文献速递肿瘤 PET/CT

PET/CT 成像中的深度学习图像增强算法:体模与肉瘤患者的影像组学评估

Deep learning image enhancement algorithms in PET/CT imaging: a phantom and sarcoma patient radiomic evaluation.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2025-02-27

本研究在体模和20例肉瘤患者的[18F]FDG PET/CT数据中,用93个IBSI标准化影像组学特征比较两种厂商深度学习图像增强算法与金标准重建图像的差异。结果显示,深度学习增强图像与金标准图像相比,体模和患者数据中分别仅4.0%和9.7%的特征有显著差异,超过80%的特征无显著差异。

要点

  • 体模数据中,深度学习增强图像与金标准图像相比,4.0%的影像组学特征有显著差异。
  • 肉瘤患者数据中,深度学习增强图像与金标准图像相比,9.7%的影像组学特征有显著差异。
  • 深度学习增强图像与算法输入图像相比,体模和患者数据中分别有29.8%和43.0%的特征有显著差异。

核心结论

  • 深度学习增强图像与金标准目标重建方法生成的图像相似,在体模和肉瘤患者数据的所有比较中,超过80%的影像组学特征无显著差异。
  • 该结果为了解深度学习算法性能提供了依据,并展示了深度学习算法在影像组学协调化及用影像组学特征定量评估深度学习算法方面的潜在应用。

研究设计与样本

  • 回顾性肉瘤临床[18F]FDG数据集,共20例,均在GE Discovery 690或710 PET/CT扫描仪上采集,由一位经验丰富的核医学放射科医生勾画感兴趣区。
  • 体模为模块化异质性成像体模,充填[18F]FDG,在GE Discovery 710 PET/CT扫描仪上重复采集5次。
  • 比较深度学习增强图像与算法训练所模拟的金标准图像及输入图像,在93个IBSI标准化影像组学特征中检验差异显著性。

主要发现

  • 深度学习增强图像对比金标准图像:体模数据中4.0%、患者数据中9.7%的影像组学特征有显著差异(两种深度学习算法平均,pcritical<0.0005)。
  • 深度学习增强图像对比算法输入图像:体模数据中29.8%、患者数据中43.0%的影像组学特征有显著差异(两种深度学习算法平均)。

关键数值与推荐

  • 影像组学特征差异显著性检验采用pcritical<0.0005。
  • 共评估93个IBSI标准化影像组学特征。

临床怎么用

  • 原文未据此给出临床推荐。

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: PET/CT imaging data contains a wealth of quantitative information that can provide valuable contributions to characterising tumours. A growing body of work focuses on the use of deep-learning (DL) techniques for denoising PET data. These models are clinically evaluated prior to use, however, quantitative image assessment provides potential for further evaluation. This work uses radiomic features to compare two manufacturer deep-learning (DL) image enhancement algorithms, one of which has been commercialised, against 'gold-standard' image reconstruction techniques in phantom data and a sarcoma patient data set (N=20). METHODS: All studies in the retrospective sarcoma clinical [ 18 F]FDG dataset were acquired on either a GE Discovery 690 or 710 PET/CT scanner with volumes segmented by an experienced nuclear medicine radiologist. The modular heterogeneous imaging phantom used in this work was filled with [ 18 F]FDG, and five repeat acquisitions of the phantom were acquired on a GE Discovery 710 PET/CT scanner. The DL-enhanced images were compared to 'gold-standard' images the algorithms were trained to emulate and input images. The difference between image sets was tested for significance in 93 international biomarker standardisation initiative (IBSI) standardised radiomic features. RESULTS: Comparing DL-enhanced images to the 'gold-standard', 4.0% and 9.7% radiomic features measured significantly different (pcritical < 0.0005) in the phantom and patient data respectively (averaged over the two DL algorithms). Larger differences were observed comparing DL-enhanced images to algorithm input images with 29.8% and 43.0% of radiomic features measuring significantly different in the phantom and patient data respectively (averaged over the two DL algorithms). CONCLUSION: DL-enhanced images were found to be similar to images generated using the 'gold-standard' target image reconstruction method with more than 80% of radiomic features not significantly different in all comparisons across unseen phantom and sarcoma patient data. This result offers insight into the performance of the DL algorithms, and demonstrate potential applications for DL algorithms in harmonisation for radiomics and for radiomic features in quantitative evaluation of DL algorithms.

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

引用

  1. Bonney LM, Kalisvaart GM, van Velden FHP, et al. Deep learning image enhancement algorithms in PET/CT imaging: a phantom and sarcoma patient radiomic evaluation. Eur J Nucl Med Mol Imaging. 2025. PMID: 40014074. doi:10.1007/s00259-025-07149-7

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。