A Novel Approach Based on Image Processing Algorithms for Microaneurysm Candidate Detection

Interpretting color fundus images by doctors is enhanced by computer-aided detection (CAD). Microaneurysm (MA) detection in CAD is an important step to identify the retinal diseases automatically. However, MA detection is still a challenging task due to the variations in retinal images. In this paper, a new MA extraction method is developed. The proposed method contains two steps: 1.) image pre-processing 2.) candidate extraction. The pre-processing stage includes a variety of operations such as binary region of interest (ROI) mask generation, median and Gaussian filtering, background subtraction and bright pixel determination. On the other hand, MA candidate extraction is carried out in five steps; 1.) The spiral sequence of gray scale values is obtained 2.) An increasing length segmentation approach is employed for partitioning of the spirally sequenced gray scale values 3.) Two new images are generated based on the mean gray scale values 4.) The newly generated images are thresholded 5.) All connected and elongated structures are removed. Our experiments and analysis show that our proposed method is efficient. Furthermore, we demonstrate that through experimental modification of a threshold parameter, our method has the potential to achieve over 90% accuracy.