为0.86(95%CI 0.82至0.90),CGMH为0.94(95%CI 0.91至1.00)。
- 6年一致性指数:NLST为0.75(95%CI 0.72至0.78),MGH为0.81(95%CI 0.77至0.85),CGMH为0.80(95%CI 0.75至0.86)。
临床怎么用
- 原文结论指出Sybil能准确预测个体未来肺癌风险以进一步实现个性化筛查,未来研究需理解其临床应用;原文未据此给出具体临床推荐。
局限性
- 原文结论指出未来研究需理解Sybil的临床应用。
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
PURPOSE: Low-dose computed tomography (LDCT) for lung cancer screening is effective, although most eligible people are not being screened. Tools that provide personalized future cancer risk assessment could focus approaches toward those most likely to benefit. We hypothesized that a deep learning model assessing the entire volumetric LDCT data could be built to predict individual risk without requiring additional demographic or clinical data. METHODS: We developed a model called Sybil using LDCTs from the National Lung Screening Trial (NLST). Sybil requires only one LDCT and does not require clinical data or radiologist annotations; it can run in real time in the background on a radiology reading station. Sybil was validated on three independent data sets: a heldout set of 6,282 LDCTs from NLST participants, 8,821 LDCTs from Massachusetts General Hospital (MGH), and 12,280 LDCTs from Chang Gung Memorial Hospital (CGMH, which included people with a range of smoking history including nonsmokers). RESULTS: Sybil achieved area under the receiver-operator curves for lung cancer prediction at 1 year of 0.92 (95% CI, 0.88 to 0.95) on NLST, 0.86 (95% CI, 0.82 to 0.90) on MGH, and 0.94 (95% CI, 0.91 to 1.00) on CGMH external validation sets. Concordance indices over 6 years were 0.75 (95% CI, 0.72 to 0.78), 0.81 (95% CI, 0.77 to 0.85), and 0.80 (95% CI, 0.75 to 0.86) for NLST, MGH, and CGMH, respectively. CONCLUSION: Sybil can accurately predict an individual's future lung cancer risk from a single LDCT scan to further enable personalized screening. Future study is required to understand Sybil's clinical applications. Our model and annotations are publicly available. UNLABELLED: [Media: see text].
引用
- Mikhael PG, Wohlwend J, Yala A, et al. Sybil: A Validated Deep Learning Model to Predict Future Lung Cancer Risk From a Single Low-Dose Chest Computed Tomography. J Clin Oncol. 2023. PMID: 36634294. doi:10.1200/JCO.22.01345
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。