Detection, extraction and quantitative measurement of atrophic regions on retinal surface in color fundus images

The problem of automatic detection and extraction of pathological images still remains an unsolved problem. The aim of this paper is to develop an automatic method for the detection, extraction and quantitative analysis of atrophic regions that occurred on retinal surface in retinal diseases. Its automatic quantification is important for determining disease progression and helpful for clinical diagnosis of disease. The paper utilized an adaptive threshold for various regions of color fundus image which determined simply by different blocking models. The algorithm is computationally efficient and fast. Quantitative evaluation experiments on 300 color fundus images show a mean sensitivity/specificity of 98.7/96.6 % for our approach.