16 December 2013 Red lesion detection using background estimation and lesions characteristics in diabetic retinal image
Author Affiliations +
Abstract
Detection of red lesions [hemorrhages (HRs) and microaneurysms (MAs)] is crucial for the diagnosis of early diabetic retinopathy. A method based on background estimation and adapted to specific characteristics of HRs and MAs is proposed. Candidate red lesions are located by background estimation and Mahalanobis distance measure and then some adaptive postprocessing techniques, which include vessel detection, nonvessel exclusion based on shape analysis, and noise points exclusion by double-ring filter (only used for MAs detection), are conducted to remove nonlesion pixels. The method is evaluated on our collected image dataset, and experimental results show that it is better than or approximate to other previous approaches. It is effective to reduce the false-positive and false-negative results that arise from incomplete and inaccurate vessel structure.
© 2013 SPIE and IS&T
Dongbo Zhang, Yinghui Peng, Yao Yi, Xingyu Shang, "Red lesion detection using background estimation and lesions characteristics in diabetic retinal image," Journal of Electronic Imaging 22(4), 043024 (16 December 2013). https://doi.org/10.1117/1.JEI.22.4.043024 . Submission:
JOURNAL ARTICLE
17 PAGES


SHARE
Back to Top