人工智能实现超低辐射暴露的全身PET扫描
该研究利用33例3-30岁淋巴瘤儿童及青年的全身18F-FDG PET/MRI扫描,开发卷积神经网络(CNN),将模拟6.25%超低剂量PET与同步采集的MRI结合生成标准剂量PET图像。结果显示AI重建图像在峰值信噪比和结构相似性上显著优于模拟6.25%剂量图像,SUVmax恢复至与标准剂量PET相似,读者诊断信心一致性显著提高(kappa=0.942 vs 0.650)。
要点
- CNN模型可从超低剂量PET输入生成模拟临床标准18F-FDG PET图像
- AI重建图像在传统图像质量指标上显著优于模拟6.25%剂量图像(p<0.001)
- AI重建后SUVmax恢复至与标准剂量PET相似,读者诊断信心一致性kappa=0.942
核心结论
- CNN模型能够从超低剂量输入生成模拟临床标准18F-FDG PET图像,并在诊断准确性和定量SUV测量方面保持临床相关信息。
研究设计与样本
- 研究使用33例3-30岁淋巴瘤儿童及青年的全身18F-FDG-PET/MRI扫描开发卷积神经网络(CNN),输入为模拟6.25%超低剂量18F-FDG PET与同步采集的MRI,输出标准剂量18F-FDG PET。
- 图像质量通过计算机视觉传统指标及专家放射科和核医学科医师评估,使用Wilcoxon符号秩检验和加权kappa统计。
主要发现
- AI重建PET图像的峰值信噪比和结构相似性指数显著高于模拟6.25%剂量图像,归一化均方根误差显著更低(p<0.001)。
- 与真实标准剂量PET相比,模拟6.25%超低剂量PET扫描中肿瘤和参考组织的SUVmax值因图像噪声显著更高。
- CNN增强后SUVmax值恢复至与标准剂量PET相似。
- 读者诊断信心定量测量显示,标准临床扫描与AI重建PET扫描之间的一致性(kappa=0.942)显著高于6.25%剂量扫描(kappa=0.650)。
临床怎么用
- 该CNN模型有望在保持诊断准确性和定量SUV测量临床相关信息的前提下,将儿童肿瘤患者的18F-FDG PET辐射暴露降至超低剂量水平。
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: To generate diagnostic 18F-FDG PET images of pediatric cancer patients from ultra-low-dose 18F-FDG PET input images, using a novel artificial intelligence (AI) algorithm. METHODS: We used whole-body 18F-FDG-PET/MRI scans of 33 children and young adults with lymphoma (3-30 years) to develop a convolutional neural network (CNN), which combines inputs from simulated 6.25% ultra-low-dose 18F-FDG PET scans and simultaneously acquired MRI scans to produce a standard-dose 18F-FDG PET scan. The image quality of ultra-low-dose PET scans, AI-augmented PET scans, and clinical standard PET scans was evaluated by traditional metrics in computer vision and by expert radiologists and nuclear medicine physicians, using Wilcoxon signed-rank tests and weighted kappa statistics. RESULTS: The peak signal-to-noise ratio and structural similarity index were significantly higher, and the normalized root-mean-square error was significantly lower on the AI-reconstructed PET images compared to simulated 6.25% dose images (p < 0.001). Compared to the ground-truth standard-dose PET, SUVmax values of tumors and reference tissues were significantly higher on the simulated 6.25% ultra-low-dose PET scans as a result of image noise. After the CNN augmentation, the SUVmax values were recovered to values similar to the standard-dose PET. Quantitative measures of the readers' diagnostic confidence demonstrated significantly higher agreement between standard clinical scans and AI-reconstructed PET scans (kappa = 0.942) than 6.25% dose scans (kappa = 0.650). CONCLUSIONS: Our CNN model could generate simulated clinical standard 18F-FDG PET images from ultra-low-dose inputs, while maintaining clinically relevant information in terms of diagnostic accuracy and quantitative SUV measurements.
引用
- Wang YJ, Baratto L, Hawk KE, et al. Artificial intelligence enables whole-body positron emission tomography scans with minimal radiation exposure. Eur J Nucl Med Mol Imaging. 2021. PMID: 33527176. doi:10.1007/s00259-021-05197-3
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。