双示踪剂学习实现68Ga-PSMA-11 PET/CT全身摄取分类与前列腺癌分期
本研究开发卷积神经网络,对173例接受68Ga-PSMA-11 PET/CT检查的前列腺癌患者图像进行可疑摄取灶分类和解剖定位,并评估18F-FDG数据辅助训练的策略。结果显示,加入18F-FDG训练数据可提升分类性能;在测试集中,网络与专家评估在区域淋巴结受累和转移分期上的一致率分别为81%和77%。
要点
- 双示踪剂训练可提升PSMA PET/CT可疑病灶自动分类性能
- 测试集网络与专家评估的M分期一致率为77%
- 区域淋巴结受累识别一致率为81%
核心结论
- 所评估算法在全身68Ga-PSMA-11 PET/CT可疑摄取灶识别和解剖定位上与专家评估具有良好一致性。
- 在PSMA配体数据有限时,使用不同放射性示踪剂的训练样本可提升性能。
研究设计与样本
- 研究纳入173例接受68Ga-PSMA-11 PET/CT检查的受试者,分为开发集121例和测试集52例。
- 训练并评估卷积神经网络,将摄取增高部位分类为可疑或非可疑癌症,并分配解剖位置。
- 评估利用18F-FDG PET/CT图像及专家注释的训练策略,包括迁移学习和将示踪剂类型编码为网络输入的联合训练。
- 按PROMISE miTNM框架评估网络注释与专家注释所分配N期和M期的一致性。
主要发现
- 在开发集中,四折交叉验证显示纳入18F-FDG训练数据改善了分类性能。
- 测试集中,与专家评估相比,使用18F-FDG数据与开发集训练对可疑摄取灶识别的平均精度为80.4%(CI:71.1-87.8)。
- 测试集中,可疑发现解剖位置分类准确率为77%(CI:70.0-83.4)。
- 测试集中,区域淋巴结受累识别一致率为81%,转移分期识别一致率为77%。
临床怎么用
- 该算法有望辅助全身68Ga-PSMA-11 PET/CT中可疑病灶的自动识别与解剖定位。
- 在PSMA配体训练数据受限时,可考虑利用其他示踪剂数据提升模型性能。
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: In PSMA-ligand PET/CT imaging, standardized evaluation frameworks and image-derived parameters are increasingly used to support prostate cancer staging. Clinical applicability remains challenging wherever manual measurements of numerous suspected lesions are required. Deep learning methods are promising for automated image analysis, typically requiring extensive expert-annotated image datasets to reach sufficient accuracy. We developed a deep learning method to support image-based staging, investigating the use of training information from two radiotracers. METHODS: In 173 subjects imaged with 68Ga-PSMA-11 PET/CT, divided into development (121) and test (52) sets, we trained and evaluated a convolutional neural network to both classify sites of elevated tracer uptake as nonsuspicious or suspicious for cancer and assign them an anatomical location. We evaluated training strategies to leverage information from a larger dataset of 18F-FDG PET/CT images and expert annotations, including transfer learning and combined training encoding the tracer type as input to the network. We assessed the agreement between the N and M stage assigned based on the network annotations and expert annotations, according to the PROMISE miTNM framework. RESULTS: In the development set, including 18F-FDG training data improved classification performance in four-fold cross validation. In the test set, compared to expert assessment, training with 18F-FDG data and the development set yielded 80.4% average precision [confidence interval (CI): 71.1-87.8] for identification of suspicious uptake sites, 77% (CI: 70.0-83.4) accuracy for anatomical location classification of suspicious findings, 81% agreement for identification of regional lymph node involvement, and 77% agreement for identification of metastatic stage. CONCLUSION: The evaluated algorithm showed good agreement with expert assessment for identification and anatomical location classification of suspicious uptake sites in whole-body 68Ga-PSMA-11 PET/CT. With restricted PSMA-ligand data available, the use of training examples from a different radiotracer improved performance. The investigated methods are promising for enabling efficient assessment of cancer stage and tumor burden.
引用
- Capobianco N, Sibille L, Chantadisai M, et al. Whole-body uptake classification and prostate cancer staging in 68Ga-PSMA-11 PET/CT using dual-tracer learning. Eur J Nucl Med Mol Imaging. 2021. PMID: 34232350. doi:10.1007/s00259-021-05473-2
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。