Annu Int Conf IEEE Eng Med Biol Soc. 2022 Jul;2022:2062-2065. doi: 10.1109/EMBC48229.2022.9871284.
With the rapid development of the world economy and increasing improvement of people's living standards, the number of diabetic patients has been growing quickly. Meanwhile, the complications of diabetes especially retinopathy have been affecting their daily life seriously. The only way to prevent it from getting worse and even leading to blindness is to make corresponding diagnosis as early as possible. However, it's extremely impossible for professionals to diagnose all the patients through their fundus images. It couldn't be better to solve the problem by automatic systems, so we present a novel network to learn the features of diabetic retinopathy (DR) and its complication diabetic macular edema (DME) and the relationship between them, focus on some vital areas in the pictures and eventually obtain the grades of the two diseases at the same time. Experimental results further prove the effectiveness of our proposed module comparing to the only joint grading network before.
随着世界经济的快速发展和人们生活水平的不断提高，糖尿病患者的数量一直在迅速增加。与此同时，糖尿病的并发症，特别是视网膜病变，严重影响了他们的日常生活。防止病情恶化甚至导致失明的唯一方法是尽早进行相应的诊断。然而，让专业人员通过眼底图像对所有患者进行诊断是极其不可能的。通过自动系统来解决这个问题再好不过了，因此我们提出了一种新的网络，用于学习糖尿病性视网膜病变 (DR) 和其并发症糖尿病性黄斑水肿 (DME) 的特征及其之间的关系，关注图片中的一些重要区域，最终同时获得两种疾病的等级。实验结果进一步证明了与之前仅有的联合分级网络相比，我们提出的模块的有效性。
