卷积神经网络基于FDG PET图像预测新诊断非小细胞肺癌淋巴结及远处转移潜能
本研究回顾性纳入264例新诊断未治疗的非小细胞肺癌患者,利用18F-FDG PET原发肿瘤图像训练卷积神经网络(CNN),预测淋巴结及远处转移。CNN预测淋巴结阳性的敏感度、特异度和准确率分别为0.74±0.32、0.84±0.16、0.80±0.17;预测远处转移的对应值分别为0.45±0.08、0.79±0.06、0.63±0.05。结论认为CNN对N分期的准确率中等偏高,但可能不足以替代有创淋巴结取样;对远处转移的敏感度较差。
要点
- CNN分析原发肿瘤FDG PET图像预测淋巴结阳性的准确率为0.80±0.17。
- CNN预测远处转移的敏感度仅0.45±0.08,特异度0.79±0.06。
- 作者认为CNN对N分期的准确率可能不足以排除有创淋巴结取样。
核心结论
- CNN分析未治疗NSCLC的原发肿瘤分割PET图像,对N分期的预测准确率中等偏高,但可能不足以替代有创淋巴结取样。
- CNN预测远处转移的敏感度较差,特异度中等偏高。
研究设计与样本
- 单中心回顾性研究,连续纳入新诊断、未治疗的NSCLC患者264例,随访中位25.2个月(范围6-43个月)。
- PET图像经局部图像特征提取软件分割,数据增强后用于CNN训练和验证。
- N分期参考标准为有创淋巴结取样或6个月随访影像;远处转移依据随访期间影像(CT或PET/CT)、新可疑病灶组织学及肿瘤科主治医师判定。
诊断标准与关键数值
- CNN预测淋巴结阳性的敏感度0.74±0.32、特异度0.84±0.16、准确率0.80±0.17。
- CNN预测远处转移的敏感度0.45±0.08、特异度0.79±0.06、准确率0.63±0.05。
- N分期可评估者223/264例(84.5%),M分期全部264例可评估。
临床应用与阅片要点
- 作者认为CNN对N分期的准确率可能不足以排除有创淋巴结取样。
- CNN预测远处转移敏感度较差,阅片时不宜单独依据其阴性结果排除远处转移。
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
OBJECTIVE. The purpose of this study was to assess, by analyzing features of the primary tumor with 18F-FDG PET, the utility of deep machine learning with a convolutional neural network (CNN) in predicting the potential of newly diagnosed non-small cell lung cancer (NSCLC) to metastasize to lymph nodes or distant sites. MATERIALS AND METHODS. Consecutively registered patients with newly diagnosed, untreated NSCLC were retrospectively included in a single-center study. PET images were segmented with local image features extraction software, and data were used for CNN training and validation after data augmentation strategies were used. The standard of reference for designation of N category was invasive lymph node sampling or 6-month follow-up imaging. Distant metastases developing during the study follow-up period were assessed by imaging (CT or PET/CT), in tissue obtained from new suspected sites of disease, and according to the treating oncologist's designation. RESULTS. A total of 264 patients with NSCLC participated in follow-up for a median of 25.2 months (range, 6-43 months). N category designations were available for 223 of 264 (84.5%) patients, and M category for all 264. The sensitivity, specificity, and accuracy of CNN for predicting node positivity were 0.74 ± 0.32, 0.84 ± 0.16, and 0.80 ± 0.17. The corresponding values for predicting distant metastases were 0.45 ± 0.08, 0.79 ± 0.06, and 0.63 ± 0.05. CONCLUSION. This study showed that using a CNN to analyze segmented PET images of patients with previously untreated NSCLC can yield moderately high accuracy for designation of N category, although this may be insufficient to preclude invasive lymph node sampling. The sensitivity of the CNN in predicting distant metastases is fairly poor, although specificity is moderately high.
引用
- Tau N, Stundzia A, Yasufuku K, et al. Convolutional Neural Networks in Predicting Nodal and Distant Metastatic Potential of Newly Diagnosed Non-Small Cell Lung Cancer on FDG PET Images. AJR Am J Roentgenol. 2020. PMID: 32348182. doi:10.2214/AJR.19.22346
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。