Ren Fulong, Cao Peng, Zhao Dazhe, Wan Chao
School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China.
Key Laboratory of Medical Image Computing of Ministry of Education, Northeastern University, Shenyang, Liaoning, China.
Technol Health Care. 2018;26(S1):389-397. doi: 10.3233/THC-174704.
Diabetic macular edema (DME) is one of the severe complication of diabetic retinopathy causing severe vision loss and leads to blindness in severe cases if left untreated.
To grade the severity of DME in retinal images.
Firstly, the macular is localized using its anatomical features and the information of the macula location with respect to the optic disc. Secondly, a novel method for the exudates detection is proposed. The possible exudate regions are segmented using vector quantization technique and formulated using a set of feature vectors. A semi-supervised learning with graph based classifier is employed to identify the true exudates. Thirdly, the disease severity is graded into different stages based on the location of exudates and the macula coordinates.
The results are obtained with the mean value of 0.975 and 0.942 for accuracy and F1-scrore, respectively.
The present work contributes to macula localization, exudate candidate identification with vector quantization and exudate candidate classification with semi-supervised learning. The proposed method and the state-of-the-art approaches are compared in terms of performance, and experimental results show the proposed system overcomes the challenge of the DME grading and demonstrate a promising effectiveness.
糖尿病性黄斑水肿（DME）是糖尿病视网膜病变的严重并发症之一，可导致严重视力丧失，若不治疗，严重情况下会导致失明。
对视网膜图像中DME的严重程度进行分级。
首先，利用黄斑的解剖特征以及黄斑相对于视盘的位置信息对黄斑进行定位。其次，提出一种新的渗出物检测方法。使用矢量量化技术分割可能的渗出物区域，并使用一组特征向量进行表述。采用基于图的半监督学习分类器来识别真正的渗出物。第三，根据渗出物的位置和黄斑坐标将疾病严重程度分为不同阶段。
准确率和F1分数的结果分别为平均值0.975和0.942。
目前的工作有助于黄斑定位、利用矢量量化识别渗出物候选区域以及利用半监督学习对渗出物候选区域进行分类。在性能方面对所提出的方法与当前最先进的方法进行了比较，实验结果表明所提出的系统克服了DME分级的挑战，并显示出有前景的有效性。
