文献速递肿瘤 PET/CT

基于深度学习的时间飞行(ToF)图像增强用于非ToF PET扫描

Deep learning-based time-of-flight (ToF) image enhancement of non-ToF PET scans.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2022-05-04

研究使用273例[18F]-FDG PET扫描(来自6个中心的GE Discovery MI ToF扫描仪),训练三种深度学习ToF增强模型将非ToF BSREM图像转换为目标ToF图像。在测试集139个病灶中,DL-ToF中、高强度模型病灶SUVmax差异分别为-8±22%和1.7±24%,视觉评分诊断信心最高达4.1分(中强度),与ToF图像相当或更高。结论认为深度学习增强模型可能提供趋近ToF等效的图像质量。

要点

  • DL-ToF中、高强度增强的非ToF图像在临床评分中平均与ToF图像相当或更高
  • 测试集病灶SUVmax差异:非ToF -28±18%,DL-ToF中 -8±22%,DL-ToF高 1.7±24%
  • 视觉检查显示DL-ToF改善了特征锐度和向ToF重建的收敛

核心结论

  • 基于深度学习的图像增强模型可能提供趋近ToF等效的图像质量而无需ToF重建。
  • 在临床评分中,DL-ToF增强的非ToF图像(中、高强度)平均评分与ToF图像相当或更高。
  • 该模型具有泛化性,因此可应用于基于BGO的PET/CT扫描仪的非ToF图像。

研究设计与样本

  • 共使用273例[18F]-FDG PET扫描,包括来自6个配备GE Discovery MI ToF扫描仪的中心的图像数据。
  • PET数据使用块序列正则化期望最大化(BSREM)算法分别在有和无ToF条件下重建。
  • 图像分为训练集(n=208)、验证集(n=15)和测试集(n=50)。
  • 训练三种DL-ToF模型将非ToF BSREM图像转换为目标ToF图像,强度分为低、中、高。
  • 使用测试集基于139个识别病灶及肝、肺正常区域的标准化摄取值(SUV)进行客观评估,并由三名放射科医生对病灶可检测性、诊断信心和图像噪声/质量进行主观评分。

主要发现

  • 测试集病灶SUVmax差异(与非ToF BSREM图像相比):非ToF -28±18%,DL-ToF低 -28±19%,DL-ToF中 -8±22%,DL-ToF高 1.7±24%(均值;标准差)。
  • 背景肺VOI的SUVmean差异分别为:非ToF 7±15%,DL-ToF低 0.6±12%,DL-ToF中 1±13%,DL-ToF高 1±11%。
  • 正常肝脏SUVmean差异分别为:非ToF 4±5%,DL-ToF低 0.7±4%,DL-ToF中 0.8±4%,DL-ToF高 0.1±4%。
  • 测试集盲法临床阅读诊断信心评分(0-5分):非ToF 3.0分,DL-ToF低 3.0分,DL-ToF中 4.1分,DL-ToF高 3.8分,ToF 3.5分;DL-ToF中强度评分最高。
  • 视觉检查显示DL-ToF改善了特征锐度和向ToF重建的收敛。

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: To improve the quantitative accuracy and diagnostic confidence of PET images reconstructed without time-of-flight (ToF) using deep learning models trained for ToF image enhancement (DL-ToF). METHODS: A total of 273 [18F]-FDG PET scans were used, including data from 6 centres equipped with GE Discovery MI ToF scanners. PET data were reconstructed using the block-sequential-regularised-expectation-maximisation (BSREM) algorithm with and without ToF. The images were then split into training (n = 208), validation (n = 15), and testing (n = 50) sets. Three DL-ToF models were trained to transform non-ToF BSREM images to their target ToF images with different levels of DL-ToF strength (low, medium, high). The models were objectively evaluated using the testing set based on standardised uptake value (SUV) in 139 identified lesions, and in normal regions of liver and lungs. Three radiologists subjectively rated the models using testing sets based on lesion detectability, diagnostic confidence, and image noise/quality. RESULTS: The non-ToF, DL-ToF low, medium, and high methods resulted in - 28 ± 18, - 28 ± 19, - 8 ± 22, and 1.7 ± 24% differences (mean; SD) in the SUVmax for the lesions in testing set, compared to ToF-BSREM image. In background lung VOIs, the SUVmean differences were 7 ± 15, 0.6 ± 12, 1 ± 13, and 1 ± 11% respectively. In normal liver, SUVmean differences were 4 ± 5, 0.7 ± 4, 0.8 ± 4, and 0.1 ± 4%. Visual inspection showed that our DL-ToF improved feature sharpness and convergence towards ToF reconstruction. Blinded clinical readings of testing sets for diagnostic confidence (scale 0-5) showed that non-ToF, DL-ToF low, medium, and high, and ToF images scored 3.0, 3.0, 4.1, 3.8, and 3.5 respectively. For this set of images, DL-ToF medium therefore scored highest for diagnostic confidence. CONCLUSION: Deep learning-based image enhancement models may provide converged ToF-equivalent image quality without ToF reconstruction. In clinical scoring DL-ToF-enhanced non-ToF images (medium and high) on average scored as high as, or higher than, ToF images. The model is generalisable and hence, could be applied to non-ToF images from BGO-based PET/CT scanners.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Mehranian A, Wollenweber SD, Walker MD, et al. Deep learning-based time-of-flight (ToF) image enhancement of non-ToF PET scans. Eur J Nucl Med Mol Imaging. 2022. PMID: 35507059. doi:10.1007/s00259-022-05824-7

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。