Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database.
Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database.
复制标题
DOI：
10.1371/journal.pone.0187336
复制
发表时间：
2017
期刊：
影响因子：
3.7
通讯作者：
Rim TH
中科院分区：
文献类型：
--
作者：
Choi JY;Yoo TK;Seo JG;Kwak J;Um TT;Rim TH
深度学习成为分析医学图像的强大工具。利用计算机辅助诊断眼底图像进行视网膜疾病检测已成为一种新的方法。我们通过MatConvNet应用深度学习卷积神经网络，利用视网膜结构分析（STARE）数据库中涉及的眼底照片自动检测多种视网膜疾病。数据集是通过扩展10个类别的数据建立的，包括正常视网膜和9种视网膜疾病。采用基于VGG-19体系结构的随机森林迁移学习方法获得最优结果。分类结果在很大程度上取决于类别的数量。随着类别数量的增加，深度学习模型的性能下降。当包括所有10个类别时，我们获得的结果的准确性为30.5%，相对分类器信息（RCI）为0.052，科恩的kappa值为0.224。考虑到三个综合正常，背景糖尿病视网膜病变和干性年龄相关性黄斑变性，多分类分类器显示准确率为72.8%，0.283 RCI和0.577 kappa。此外，几个集成分类器增强了多类别分类性能。在10种视网膜疾病分类问题中，迁移学习结合聚类和投票方法的集成分类器表现出最好的性能，准确率为36.7%，RCI为0.053，Kappa为0.225。首先，由于数据集的规模较小，本研究中的深度学习技术无法应用于许多患有各种类型视网膜疾病的患者进行诊断和治疗的诊所。第二，我们发现结合集成分类器的迁移学习可以提高分类性能，以检测多类别视网膜疾病。进一步的研究应该确认从医院获得的大数据集的算法的有效性。
Deep learning emerges as a powerful tool for analyzing medical images. Retinal disease detection by using computer-aided diagnosis from fundus image has emerged as a new method. We applied deep learning convolutional neural network by using MatConvNet for an automated detection of multiple retinal diseases with fundus photographs involved in STructured Analysis of the REtina (STARE) database. Dataset was built by expanding data on 10 categories, including normal retina and nine retinal diseases. The optimal outcomes were acquired by using a random forest transfer learning based on VGG-19 architecture. The classification results depended greatly on the number of categories. As the number of categories increased, the performance of deep learning models was diminished. When all 10 categories were included, we obtained results with an accuracy of 30.5%, relative classifier information (RCI) of 0.052, and Cohen’s kappa of 0.224. Considering three integrated normal, background diabetic retinopathy, and dry age-related macular degeneration, the multi-categorical classifier showed accuracy of 72.8%, 0.283 RCI, and 0.577 kappa. In addition, several ensemble classifiers enhanced the multi-categorical classification performance. The transfer learning incorporated with ensemble classifier of clustering and voting approach presented the best performance with accuracy of 36.7%, 0.053 RCI, and 0.225 kappa in the 10 retinal diseases classification problem. First, due to the small size of datasets, the deep learning techniques in this study were ineffective to be applied in clinics where numerous patients suffering from various types of retinal disorders visit for diagnosis and treatment. Second, we found that the transfer learning incorporated with ensemble classifiers can improve the classification performance in order to detect multi-categorical retinal diseases. Further studies should confirm the effectiveness of algorithms with large datasets obtained from hospitals.
登录
查看更多内容
影响因子：
3.7
作者：
Casanova R;Saldana S;Chew EY;Danis RP;Greven CM;Ambrosius WT
通讯作者：
Ambrosius WT
影响因子：
8.5
作者：
Ben-David, Arie
通讯作者：
Ben-David, Arie
影响因子：
7.7
作者：
Acharya, U. Rajendra;Mookiah, Muthu Rama Krishnan;Laude, Augustinus
通讯作者：
Laude, Augustinus
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S
影响因子：
4.4
作者：
Abramoff, Michael David;Lou, Yiyue;Niemeijer, Meindert
通讯作者：
Niemeijer, Meindert