期刊
ELECTRONICS
卷 10, 期 6, 页码 -出版社
MDPI
DOI: 10.3390/electronics10060726
关键词
future diabetic retinopathy image synthesis; prediction occurrence probability; generative adversarial network
资金
- National Research Foundation of Korea (NRF) - Korean government (MSIT) [2020R1F1A1065626]
- MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program [IITP-2020-2018-0-01798]
- Biomedical Institute for Convergence (BICS), Sungkyunkwan University
- National Research Foundation of Korea [2020R1F1A1065626] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
This paper presents a two-step training approach for synthesizing future fundus images considering disease progression in Diabetic Retinopathy (DR). By focusing on lesion segmentation mask and vessel segmentation mask, and training a lesion probability predictor, the framework generates predicted future fundus images based on the probability map and current vessel information. This approach achieves meaningful capabilities in predicting DR severity and DME occurrence with high F1 scores.
Diabetic Retinopathy (DR) is one of the major causes of blindness. If the lesions observed in DR occur in the central part of the fundus, it can cause severe vision loss, and we call this symptom Diabetic Macular Edema (DME). All patients with DR potentially have DME since DME can occur in every stage of DR. While synthesizing future fundus images, the task of predicting the progression of the disease state is very challenging since we need a lot of longitudinal data over a long period of time. Even if the longitudinal data are collected, there is a pixel-level difference between the current fundus image and the target future image. It is difficult to train a model based on deep learning for synthesizing future fundus images that considers the lesion change. In this paper, we synthesize future fundus images by considering the progression of the disease with a two-step training approach to overcome these problems. In the first step, we concentrate on synthesizing a realistic fundus image using only a lesion segmentation mask and vessel segmentation mask from a large dataset for a fundus generator. In the second step, we train a lesion probability predictor to create a probability map that contains the occurrence probability information of the lesion. Finally, based on the probability map and current vessel, the pre-trained fundus generator synthesizes a predicted future fundus image. We visually demonstrate not only the capacity of the fundus generator that can control the pathological information but also the prediction of the disease progression on fundus images generated by our framework. Our framework achieves an F1-score of 0.74 for predicting DR severity and 0.91 for predicting DME occurrence. We demonstrate that our framework has a meaningful capability by comparing the scores of each class of DR severity, which are obtained by passing the predicted future image and real future image through an evaluation model.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据