文献速递中枢神经肿瘤放疗头颈部肿瘤放疗放疗物理与技术

脑与头颈放疗通用医学影像模态转换模型

A universal medical imaging modality translation model in brain and head-and-neck radiotherapy.
PubMed 文献 · Radiother Oncol · 2025-12-07

研究开发了通用影像转换模型TAM,用90例脑与头颈放疗患者的多模态影像,通过两阶段策略合成MRI序列与CT。在46项转换任务中,TAM的图像质量指标优于CycleGAN和UNIT;基于合成CT的剂量计算Gamma通过率在2%/2mm和1%/1mm标准下分别达99.1%和94.1%,剂量体积直方图与真实CT计划接近。

要点

  • TAM采用3D U-Net分割软组织与骨骼作解剖锚点,再由条件扩散模型引导合成目标模态。
  • TAM图像质量PSNR 30.0、SSIM 0.973,优于UNIT和CycleGAN。
  • 合成CT剂量计算Gamma通过率2%/2mm为99.1%,1%/1mm为94.1%。

核心结论

  • TAM是一种新型任意到任意医学影像模态转换模型,可在MRI序列与CT间提供灵活且解剖保真的转换,进而提升配准和剂量计算等下游任务的准确性。

研究设计与样本

  • 回顾性纳入90例患者(43例脑、47例头颈)的多模态影像,每例最多含8个MRI序列及配对CT。
  • TAM采用两阶段转换策略:3D U-Net先分割软组织与骨骼作为解剖锚点,条件扩散模型再据此从任意可用输入模态合成目标模态。
  • 评估46项MRI-to-MRI和MRI-to-CT转换任务,与CycleGAN和UNIT两种方法比较,指标包括FID、PSNR、SSIM和基于HU的MAE。
  • 临床相关性通过模拟B样条变形的多模态配准和临床计划剂量计算(Gamma标准1%/1mm和2%/2mm)检验。

主要发现

  • TAM图像质量PSNR为30.0±3.7、SSIM为0.973±0.024,优于UNIT(27.0±3.2;0.958±0.026)和CycleGAN(25.4±4.1;0.949±0.037)。
  • 基于TAM合成CT的平均Gamma指数为99.1±1.7%(2%/2mm)和94.1±6.4%(1%/1mm),CycleGAN为93.1±7.5%/84.0±9.5%,UNIT为93.8±7.0%/86.3±9.4%。
  • 基于TAM合成CT的剂量体积直方图与真实CT计划密切匹配。

关键数值与推荐

  • 图像质量评价指标包括FID、PSNR、SSIM和基于HU的MAE。
  • 剂量计算验证采用Gamma标准1%/1mm和2%/2mm。
  • 配准验证采用模拟B样条变形。

临床怎么用

  • TAM可用于脑与头颈放疗中MRI序列与CT的灵活转换,支持多模态配准和基于合成CT的剂量计算。
  • 合成CT的剂量计算精度在2%/2mm标准下平均Gamma通过率达99.1%,1%/1mm下达94.1%, DVH与真实CT计划接近。

局限性

  • 本研究为回顾性研究,样本量90例(脑43例、头颈47例)。

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: We developed a universal image translation model-Translate Any Modality (TAM) model to synthesize MRI sequences and CT for brain and head-and-neck radiotherapy, facilitating downstream clinical tasks including multimodal registration and treatment dose calculation. METHODS AND MATERIALS: We retrospectively curated multi-modal imaging from 90 patients (43 brain, and 47 head-and-neck), each with up to eight MRI sequences and a paired CT. TAM uses a two-stage translation strategy: a 3D U-Net to firstly segment soft tissues and bones to serve as anatomical anchors; and a conditional diffusion model, guided by these masks, to synthesize the target modality from any available input modalities. We evaluated 46 MRI-to-MRI and MRI-to-CT translation tasks against two comparison methods, CycleGAN and UNIT, using Frechet Inception Distance (FID), peak signal-to-noise-ratio (PSNR), structural similarity index (SSIM), and Hounsfield unit (HU)-based mean absolute error (MAE). Clinical relevance was tested via multi-modality registration with simulated B-spline deformations and dose calculation using clinical plans with Gamma criteria 1 %/1 mm and 2 %/2 mm. RESULTS: TAM improved image quality (PSNR 30.0 ± 3.7; SSIM 0.973 ± 0.024) versus UNIT (27.0 ± 3.2; 0.958 ± 0.026) and CycleGAN (25.4 ± 4.1; 0.949 ± 0.037). For synthesized CT, TAM-based CT achieved average Gamma indices of 99.1 ± 1.7 % (2 %/2 mm) and 94.1 ± 6.4 % (1 %/1 mm) versus CycleGAN 93.1 ± 7.5 %/84.0 ± 9.5 % and UNIT 93.8 ± 7.0 %/86.3 ± 9.4 %, with dose-volume histograms closely matching real-CT plans. CONCLUSION: TAM is a novel any-to-any medical image modality translation model. It provides flexible, anatomically faithful translation among MRI sequences and CT, which subsequently improves the accuracy of downstream tasks, including registration and dose calculation.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Li Y, Liang X, Xie J, et al. A universal medical imaging modality translation model in brain and head-and-neck radiotherapy. Radiother Oncol. 2025. PMID: 41365375. doi:10.1016/j.radonc.2025.111321

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。