Solak Merve, Tören Murat, Asan Berkutay, Kaba Esat, Beyazal Mehmet, Çeliker Fatma Beyazal
Recep Tayyip Erdogan University, Department of Radiology, Rize, Turkey (M.S., E.K., M.B., F.B.C.).
Recep Tayyip Erdogan University, Department of Electrical and Electronics Engineering, Rize, Turkey (M.T., B.A.).
Acad Radiol. 2025 Apr;32(4):2220-2232. doi: 10.1016/j.acra.2024.11.021. Epub 2024 Dec 18.
Magnetic resonance imaging (MRI) is a vital tool for diagnosing neurological disorders, frequently utilising gadolinium-based contrast agents (GBCAs) to enhance resolution and specificity. However, GBCAs present certain risks, including side effects, increased costs, and repeated exposure. This study proposes an innovative approach using generative adversarial networks (GANs) for virtual contrast enhancement in brain MRI, with the aim of reducing or eliminating GBCAs, minimising associated risks, and enhancing imaging efficiency while preserving diagnostic quality.
In this study, 10,235 images were acquired in a 3.0 Tesla MRI scanner from 81 participants (54 females, 27 males; mean age 35 years, range 19-68 years). T1-weighted and contrast-enhanced images were obtained following the administration of a standard dose of a GBCA. In order to generate "synthetic" images for contrast-enhanced T1-weighted, a CycleGAN model, a sub-model of the GAN structure, was trained to process pre- and post-contrast images. The dataset was divided into three subsets: 80% for training, 10% for validation, and 10% for testing. TensorBoard was employed to prevent image deterioration throughout the training phase, and the image processing and training procedures were optimised. The radiologists were presented with a non-contrast input image and asked to choose between a real contrast-enhanced image and synthetic MR images generated by CycleGAN corresponding to this non-contrast MR image (Turing test).
The performance of the CycleGAN model was evaluated using a combination of quantitative and qualitative analyses. For the entire dataset, in the test set, the mean square error (MSE) was 0.0038, while the structural similarity index (SSIM) was 0.58. Among the submodels, the most successful model achieved an MSE of 0.0053, while the SSIM was 0.8. The qualitative evaluation was validated through a visual Turing test conducted by four radiologists with varying levels of clinical experience.
The findings of this study support the efficacy of the CycleGAN model in generating synthetic contrast-enhanced T1-weighted brain MR images. Both quantitative and qualitative evaluations demonstrated excellent performance, confirming the model's ability to produce realistic synthetic images. This method shows promise in potentially eliminating the need for intravenous contrast agents, thereby minimising the associated risks of their use.
磁共振成像（MRI）是诊断神经系统疾病的重要工具，经常使用基于钆的造影剂（GBCA）来提高分辨率和特异性。然而，GBCA存在一定风险，包括副作用、成本增加以及重复暴露。本研究提出一种创新方法，使用生成对抗网络（GAN）进行脑MRI的虚拟对比增强，目的是减少或消除GBCA，将相关风险降至最低，同时在保持诊断质量的情况下提高成像效率。
在本研究中，从81名参与者（54名女性，27名男性；平均年龄35岁，范围19 - 68岁）中，在3.0特斯拉MRI扫描仪上采集了10235张图像。在给予标准剂量的GBCA后，获得了T1加权图像和对比增强图像。为了生成对比增强T1加权的“合成”图像，训练了GAN结构的子模型CycleGAN来处理对比前和对比后的图像。数据集被分为三个子集：80%用于训练，10%用于验证，10%用于测试。在整个训练阶段使用TensorBoard防止图像退化，并对图像处理和训练程序进行了优化。向放射科医生展示一张非对比输入图像，并要求他们在真实的对比增强图像和由CycleGAN生成的与该非对比MR图像对应的合成MR图像之间进行选择（图灵测试）。
使用定量和定性分析相结合的方法评估了CycleGAN模型的性能。对于整个数据集，在测试集中，均方误差（MSE）为0.0038，而结构相似性指数（SSIM）为0.58。在子模型中，最成功的模型MSE为0.0053，而SSIM为0.8。通过由四名具有不同临床经验水平的放射科医生进行的视觉图灵测试对定性评估进行了验证。
本研究结果支持CycleGAN模型在生成合成对比增强T1加权脑MR图像方面的有效性。定量和定性评估均显示出优异的性能，证实了该模型生成逼真合成图像的能力。这种方法有望潜在地消除对静脉造影剂的需求，从而将使用它们的相关风险降至最低。
