Xiangji Pan1, Kai Jin1, Jing Cao1, Zhifang Liu1, Jian Wu2, Kun You2, Yifei Lu2, Yufeng Xu1, Zhaoan Su1, Jiekai Jiang1, Ke Yao1, Juan Ye3. 1. Department of Ophthalmology, The Second Affiliated Hospital of Zhejiang University, College of Medicine, Hangzhou, 310009, China. 2. College of Computer Science and Technology, Zhejiang University, Hangzhou, 310027, China. 3. Department of Ophthalmology, The Second Affiliated Hospital of Zhejiang University, College of Medicine, Hangzhou, 310009, China. yejuan@zju.edu.cn.
Abstract
PURPOSE: To automatically detect and classify the lesions of diabetic retinopathy (DR) in fundus fluorescein angiography (FFA) images using deep learning algorithm through comparing 3 convolutional neural networks (CNNs). METHODS: A total of 4067 FFA images from Eye Center at the Second Affiliated Hospital of Zhejiang University School of Medicine were annotated with 4 kinds of lesions of DR, including non-perfusion regions (NP), microaneurysms, leakages, and laser scars. Three CNNs including DenseNet, ResNet50, and VGG16 were trained to achieve multi-label classification, which means the algorithms could identify 4 retinal lesions above at the same time. RESULTS: The area under the curve (AUC) of DenseNet reached 0.8703, 0.9435, 0.9647, and 0.9653 for detecting NP, microaneurysms, leakages, and laser scars, respectively. For ResNet50, AUC was 0.8140 for NP, 0.9097 for microaneurysms, 0.9585 for leakages, and 0.9115 for laser scars. And for VGG16, AUC was 0.7125 for NP, 0.5569 for microaneurysms, 0.9177 for leakages, and 0.8537 for laser scars. CONCLUSIONS: Experimental results demonstrate that DenseNet is a suitable model to automatically detect and distinguish retinal lesions in the FFA images with multi-label classification, which lies the foundation of automatic analysis for FFA images and comprehensive diagnosis and treatment decision-making for DR.
PURPOSE: To automatically detect and classify the lesions of diabetic retinopathy (DR) in fundus fluorescein angiography (FFA) images using deep learning algorithm through comparing 3 convolutional neural networks (CNNs). METHODS: A total of 4067 FFA images from Eye Center at the Second Affiliated Hospital of Zhejiang University School of Medicine were annotated with 4 kinds of lesions of DR, including non-perfusion regions (NP), microaneurysms, leakages, and laser scars. Three CNNs including DenseNet, ResNet50, and VGG16 were trained to achieve multi-label classification, which means the algorithms could identify 4 retinal lesions above at the same time. RESULTS: The area under the curve (AUC) of DenseNet reached 0.8703, 0.9435, 0.9647, and 0.9653 for detecting NP, microaneurysms, leakages, and laser scars, respectively. For ResNet50, AUC was 0.8140 for NP, 0.9097 for microaneurysms, 0.9585 for leakages, and 0.9115 for laser scars. And for VGG16, AUC was 0.7125 for NP, 0.5569 for microaneurysms, 0.9177 for leakages, and 0.8537 for laser scars. CONCLUSIONS: Experimental results demonstrate that DenseNet is a suitable model to automatically detect and distinguish retinal lesions in the FFA images with multi-label classification, which lies the foundation of automatic analysis for FFA images and comprehensive diagnosis and treatment decision-making for DR.
Entities:
Keywords:
Deep learning; Diabetic retinopathy; Fundus fluorescein angiography; Multi-label classification
Authors: Caner Mercan; Selim Aksoy; Ezgi Mercan; Linda G Shapiro; Donald L Weaver; Joann G Elmore Journal: IEEE Trans Med Imaging Date: 2017-10-02 Impact factor: 10.048
Authors: Igor Kozak; Sharif Y El-Emam; Lingyun Cheng; Dirk-Uwe Bartsch; Jay Chhablani; William R Freeman; J Fernando Arevalo Journal: Retina Date: 2014-08 Impact factor: 4.256
Authors: Josep Vidal-Alaball; Dídac Royo Fibla; Miguel A Zapata; Francesc X Marin-Gomez; Oscar Solans Fernandez Journal: JMIR Res Protoc Date: 2019-02-01