深度学习用于CT图像上偶发亚厘米肺结节恶性风险估计
研究基于华西医院CT图像训练四种深度学习模型,用于偶发亚厘米肺结节恶性风险估计,并在内部测试集和三个外部队列验证。测试集中,基于基线结节框和基线加随访结节框的模型AUC分别为0.928和0.942,随访模型表现与高年资呼吸科医生相当。模型仅利用结节信息即可有效预测恶性,可能辅助临床优化随访建议。
要点
- 基于基线结节框的模型在测试集AUC为0.928,基于基线加随访结节框的模型AUC为0.942。
- 基线结节框模型在三个外部数据集AUC分别为0.808、0.848和0.939。
- 测试集中随访模型表现与高年资呼吸科医生相当(准确率90.0%)。
核心结论
- 仅挖掘结节信息的深度学习算法可有效预测偶发亚厘米肺结节的恶性。
研究设计与样本
- 研究论文;训练集1822个结节(981个恶性),测试集806个(416个恶性),外部集共357个(253个恶性);来自华西医院,内部测试并在三个队列外部验证;四种模型分别学习基线全肺区域、基线结节所在图像块、基线结节框、基线加随访结节框的3D深度特征;所有感兴趣区自动分割,结节框额外人工核对。
诊断标准与关键数值
- 测试集AUC:基线全肺模型0.754,基线图像块模型0.855,基线结节框模型0.928,基线加随访结节框模型0.942;外部验证(无随访图像)时结节框模型在三个外部数据集AUC分别为0.808、0.848、0.939;测试集准确率:住院医师67.0%,初级医师82.5%,高级医师90.0%;测试集诊断准确率:基线结节框模型86.4%,基线加随访结节框模型90.4%。
临床应用与阅片要点
- 作者认为所建立的模型可能有助于支持临床医生在日常临床实践中优化亚厘米肺结节的随访建议,并可能减少不必要的诊断干预和诊断延迟。
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 establish deep learning models for malignancy risk estimation of sub-centimeter pulmonary nodules incidentally detected by chest CT and managed in clinical settings.
MATERIALS AND METHODS: Four deep learning models were trained using CT images of sub-centimeter pulmonary nodules from West China Hospital, internally tested, and externally validated on three cohorts. The four models respectively learned 3D deep features from the baseline whole lung region, baseline image patch where the nodule located, baseline nodule box, and baseline plus follow-up nodule boxes. All regions of interest were automatically segmented except that the nodule boxes were additionally manually checked. The performance of models was compared with each other and that of three respiratory clinicians.
RESULTS: There were 1822 nodules (981 malignant) in the training set, 806 (416 malignant) in the testing set, and 357 (253 malignant) totally in the external sets. The area under the curve (AUC) in the testing set was 0.754, 0.855, 0.928, and 0.942, respectively, for models derived from baseline whole lung, image patch, nodule box, and the baseline plus follow-up nodule boxes. When baseline models externally validated (follow-up images not available), the nodule-box model outperformed the other two with AUC being 0.808, 0.848, and 0.939 respectively in the three external datasets. The resident, junior, and senior clinicians achieved an accuracy of 67.0%, 82.5%, and 90.0%, respectively, in the testing set. The follow-up model performed comparably to the senior clinician.
CONCLUSION: The deep learning algorithms solely mining nodule information can efficiently predict malignancy of incidental sub-centimeter pulmonary nodules.
CLINICAL RELEVANCE STATEMENT: The established models may be valuable for supporting clinicians in routine clinical practice, potentially reducing the number of unnecessary examinations and also delays in diagnosis.
KEY POINTS: • According to different regions of interest, four deep learning models were developed and compared to evaluate the malignancy of sub-centimeter pulmonary nodules by CT images. • The models derived from baseline nodule box or baseline plus follow-up nodule boxes demonstrated sufficient diagnostic accuracy (86.4% and 90.4% in the testing set), outperforming the respiratory resident (67.0%) and junior clinician (82.5%). • The proposed deep learning methods may aid clinicians in optimizing follow-up recommendations for sub-centimeter pulmonary nodules and may lead to fewer unnecessary diagnostic interventions.
引用
- Zhang R, Wei Y, Wang D, et al. Deep learning for malignancy risk estimation of incidental sub-centimeter pulmonary nodules on CT images. Eur Radiol. 2023. PMID: 38114849. doi:10.1007/s00330-023-10518-1
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。