<br>从全身 [68Ga]Ga-PSMA-11 PET/CT 图像中的转移性前列腺病变分割中提取全自动预后生物标志物,European Journal of Nuclear Medicine and Molecular Imaging

当前位置： X-MOL 学术 › Eur. J. Nucl. Med. Mol. Imaging › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

从全身 [68Ga]Ga-PSMA-11 PET/CT 图像中的转移性前列腺病变分割中提取全自动预后生物标志物
European Journal of Nuclear Medicine and Molecular Imaging ( IF 8.6 ) Pub Date : 2022-08-17 , DOI: 10.1007/s00259-022-05927-1
Jake Kendrick ₁ , Roslyn J Francis _{2,

3} , Ghulam Mubashar Hassan ₁ , Pejman Rowshanfarzad ₁ , Jeremy S L Ong ₄ , Martin A Ebert _{1,

5,

6}

Affiliation

目的

本研究旨在开发和评估一种基于深度学习的自动分割框架，用于全身 [⁶⁸Ga]Ga-PSMA-11 PET/CT 图像中的转移性前列腺癌（mPCa）病变，以提取患者水平的预后生物标志物。

方法

从一组生化复发的 PCa 患者中检索了 337 张 [⁶⁸Ga]Ga-PSMA-11 PET/CT 图像。提出了一种全 3D 卷积神经网络（CNN），它基于自配置的 nnU-Net 框架，并在这些扫描的子集上进行了训练，并保留了用于模型评估的独立测试集。使用骰子相似系数（DSC）、阳性预测值（PPV）和灵敏度评估体素级分割结果。计算敏感性和 PPV 以评估病变水平检测;通过准确性、 PPV 和敏感性评估患者水平的分类结果。通过自动分割计算全身生物标志物总病灶体积（TLV_auto）和总病灶摄取（TLU_auto），并使用 Kaplan-Meier 分析评估生物标志物与患者总生存期的关系。

结果

在患者层面，准确性、敏感性和 PPV 均为 > 90%，最佳指标是 PPV （97.2%）。病变水平的 PPV 和敏感性分别为 88.2% 和 73.0%。在测量的观察者间变异性内在体素水平上测量的 DSC 和 PPV（DSC，中位数 = 50.7% vs. 第二观察者 = 32%，p = 0.012;PPV，中位数 = 64.9% vs. 第二观察者 = 25.7%，p < 0.005）。TLV_auto 和 TLU_auto 的 Kaplan-Meier 分析显示它们与患者总生存期显著相关（均 p < 0.005）。

结论

使用深度学习对全身 [⁶⁸Ga]Ga-PSMA-11 PET/CT 图像进行全自动评估显示出巨大的前景，可产生准确的扫描分类、观察者间变异性内的体素级分割，以及与患者总生存期相关的潜在临床有用的预后生物标志物。

试用注册

这项研究于 2015 年 6 月 11 日在澳大利亚新西兰临床试验注册处（ACTRN12615000608561）注册。

"点击查看英文标题和摘要"

Fully automatic prognostic biomarker extraction from metastatic prostate lesion segmentations in whole-body [68Ga]Ga-PSMA-11 PET/CT images

Purpose

This study aimed to develop and assess an automated segmentation framework based on deep learning for metastatic prostate cancer (mPCa) lesions in whole-body [⁶⁸Ga]Ga-PSMA-11 PET/CT images for the purpose of extracting patient-level prognostic biomarkers.

Methods

Three hundred thirty-seven [⁶⁸Ga]Ga-PSMA-11 PET/CT images were retrieved from a cohort of biochemically recurrent PCa patients. A fully 3D convolutional neural network (CNN) is proposed which is based on the self-configuring nnU-Net framework, and was trained on a subset of these scans, with an independent test set reserved for model evaluation. Voxel-level segmentation results were assessed using the dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity. Sensitivity and PPV were calculated to assess lesion level detection; patient-level classification results were assessed by the accuracy, PPV, and sensitivity. Whole-body biomarkers total lesional volume (TLV_auto) and total lesional uptake (TLU_auto) were calculated from the automated segmentations, and Kaplan–Meier analysis was used to assess biomarker relationship with patient overall survival.

Results

At the patient level, the accuracy, sensitivity, and PPV were all > 90%, with the best metric being the PPV (97.2%). PPV and sensitivity at the lesion level were 88.2% and 73.0%, respectively. DSC and PPV measured at the voxel level performed within measured inter-observer variability (DSC, median = 50.7% vs. second observer = 32%, p = 0.012; PPV, median = 64.9% vs. second observer = 25.7%, p < 0.005). Kaplan–Meier analysis of TLV_auto and TLU_auto showed they were significantly associated with patient overall survival (both p < 0.005).

Conclusion

The fully automated assessment of whole-body [⁶⁸Ga]Ga-PSMA-11 PET/CT images using deep learning shows significant promise, yielding accurate scan classification, voxel-level segmentations within inter-observer variability, and potentially clinically useful prognostic biomarkers associated with patient overall survival.