School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, China; School of Management, Guangzhou University, Guangzhou, China.
School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, China.
Photodiagnosis Photodyn Ther. 2023 Mar;41:103272. doi: 10.1016/j.pdpdt.2023.103272. Epub 2023 Jan 9.
This study sought to assess the predictive performance of optical coherence tomography (OCT) images for the response of diabetic macular edema (DME) patients to anti-vascular endothelial growth factor (VEGF) therapy generated from baseline images using generative adversarial networks (GANs).
Patient information, including clinical and imaging data, was obtained from inpatients at the Ophthalmology Department of Qilu Hospital. 715 and 103 pairs of pre-and post-treatment OCT images of DME patients were included in the training and validation sets, respectively. The post-treatment OCT images were used to assess the validity of the generated images. Six different GAN models (CycleGAN, PairGAN, Pix2pixHD, RegGAN, SPADE, UNIT) were applied to predict the efficacy of anti-VEGF treatment by generating OCT images. Independent screening and evaluation experiments were conducted to validate the quality and comparability of images generated by different GAN models.
OCT images generated f GAN models exhibited high comparability to the real images, especially for edema absorption. RegGAN exhibited the highest prediction accuracy over the CycleGAN, PairGAN, Pix2pixHD, SPADE, and UNIT models. Further analyses were conducted based on the RegGAN. Most post-therapeutic OCT images (95/103) were difficult to differentiate from the real OCT images by retinal specialists. A mean absolute error of 26.74 ± 21.28 μm was observed for central macular thickness (CMT) between the synthetic and real OCT images.
Different generative adversarial networks have different prognostic efficacy for DME, and RegGAN yielded the best performance in our study. Different GAN models yielded good accuracy in predicting the OCT-based response to anti-VEGF treatment at one month. Overall, the application of GAN models can assist clinicians in prognosis prediction of patients with DME to design better treatment strategies and follow-up schedules.
本研究旨在评估基于生成对抗网络（GAN）的基线图像，利用光学相干断层扫描（OCT）图像预测糖尿病黄斑水肿（DME）患者对血管内皮生长因子（VEGF）治疗反应的预测性能。
患者信息包括临床和影像学数据，均来自齐鲁医院眼科住院患者。715 对和 103 对 DME 患者治疗前后的 OCT 图像分别纳入训练集和验证集。使用治疗后的 OCT 图像评估生成图像的有效性。应用六种不同的 GAN 模型（CycleGAN、PairGAN、Pix2pixHD、RegGAN、SPADe、UNIT）生成 OCT 图像，预测抗 VEGF 治疗的疗效。进行独立筛选和评估实验，验证不同 GAN 模型生成图像的质量和可比性。
GAN 模型生成的 OCT 图像与真实图像具有高度的可比性，特别是在水肿吸收方面。RegGAN 在预测准确性方面优于 CycleGAN、PairGAN、Pix2pixHD、SPADe 和 UNIT 模型。进一步的分析基于 RegGAN 进行。大多数治疗后 OCT 图像（95/103）很难与视网膜专家区分开。在合成和真实 OCT 图像之间，中央黄斑厚度（CMT）的平均绝对误差为 26.74±21.28μm。
不同的生成对抗网络对 DME 有不同的预后疗效，在本研究中，RegGAN 表现最佳。不同的 GAN 模型在预测抗 VEGF 治疗一个月后的 OCT 反应方面具有良好的准确性。总体而言，GAN 模型的应用可以帮助临床医生预测 DME 患者的预后，设计更好的治疗策略和随访计划。
