.png){kind=icon}
.png){kind=icon}
Return
Forecasting the diabetic retinopathy progression using generative adversarial networks
.png){kind=icon}
OA
AI
DOI：10.1038/s43856-025-01092-2.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Diabetic retinopathy (DR) is the leading cause of blindness worldwide, making early prediction of DR progression crucial for effectively preventing visual loss. This study introduces a prediction framework DRForecastGAN (Diabetic Retinopathy Forecast Generative Adversarial Network), and investigates its clinical value in predicting DR development. DRForecastGAN model, consisting of a generator, discriminator, and registration network, was trained, validated, and tested in training (12,852 images), internal validation (2734 images), and external test (8523 images) datasets. A pre-trained ResNet50 classification model identified the DR severity on synthetic images. The performance of the proposed DRForecastGAN model was compared with the CycleGAN and Pix2Pix models in image reality and DR severity of the synthesized fundus images by calculating Fréchet Inception Distance (FID), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and area under the curve (AUC). DRForecastGAN model has the lowest FID, highest PSNR and highest SSIM on internal validation (FID: 27.3 vs. 32.8 vs. 34.4; PSNR: 25.3 vs. 17.0 vs. 16.9; SSIM: 0.93 vs. 0.79 vs. 0.65) and external test (FID: 37.6 vs.45.1 vs.48.4; PSNR: 20.7 vs.15.2 vs.14.7; SSIM: 0.86 vs.0.69 vs.0.63) datasets compared with Pix2Pix and CycleGAN models. In the prediction of DR severity, our DRForecastGAN model outperforms both Pix2Pix and CycleGAN models, achieving the highest AUC values on both internal validation (0.87 vs. 0.76 vs. 0.75) and external test (0.85 vs. 0.70 vs. 0.69) datasets. The proposed DRForecastGAN model can effectively visualize DR development by synthesizing future fundus images, offering potential utility for both treatment and ongoing monitoring of DR. Diabetic retinopathy (DR) is a serious eye condition that can occur in people with diabetes. It requires diagnosis by ophthalmologists (eye doctors) through detailed eye exams involving screening and basic imaging and then tracking of disease progression. This study presents a new prediction tool called DRForecastGAN designed to forecast the progression of DR. The tool was tested in training, internal validation, and external test datasets of eye images of patients. In predicting DR severity, the DRForecastGAN model outperformed several existing tools used for this task. Additionally, DRForecastGAN demonstrated the ability to effectively visualize the progression of DR, offering potential benefits for the treatment planning and continuous monitoring of DR by ophthalmologists. Qiao and Tang et al. present DRForecastGAN, a GAN-based model that predicts diabetic retinopathy progression by generating future fundus images. The model outperforms Pix2Pix and CycleGAN in both image quality and diagnostic accuracy across internal and external datasets.
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.3
Papers:
1.8K
Citations:
2.6K
View more organizations