A new deep learning approach for the retinal hard exudates detection based on superpixel multi-feature extraction and patch-based CNN

NEUROCOMPUTING

卷:452

Article

Huang, Chenxi¹  Zong, Yongshuo²  Ding, Yimin³  Luo, Xin³  Clawson, Kathy⁴  Peng, Yonghong⁵ 

[1] Xiamen Univ, Sch Informat, Xiamen, Peoples R China

[2] Tongji Univ, Dept Comp Sci, Shanghai, Peoples R China

[3] Tongji Univ, Sch Elect & Informat Engn, Shanghai, Peoples R China

[4] Univ Sunderland, Sch Comp Sci, St Peter Campus, Sunderland, England

[5] Manchester Metropolitan Univ, Dept Comp & Math, Manchester, Lancs, England

关键词: Retinal hard exudates;    Superpixel;    Feature extraction;    Deep learning;    Automatic diagnosis;   

DOI  :  10.1016/j.neucom.2020.07.145

来源: Elsevier

【 摘 要 】

Diabetic Retinopathy (DR) is a severe complication of chronic diabetes causing significant visual deterioration and may lead to blindness with delay of being treated. Exudative diabetic maculopathy, a form of macular edema where hard exudates (HE) develop, is a frequent cause of visual deterioration in DR. The detection of HE comprises a significant role in the DR diagnosis. In this paper, an automatic exudates detection method based on superpixel multi-feature extraction and patch-based deep convolutional neural network is proposed. Firstly, superpixels, regarded as candidates, are generated on each resized image using the superpixel segmentation algorithm called Simple Linear Iterative Clustering (SLIC). Then, 25 features extracted from resized images and patches are generated on each feature. Patches are subsequently used to train a deep convolutional neural network, which distinguishes the hard exudates from the background. Experiments conducted on three publicly available datasets (DiaretDB1, e-ophtha EX and IDRiD) demonstrate that our proposed methodology achieved superior HE detection when compared with current state-of-art algorithms. (C) 2020 Elsevier B.V. All rights reserved.

【 授权许可】

Free