激光与光电子学进展, 2021, 58 (1): 0117002, 网络出版: 2021-01-04
光学相干断层扫描视网膜图像的迁移学习分类 下载: 1038次
Transfer Learning-Based Classification of Optical Coherence Tomography Retinal Images
医用光学 光学相干断层扫描 迁移学习 高斯滤波 微调 全局平均池化 medical optics optical coherence tomography transfer learning Gaussian filter fine-tuning global average pooling
摘要
光学相干断层扫描是目前检测糖尿病视网膜黄斑病变较为灵敏的方法之一,但病变的人工判断易产生主观失误,且比较耗时。为此,本文在迁移学习的基础上提出了一种改进的深度学习网络,用于视网膜图像的自动分类。先基于自适应阈值联合高斯滤波算法对图像进行预处理;然后以预训练模型为基础,通过微调解决样本差异的问题,并以全局平均池化方法替代传统的全连接层来提取深层特征,以降低网络的过拟合现象。基于实验数据对该网络进行验证,所提网络对视网膜病变图像的分类准确率可达97.3%,说明了所提网络对视网膜黄斑病变图像自动分类的有效性。
Abstract
Currently, optical coherence tomography is one of the most sensitive methods for detecting diabetic retinopathy. However, the artificial detection of diabetic retinopathy is time consuming and prone to subjective errors. Accordingly,this paper proposed an improved deep learning network based on transfer learning for automatic classification of retinal images. First, the image was preprocessed via adaptive threshold combined with the Gaussian filter algorithm. Then, on the basis of the pretraining model, the problem of sample difference was solved through fine-tuning, and the traditional fully connected layer was replaced by the global average pooling method for extracting deep features and reducing overfitting. The network was validated based on the experimental data, with the accuracy of the retinal image classification being 97.3%. Results reveal that the proposed network is effective for the automatic classification of retinal macular lesions.
连超铭, 钟舜聪, 张添福, 周宁, 谢茂松. 光学相干断层扫描视网膜图像的迁移学习分类[J]. 激光与光电子学进展, 2021, 58(1): 0117002. Lian Chaoming, Zhong Shuncong, Zhang Tianfu, Zhou Ning, Xie Maosong. Transfer Learning-Based Classification of Optical Coherence Tomography Retinal Images[J]. Laser & Optoelectronics Progress, 2021, 58(1): 0117002.