文献速递神经技术与安全MRPET

基于条件生成对抗网络在脑肿瘤中将MR图像跨模态转换为合成18F-FDOPA PET/MR融合图像

Cross-modality image-to-image translation from MR to synthetic 18F-FDOPA PET/MR fusion images using conditional GAN in brain cancer.
PubMed 文献 · Neuroradiology · 2025-07-19

回顾性纳入27例脑肿瘤患者的32次同期18F-FDOPA PET/MR检查,采用Pix2Pix算法将T1加权增强MR转换为合成PET/T1C融合图像。合成与真实图像的TBRmax相关系数0.706、TBRmean相关系数0.901(均p<0.001),定量指标PSNR 31.075±3.976、MSE 0.001±0.001、SSIM 0.868±0.079、FSIM 0.922±0.044;作者认为该方法显示跨模态转换潜力,但受限于小数据集且缺乏外部验证,需进一步研究。

要点

  • T1C到合成PET/T1C融合图像的转换中,TBRmean相关系数0.901(CI:0.831-0.943,p<0.001)高于TBRmax的0.706(CI:0.533-0.822,p<0.001)。
  • 合成图像定量相似度:PSNR 31.075±3.976、MSE 0.001±0.001、SSIM 0.868±0.079、FSIM 0.922±0.044。
  • 作者认为该方法显示跨模态转换潜力,但受限于小数据集且缺乏外部验证,需进一步研究。

核心结论

  • 基于同期18F-FDOPA PET/MR数据的CGAN(Pix2Pix算法)展示了从T1C到PET/T1C融合图像跨模态图像转换的潜力,但受限于小数据集且缺乏外部验证,需进一步研究。

研究设计与样本

  • 回顾性研究,纳入27例确诊脑肿瘤患者的32次同期18F-FDOPA PET/MR检查,将配对轴位T1C与PET/T1C融合图像(共2167对)按9:1随机分为训练集1950对和测试集217对,训练集再按4:1分为训练集1560对和验证集390对,采用CGAN的Pix2Pix算法从T1C转换生成合成PET/T1C融合图像。

诊断标准与关键数值

  • 以真实PET/T1C融合图像为参考,合成与真实图像的相关系数:TBRmax 0.706(CI:0.533-0.822,p<0.001),TBRmean 0.901(CI:0.831-0.943,p<0.001);定量分析:PSNR 31.075±3.976、MSE 0.001±0.001、SSIM 0.868±0.079、FSIM 0.922±0.044。

临床应用与阅片要点

  • 作者认为CGAN基于同期18F-FDOPA PET/MR数据从T1C转换生成PET/T1C融合图像显示潜力,但受限于小数据集且缺乏外部验证,需进一步研究。

局限性

  • 小数据集
  • 缺乏外部验证
  • 需进一步研究

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)。

英文原文(摘要)· 点击展开

OBJECTIVE: This study aims to identify the possibility of cross-modality image-to-image translation from magnetic resonance (MR) to synthetic positron emission tomography (PET)/MR fusion images using conditional generative adversarial networks (CGAN).

METHODS: Retrospective study was conducted involving 32 simultaneous 6-[18F]-fluoro-L-3,4-dihydroxyphenylalanine (18F-FDOPA) PET/MR imaging examinations from 27 patients diagnosed with brain cancer. We applied paired axial T1-weighted contrast MR (T1C) and PET/T1C fusion images to translate from T1C to synthetic PET/T1C fusion images using the Pix2Pix algorithm of CGAN. To access the image similarity between real and synthetic PET/T1C fusion images, we calculated correlation coefficients for the maximum/mean tumor-to-background ratio (TBRmax/mean) and quantitative analyses were performed using peak signal-to-noise ratio (PSNR), mean squared error (MSE), structural similarity index (SSIM), and feature similarity index measure (FSIM).

RESULTS: Total 2167 pairs of T1C and PET/T1C fusion images were obtained, which were randomly assigned to training and test datasets in 9:1 ratio (1950 and 217 pairs), and training data were further divided into training and validation datasets in 4:1 ratio (1560 and 390 pairs). The correlation coefficients were 0.706 (CI:0.533-0.822) for TBRmax (p < 0.001) and 0.901 (CI:0.831-0.943) for TBRmean (p < 0.001). The quantitative analyses were PSNR of 31.075 ± 3.976, MSE of 0.001 ± 0.001, SSIM of 0.868 ± 0.079, and FSIM of 0.922 ± 0.044, respectively.

CONCLUSION: CGAN based on simultaneous 18F-FDOPA PET/MR imaging data demonstrated the potential for cross-modality image-to-image translation from T1C to PET/T1C fusion images, though limitations in small dataset and lack of external validation requiring further research.

来源:Neuroradiology,查看原文。版权归原作者所有。

引用

  1. Seo Y, Yang H, Kong E, et al. Cross-modality image-to-image translation from MR to synthetic 18F-FDOPA PET/MR fusion images using conditional GAN in brain cancer. Neuroradiology. 2025. PMID: 40682663. doi:10.1007/s00234-025-03704-z

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。