Hemorrhage detection in fundus image based on 2D Gaussian fitting and human visual characteristics

Abstract Hemorrhage is one of the early symptoms of diabetic retinopathy, so accurate detection of hemorrhage has important significance in building automatic screening system of diabetic retinopathy. In this paper, a method based on two dimensional (2D) Gaussian fitting and human visual characteristics is proposed. Firstly, brightness correction and contrast limited adaptive histogram equalization are used to preprocess original color fundus image. Secondly, candidate hemorrhages are extracted based on background estimation and watershed segmentation. Thirdly, 2D Gaussian fitting and human visual characteristics are used to extract visual features of candidate hemorrhages. Finally, hemorrhages are obtained from candidate hemorrhages based on visual features. The proposed method is evaluated on 219 fundus images of DIARETDB database. Experimental results show that overall average sensitivity, specificity and accuracy for hemorrhage in image level are 100%, 82% and 95.42% respectively, and overall average sensitivity and positive predictive value for hemorrhage in lesion level are 94.01% and 90.30% respectively. The results show that this method can realize automatic detection of hemorrhages in fundus image with high accuracy.

[1]  Wei-Ping Zhu,et al.  Multi-scale context for scene labeling via flexible segmentation graph , 2016, Pattern Recognit..

[2]  Huimin Lu,et al.  Deep adversarial metric learning for cross-modal retrieval , 2019, World Wide Web.

[3]  Bin Li,et al.  Wound intensity correction and segmentation with convolutional neural networks , 2017, Concurr. Comput. Pract. Exp..

[4]  Huimin Lu,et al.  Brain Intelligence: Go beyond Artificial Intelligence , 2017, Mobile Networks and Applications.

[5]  Huimin Lu,et al.  Low illumination underwater light field images reconstruction using deep convolutional neural networks , 2018, Future Gener. Comput. Syst..

[6]  Quan Zhou,et al.  Object-based attention: saliency detection using contrast via background prototypes , 2014 .

[7]  A. Ezhilarasi.  Multi-scale LBP and SVM Classification to Identify Diabetic Retinopathy in Lesions , 2015 .

[8]  Ho Chul Kang,et al.  A Study on Hemorrhage Detection Using Hybrid Method in Fundus Images , 2011, Journal of Digital Imaging.

[9]  Huimin Lu,et al.  Multi-scale deep context convolutional neural networks for semantic segmentation , 2017, World Wide Web.

[10]  Huimin Lu,et al.  Underwater image dehazing using joint trilateral filter , 2014, Comput. Electr. Eng..

[11]  Huimin Lu,et al.  Motor Anomaly Detection for Unmanned Aerial Vehicles Using Reinforcement Learning , 2018, IEEE Internet of Things Journal.

[12]  Jian-Xin Shen,et al.  [Algorithm of locally adaptive region growing based on multi-template matching applied to automated detection of hemorrhages]. , 2013, Guang pu xue yu guang pu fen xi = Guang pu.