用GAN生成眼底图像数据，提升CNN对近视、青光眼等疾病的分类准确率。
Ocular Disease Classification Using CNN with Deep Convolutional Generative Adversarial Network
- 用GAN合成眼底图像，解决真实数据不足问题。
- 分类准确率达84.6%，青光眼最高达88.6%。
- 适合医疗图像数据稀缺场景下的模型训练参考。
卷积神经网络（CNN）因强大的学习能力在图像分类中表现优异，但需大量均衡数据以避免过拟合。公开的眼底图像数据集不足以训练出高精度分类模型。为此，本文提出基于生成对抗网络（GAN）的数据生成技术，合成用于训练的图像数据，并使用原始含病灶眼底图像进行测试。实验结果显示，模型对近视的分类准确率为78.6%，青光眼为88.6%，白内障为84.6%，整体分类准确率达到84.6%。
原文摘要 · Abstract (English)
The Convolutional Neural Network (CNN) has shown impressive performance in image classification because of its strong learning capabilities. However, it demands a substantial and balanced dataset for effective training. Otherwise, networks frequently exhibit over fitting and struggle to generalize to new examples. Publicly available dataset of fundus images of ocular disease is insufficient to train any classification model to achieve satisfactory accuracy. So, we propose Generative Adversarial Network(GAN) based data generation technique to synthesize dataset for training CNN based classification model and later use original disease containing ocular images to test the model. During testing the model classification accuracy with the original ocular image, the model achieves an accuracy rate of 78.6% for myopia, 88.6% for glaucoma, and 84.6% for cataract, with an overall classification accuracy of 84.6%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。