基于[18F]FDG-PET/CT深度学习全自动检测肺癌病理性纵隔淋巴结
该研究回顾性分析134例患者全身[18F]FDG-PET/CT扫描,采用U-Net定位候选区域并用3D CNN分类,实现病理性纵隔淋巴结自动检测。在第一台扫描仪测试集上敏感度0.87(95%CI 0.74-0.94),假阳性0.41/患者,与专家表现相当;在第二台不同扫描仪数据上,无迁移学习敏感度0.53,迁移学习后升至0.88。
要点
- 模型在第一台扫描仪测试集敏感度0.87,假阳性0.41/患者,与专家相当。
- 跨扫描仪无迁移学习敏感度降至0.53,迁移学习后恢复至0.88。
- 首次实现从全身[18F]FDG-PET/CT直接定位病理性纵隔淋巴结。
核心结论
- 同扫描仪数据上模型性能与专家相当,迁移学习后可应用于不同扫描仪数据。
研究设计与样本
- 回顾性分析134例患者全身[18F]FDG-PET/CT扫描(Philips Gemini TF),自动定位胸部后以U-Net识别候选区域,再分割为重叠3D cubes用3D CNN预测阳性或阴性。
- 第二队列71例来自不同新扫描仪(GE Discovery MI),测试模型有无迁移学习的性能。
主要发现
- 第一台扫描仪测试集敏感度0.87(95%CI 0.74-0.94),假阳性0.41/患者(95%CI 0.22-0.71),与专家表现相当。
- 第二台扫描仪测试集无迁移学习敏感度0.53(95%CI 0.35-0.70),假阳性0.24/患者(95%CI 0.10-0.49)。
- 第二台扫描仪测试集迁移学习后敏感度0.88(95%CI 0.73-0.97),假阳性0.69/患者(95%CI 0.43-1.04)。
临床怎么用
- 该模型可在同扫描仪数据上辅助自动检测病理性纵隔淋巴结,跨扫描仪应用时需迁移学习。
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: The identification of pathological mediastinal lymph nodes is an important step in the staging of lung cancer, with the presence of metastases significantly affecting survival rates. Nodes are currently identified by a physician, but this process is time-consuming and prone to errors. In this paper, we investigate the use of artificial intelligence-based methods to increase the accuracy and consistency of this process. METHODS: Whole-body 18F-labelled fluoro-2-deoxyglucose ([18F]FDG) positron emission tomography/computed tomography ([18F]FDG-PET/CT) scans (Philips Gemini TF) from 134 patients were retrospectively analysed. The thorax was automatically located, and then slices were fed into a U-Net to identify candidate regions. These regions were split into overlapping 3D cubes, which were individually predicted as positive or negative using a 3D CNN. From these predictions, pathological mediastinal nodes could be identified. A second cohort of 71 patients was then acquired from a different, newer scanner (GE Discovery MI), and the performance of the model on this dataset was tested with and without transfer learning. RESULTS: On the test set from the first scanner, our model achieved a sensitivity of 0.87 (95% confidence intervals [0.74, 0.94]) with 0.41 [0.22, 0.71] false positives/patient. This was comparable to the performance of an expert. Without transfer learning, on the test set from the second scanner, the corresponding results were 0.53 [0.35, 0.70] and 0.24 [0.10, 0.49], respectively. With transfer learning, these metrics were 0.88 [0.73, 0.97] and 0.69 [0.43, 1.04], respectively. CONCLUSION: Model performance was comparable to that of an expert on data from the same scanner. With transfer learning, the model can be applied to data from a different scanner. To our knowledge it is the first study of its kind to go directly from whole-body [18F]FDG-PET/CT scans to pathological mediastinal lymph node localisation.
引用
- Wallis D, Soussan M, Lacroix M, et al. An [18F]FDG-PET/CT deep learning method for fully automated detection of pathological mediastinal lymph nodes in lung cancer patients. Eur J Nucl Med Mol Imaging. 2021. PMID: 34519888. doi:10.1007/s00259-021-05513-x
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。