差分隐私保护的联邦迁移学习用于多机构68Ga-PET图像伪影检测与解缠
本研究纳入3个国家8个中心的1413例68Ga-PSMA/DOTA-TATE PET/CT患者,采用差分隐私联邦迁移学习(FTL)构建中心特异性模型检测和校正PET图像伪影。在清洁测试集上,FTL的MAE为0.28±0.15(95%CI 0.25-0.31),优于CeBa和CeZe(p<0.05)。核医学医师定性评估显示FTL-ASC较CT-ASC显著改善图像质量和诊断信心并减少伪影。
要点
- FTL在清洁测试集上MAE为0.28±0.15,优于CeBa和CeZe(p<0.05)。
- FTL-ASC较CT-ASC显著改善68Ga-PET图像质量和诊断信心并减少伪影。
- 胸部、腹部和盆腔的错配和光晕伪影被成功检测和解缠。
核心结论
- 所提出的方法受益于使用多中心大型数据集同时保护患者隐私。
- 核医学医师定性评估表明该模型正确解决了68Ga-PET成像中两种主要挑战性伪影。
- 该技术可利用多中心异质性数据集整合到临床用于68Ga-PET成像伪影检测和解缠。
研究设计与样本
- 纳入3个国家8个中心的1413例68Ga-PSMA/DOTA-TATE PET/CT患者。
- 所有中心采用CT衰减和散射校正(CT-ASC)进行定量PET重建。
- 由经验丰富的核医学医师审核所有图像以确保使用高质量无伪影PET图像(421例患者图像)。
- 在80%无伪影PET图像上训练深度神经网络(修改的U2Net),采用基于中心(CeBa)、集中式(CeZe)和所提出的差分隐私FTL框架。
- 在每个中心20%清洁数据(无伪影)上进行定量分析。
主要发现
- CeBa、CeZe和FTL三种方法的MAE分别为0.42±0.21(95%CI 0.38-0.47)、0.32±0.23(95%CI 0.27-0.37)和0.28±0.15(95%CI 0.25-0.31)。
- Wilcoxon检验显示三种方法间差异显著,FTL在清洁测试集上优于CeBa和CeZe(p<0.05)。
- 定性评估显示FTL-ASC较CT-ASC显著改善68Ga-PET图像质量和诊断信心并减少图像伪影。
- 胸部、腹部和盆腔区域的错配和光晕伪影被成功检测和解缠。
关键数值与推荐
- 清洁测试集上FTL的MAE为0.28±0.15(95%CI 0.25-0.31),CeZe为0.32±0.23(95%CI 0.27-0.37),CeBa为0.42±0.21(95%CI 0.38-0.47)。
- Wilcoxon检验显示FTL与CeBa和CeZe差异显著(p<0.05)。
- 定性评估中FTL-ASC较CT-ASC显著改善图像质量和诊断信心并减少伪影。
临床怎么用
- 核医学医师定性评估表明该模型正确解决了68Ga-PET成像中两种主要挑战性伪影。
- 作者认为该技术可利用多中心异质性数据集整合到临床用于68Ga-PET成像伪影检测和解缠。
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)。
原文
PURPOSE: Image artefacts continue to pose challenges in clinical molecular imaging, resulting in misdiagnoses, additional radiation doses to patients and financial costs. Mismatch and halo artefacts occur frequently in gallium-68 (68Ga)-labelled compounds whole-body PET/CT imaging. Correcting for these artefacts is not straightforward and requires algorithmic developments, given that conventional techniques have failed to address them adequately. In the current study, we employed differential privacy-preserving federated transfer learning (FTL) to manage clinical data sharing and tackle privacy issues for building centre-specific models that detect and correct artefacts present in PET images. METHODS: Altogether, 1413 patients with 68Ga prostate-specific membrane antigen (PSMA)/DOTA-TATE (TOC) PET/CT scans from 3 countries, including 8 different centres, were enrolled in this study. CT-based attenuation and scatter correction (CT-ASC) was used in all centres for quantitative PET reconstruction. Prior to model training, an experienced nuclear medicine physician reviewed all images to ensure the use of high-quality, artefact-free PET images (421 patients' images). A deep neural network (modified U2Net) was trained on 80% of the artefact-free PET images to utilize centre-based (CeBa), centralized (CeZe) and the proposed differential privacy FTL frameworks. Quantitative analysis was performed in 20% of the clean data (with no artefacts) in each centre. A panel of two nuclear medicine physicians conducted qualitative assessment of image quality, diagnostic confidence and image artefacts in 128 patients with artefacts (256 images for CT-ASC and FTL-ASC). RESULTS: The three approaches investigated in this study for 68Ga-PET imaging (CeBa, CeZe and FTL) resulted in a mean absolute error (MAE) of 0.42 ± 0.21 (CI 95%: 0.38 to 0.47), 0.32 ± 0.23 (CI 95%: 0.27 to 0.37) and 0.28 ± 0.15 (CI 95%: 0.25 to 0.31), respectively. Statistical analysis using the Wilcoxon test revealed significant differences between the three approaches, with FTL outperforming CeBa and CeZe (p-value < 0.05) in the clean test set. The qualitative assessment demonstrated that FTL-ASC significantly improved image quality and diagnostic confidence and decreased image artefacts, compared to CT-ASC in 68Ga-PET imaging. In addition, mismatch and halo artefacts were successfully detected and disentangled in the chest, abdomen and pelvic regions in 68Ga-PET imaging. CONCLUSION: The proposed approach benefits from using large datasets from multiple centres while preserving patient privacy. Qualitative assessment by nuclear medicine physicians showed that the proposed model correctly addressed two main challenging artefacts in 68Ga-PET imaging. This technique could be integrated in the clinic for 68Ga-PET imaging artefact detection and disentanglement using multicentric heterogeneous datasets.
引用
- Shiri I, Salimi Y, Maghsudi M, et al. Differential privacy preserved federated transfer learning for multi-institutional 68Ga-PET image artefact detection and disentanglement. Eur J Nucl Med Mol Imaging. 2023. PMID: 37682303. doi:10.1007/s00259-023-06418-7
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。