Dixon-VIBE深度学习(DIVIDE)骨盆伪CT合成用于PET/MR衰减校正
DIVIDE是一种深度学习网络,仅基于商用PET/MR扫描仪常规采集的Dixon-VIBE图像合成骨盆伪CT用于衰减校正。在19例患者28个数据集上,DIVIDE法各感兴趣区相对CT衰减校正的平均绝对相对变化低于2%(骨组织低于4%,为Dixon法的6.75分之一),PETCT与PETDIVIDE体素级相关性R²=0.9998(P<0.01),合成病灶中股骨和脊柱病灶量化改善最大。
要点
- DIVIDE仅用标准Dixon-VIBE四幅2D图像合成骨盆伪CT,可快速生成并支持回顾性处理。
- 除骨组织外各感兴趣区相对CT的平均绝对相对变化低于2%,骨组织低于4%。
- PETCT与PETDIVIDE体素级相关R²=0.9998(P<0.01),Bland-Altman差异均值0.0003、标准差0.0094。
核心结论
- DIVIDE方法可基于标准Dixon-VIBE图像准确合成骨盆伪CT,从而在PET/MR扫描仪中实现准确衰减校正。
- 该实现可快速合成伪CT,适合常规应用,甚至可对Dixon-VIBE数据进行回顾性处理。
研究设计与样本
- 研究提出将四幅2D Dixon MR图像(水、脂肪、同相位、反相位)映射到对应2D CT图像的深度学习网络,采用转置卷积学习上采样参数、以完整2D切片提供上下文信息,并用脑图像预训练网络。
- 使用19例接受PET/CT与PET/MR检查患者的28个数据集评估该方法,通过基于体素和基于区域的分析比较Dixon-VIBE衰减校正(PETDixon)、DIVIDE衰减校正(PETDIVIDE)与CT衰减校正(PETCT)后的SUV(单位g/mL)。
- 在前列腺、直肠、骨盆和脊柱定义的合成病灶中评估量化偏差。
主要发现
- DIVIDE法相对CT衰减校正的平均绝对相对变化值在除骨组织外的每个感兴趣区均低于2%。
- 骨组织中DIVIDE法相对CT的平均绝对相对变化低于4%,比Dixon法的相对变化小6.75倍。
- PETCT与PETDIVIDE的体素级相关性极好(R²=0.9998,P<0.01)。
- PETCT与PETDIVIDE的Bland-Altman分析:差异均值0.0003、标准差0.0094、95%CI [-0.0180,0.0188];PETCT与PETDixon:差异均值0.0006、标准差0.0264、95%CI [-0.0510,0.0524]。
- 合成病灶中两种方法间PET数据量化变化有统计学显著差异,股骨和脊柱病灶改善最大。
关键数值与推荐
- DIVIDE法相对CT衰减校正的平均绝对相对变化:除骨组织外各感兴趣区低于2%。
- 骨组织DIVIDE法相对CT的平均绝对相对变化低于4%,为Dixon法相对变化的6.75分之一。
- PETCT与PETDIVIDE体素级相关R²=0.9998(P<0.01)。
- PETCT-PETDIVIDE的SUV差异均值0.0003、标准差0.0094、95%CI [-0.0180,0.0188]。
- PETCT-PETDixon的SUV差异均值0.0006、标准差0.0264、95%CI [-0.0510,0.0524]。
临床怎么用
- 原文结论指出DIVIDE可基于标准Dixon-VIBE图像准确合成骨盆伪CT,用于PET/MR衰减校正。
- 原文指出该实现可快速合成伪CT,适合常规应用,并允许对Dixon-VIBE数据进行回顾性处理。
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
Whole-body attenuation correction (AC) is still challenging in combined PET/MR scanners. We describe Dixon-VIBE Deep Learning (DIVIDE), a deep-learning network that allows synthesizing pelvis pseudo-CT maps based only on the standard Dixon volumetric interpolated breath-hold examination (Dixon-VIBE) images currently acquired for AC in some commercial scanners. Methods: We propose a network that maps between the four 2-dimensional (2D) Dixon MR images (water, fat, in-phase, and out-of-phase) and their corresponding 2D CT image. In contrast to previous methods, we used transposed convolutions to learn the up-sampling parameters, we used whole 2D slices to provide context information, and we pretrained the network with brain images. Twenty-eight datasets obtained from 19 patients who underwent PET/CT and PET/MR examinations were used to evaluate the proposed method. We assessed the accuracy of the μ-maps and reconstructed PET images by performing voxel- and region-based analysis comparing the SUVs (in g/mL) obtained after AC using the Dixon-VIBE (PETDixon), DIVIDE (PETDIVIDE), and CT-based (PETCT) methods. Additionally, the bias in quantification was estimated in synthetic lesions defined in the prostate, rectum, pelvis, and spine. Results: Absolute mean relative change values relative to CT AC were lower than 2% on average for the DIVIDE method in every region of interest except for bone tissue, where it was lower than 4% and 6.75 times smaller than the relative change of the Dixon method. There was an excellent voxel-by-voxel correlation between PETCT and PETDIVIDE (R2 = 0.9998, P < 0.01). The Bland-Altman plot between PETCT and PETDIVIDE showed that the average of the differences and the variability were lower (mean PETCT-PETDIVIDE SUV, 0.0003; PETCT-PETDIVIDE SD, 0.0094; 95% confidence interval, [-0.0180,0.0188]) than the average of differences between PETCT and PETDixon (mean PETCT-PETDixon SUV, 0.0006; PETCT-PETDixon SD, 0.0264; 95% confidence interval, [-0.0510,0.0524]). Statistically significant changes in PET data quantification were observed between the 2 methods in the synthetic lesions, with the largest improvement in femur and spine lesions. Conclusion: The DIVIDE method can accurately synthesize a pelvis pseudo-CT scan from standard Dixon-VIBE images, allowing for accurate AC in combined PET/MR scanners. Additionally, our implementation allows rapid pseudo-CT synthesis, making it suitable for routine applications and even allowing retrospective processing of Dixon-VIBE data.
引用
- Torrado-Carvajal A, Vera-Olmos J, Izquierdo-Garcia D, et al. Dixon-VIBE Deep Learning (DIVIDE) Pseudo-CT Synthesis for Pelvis PET/MR Attenuation Correction. J Nucl Med. 2018. PMID: 30166357. doi:10.2967/jnumed.118.209288
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。