Peng Kun, Huang Dan, Chen Yurong
School of Automation and Information Engineering, Sichuan University of Science & Engineering, Key Laboratory of Artificial Intelligence, Yibin, 644000, Sichuan, China.
Med Biol Eng Comput. 2025 Jan 25. doi: 10.1007/s11517-025-03286-1.
Accurately classifying optical coherence tomography (OCT) images is essential for diagnosing and treating ophthalmic diseases. This paper introduces a novel generative adversarial network framework called MGR-GAN. The masked image modeling (MIM) method is integrated into the GAN model's generator, enhancing its ability to synthesize more realistic images by reconstructing them based on unmasked patches. A ResNet-structured discriminator is employed to determine whether the image is generated by the generator. Through the unique game process of the generative adversarial network (GAN) model, the discriminator acquires high-level discriminant features, essential for precise OCT classification. Experimental results demonstrate that MGR-GAN achieves a classification accuracy of 98.4% on the original UCSD dataset. As the trained generator can synthesize OCT images with higher precision, and owing to category imbalances in the UCSD dataset, the generated OCT images are leveraged to address this imbalance. After balancing the UCSD dataset, the classification accuracy further improves to 99%.
准确分类光学相干断层扫描（OCT）图像对于眼科疾病的诊断和治疗至关重要。本文介绍了一种名为MGR-GAN的新型生成对抗网络框架。掩蔽图像建模（MIM）方法被集成到GAN模型的生成器中，通过基于未掩蔽的图像块重建图像来增强其合成更逼真图像的能力。采用ResNet结构的判别器来确定图像是否由生成器生成。通过生成对抗网络（GAN）模型独特的博弈过程，判别器获得了高级判别特征，这对于精确的OCT分类至关重要。实验结果表明，MGR-GAN在原始UCSD数据集上实现了98.4%的分类准确率。由于训练后的生成器可以更精确地合成OCT图像，并且由于UCSD数据集中存在类别不平衡问题，利用生成的OCT图像来解决这种不平衡。在平衡UCSD数据集后，分类准确率进一步提高到99%。
