深度学习生成全身TOF 18F-FDG PET/MRI衰减图
本研究回顾性使用100例癌症患者的全身18F-FDG PET/CT数据,训练改进U-net卷积神经网络,以MLAA算法生成的活度分布和μ图为输入预测CT来源的衰减图。结果显示CNN生成的衰减图噪声更低、骨识别优于MLAA,骨区Dice系数0.77显著高于MLAA的0.36,且与CT衰减校正后的活度图相关性最佳。
要点
- CNN衰减图骨区Dice系数0.77,显著高于MLAA的0.36。
- CNN生成衰减图噪声更低且骨识别优于MLAA。
- CNN结果与CT衰减校正的活度图相关性最佳。
核心结论
- 所提深度神经网络生成的511 keV光子衰减图比全身PET/MRI现用的4段法更可靠。
研究设计与样本
- 回顾性使用100例癌症患者(38男62女,年龄57.3±14.1岁)的全身18F-FDG PET/CT数据训练和测试CNN。
- 改进U-net以MLAA生成的活度分布和μ图为输入预测CT来源μ图。
- 将μ-CNN、μ-MLAA和4段法生成的衰减图与作为金标准的μ-CT比较。
主要发现
- CNN生成比MLAA噪声更低的衰减图,骨识别优于MLAA。
- μ-CNN与μ-CT骨区平均Dice相似系数为0.77,显著高于μ-MLAA与μ-CT的0.36。
- CNN结果与CT来源结果像素级相关性最佳,且相比CT衰减校正活度图差异显著减小。
关键数值与推荐
- 骨区Dice相似系数:μ-CNN vs μ-CT为0.77,μ-MLAA vs μ-CT为0.36。
临床怎么用
- 该方法可为全身TOF 18F-FDG PET/MRI提供比4段法更可靠的衰减校正。
局限性
- 原文未报告
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
We propose a new deep learning-based approach to provide more accurate whole-body PET/MRI attenuation correction than is possible with the Dixon-based 4-segment method. We use activity and attenuation maps estimated using the maximum-likelihood reconstruction of activity and attenuation (MLAA) algorithm as inputs to a convolutional neural network (CNN) to learn a CT-derived attenuation map. Methods: The whole-body 18F-FDG PET/CT scan data of 100 cancer patients (38 men and 62 women; age, 57.3 ± 14.1 y) were retrospectively used for training and testing the CNN. A modified U-net was trained to predict a CT-derived μ-map (μ-CT) from the MLAA-generated activity distribution (λ-MLAA) and μ-map (μ-MLAA). We used 1.3 million patches derived from 60 patients' data for training the CNN, data of 20 others were used as a validation set to prevent overfitting, and the data of the other 20 were used as a test set for the CNN performance analysis. The attenuation maps generated using the proposed method (μ-CNN), μ-MLAA, and 4-segment method (μ-segment) were compared with the μ-CT, a ground truth. We also compared the voxelwise correlation between the activity images reconstructed using ordered-subset expectation maximization with the μ-maps, and the SUVs of primary and metastatic bone lesions obtained by drawing regions of interest on the activity images. Results: The CNN generates less noisy attenuation maps and achieves better bone identification than MLAA. The average Dice similarity coefficient for bone regions between μ-CNN and μ-CT was 0.77, which was significantly higher than that between μ-MLAA and μ-CT (0.36). Also, the CNN result showed the best pixel-by-pixel correlation with the CT-based results and remarkably reduced differences in activity maps in comparison to CT-based attenuation correction. Conclusion: The proposed deep neural network produced a more reliable attenuation map for 511-keV photons than the 4-segment method currently used in whole-body PET/MRI studies.
引用
- Hwang D, Kang SK, Kim KY, et al. Generation of PET Attenuation Map for Whole-Body Time-of-Flight 18F-FDG PET/MRI Using a Deep Neural Network Trained with Simultaneously Reconstructed Activity and Attenuation Maps. J Nucl Med. 2019. PMID: 30683763. doi:10.2967/jnumed.118.219493
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。