文献速递消化道肿瘤放疗放疗物理与技术

基于深度学习在多中心数据集中生成盆腔合成CT

Synthetic CT generation for pelvic cases based on deep learning in multi-center datasets.
PubMed 文献 · Radiat Oncol · 2024-07-09

本研究探讨在多中心数据集中利用生成对抗网络(GAN)从MR图像合成CT图像,用于直肠癌MR-only放疗的可行性。研究纳入北京大学人民医院90例直肠癌患者及公共数据集19例患者的T2加权MR和CT图像,提出结合对比学习损失与一致性正则化损失的新模型以增强多中心盆腔MRI到CT合成的泛化能力。结果显示模型在未见数据集上泛化性能(GP)为0.911,优于普通CycleGAN,合成CT与真实CT间多数剂量学差异小于1%,表明直肠癌MRI-only工作流程具有可行性。

要点

  • 新模型在未见数据集上GP为0.911,MAE从47.129降至42.344,SNRpeak从25.167升至26.979,SSIM从0.978升至0.992。
  • 合成CT与真实CT间多数DVH指标的相对剂量差异小于1%。
  • 多数剂量学差异在光子放疗临床可接受标准内,支持直肠癌MRI-only工作流程的可行性。

核心结论

  • 所提模型可从T2加权MR图像在多中心数据集中生成准确的合成CT。
  • 多数剂量学差异在光子放疗临床可接受标准内,证明直肠癌患者MRI-only工作流程的可行性。

研究设计与样本

  • 研究纳入北京大学人民医院90例直肠癌患者及公共数据集19例患者的常规T2加权MR和CT图像。
  • 研究提出结合对比学习损失与一致性正则化损失的新模型,以增强多中心盆腔MRI到CT合成的泛化能力。
  • 通过计算MAE、SNRpeak、SSIM和泛化性能(GP)评估CT与合成CT的图像相似性,并针对光子计划验证合成CT的剂量学准确性。

主要发现

  • 模型在未见数据集上GP为0.911,优于普通CycleGAN,MAE从47.129降至42.344,SNRpeak从25.167升至26.979,SSIM从0.978升至0.992。
  • 剂量学分析显示合成CT与真实CT间多数剂量和体积直方图(DVH)指标的相对差异小于1%。

关键数值与推荐

  • MAE从普通CycleGAN的47.129降至新模型的42.344。
  • SNRpeak从普通CycleGAN的25.167升至新模型的26.979。
  • SSIM从普通CycleGAN的0.978升至新模型的0.992。
  • 新模型在未见数据集上的GP为0.911。
  • 合成CT与真实CT间多数DVH指标的相对剂量差异小于1%。

临床怎么用

  • 原文结论指出,所提模型可从T2加权MR图像在多中心数据集中生成准确的合成CT,多数剂量学差异在光子放疗临床可接受标准内,证明直肠癌MRI-only工作流程的可行性。

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

BACKGROUND AND PURPOSE: To investigate the feasibility of synthesizing computed tomography (CT) images from magnetic resonance (MR) images in multi-center datasets using generative adversarial networks (GANs) for rectal cancer MR-only radiotherapy. MATERIALS AND METHODS: Conventional T2-weighted MR and CT images were acquired from 90 rectal cancer patients at Peking University People's Hospital and 19 patients in public datasets. This study proposed a new model combining contrastive learning loss and consistency regularization loss to enhance the generalization of model for multi-center pelvic MRI-to-CT synthesis. The CT-to-sCT image similarity was evaluated by computing the mean absolute error (MAE), peak signal-to-noise ratio (SNRpeak), structural similarity index (SSIM) and Generalization Performance (GP). The dosimetric accuracy of synthetic CT was verified against CT-based dose distributions for the photon plan. Relative dose differences in the planning target volume and organs at risk were computed. RESULTS: Our model presented excellent generalization with a GP of 0.911 on unseen datasets and outperformed the plain CycleGAN, where MAE decreased from 47.129 to 42.344, SNRpeak improved from 25.167 to 26.979, SSIM increased from 0.978 to 0.992. The dosimetric analysis demonstrated that most of the relative differences in dose and volume histogram (DVH) indicators between synthetic CT and real CT were less than 1%. CONCLUSION: The proposed model can generate accurate synthetic CT in multi-center datasets from T2w-MR images. Most dosimetric differences were within clinically acceptable criteria for photon radiotherapy, demonstrating the feasibility of an MRI-only workflow for patients with rectal cancer.

来源:Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Li X, Jia L, Lin F, et al. Synthetic CT generation for pelvic cases based on deep learning in multi-center datasets. Radiat Oncol. 2024. PMID: 38982452. doi:10.1186/s13014-024-02467-w

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。