A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retina

• Published in: IEEE transactions on medical imaging 2002-10, Vol.21 (10), p.1236-1243
• Main Authors: Walter, T., Klein, J.-C., Massin, P., Erginay, A.
• Format: Article
• Language: English
• Subjects: Algorithms; Associated diseases and complications; Biological and medical sciences; Color; Computer aided diagnosis; Diabetes; Diabetes. Impaired glucose tolerance; Diabetic retinopathy; Diabetic Retinopathy - metabolism; Diabetic Retinopathy - pathology; Endocrine pancreas. Apud cells (diseases); Endocrinopathies; Endoscopy; Exudates and Transudates - metabolism; Fluorescein Angiography - methods; Fundus Oculi; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image processing; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Observer Variation; Ophthalmology; Ophthalmoscopes; Ophthalmoscopy; Ophthalmoscopy - methods; Optic Disk - anatomy & histology; Optic Disk - metabolism; Optical detectors; Optical filters; Optical sensors; Pattern Recognition, Automated; Quality Control; Reproducibility of Results; Retina; Retina - metabolism; Retina - pathology; Retinopathy; Sensitivity and Specificity
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2002.806290

In the framework of computer assisted diagnosis of diabetic retinopathy, a new algorithm for detection of exudates is presented and discussed. The presence of exudates within the macular region is a main hallmark of diabetic macular edema and allows its detection with a high sensitivity. Hence, detection of exudates is an important diagnostic task, in which computer assistance may play a major role. Exudates are found using their high grey level variation, and their contours are determined by means of morphological reconstruction techniques. The detection of the optic disc is indispensable for this approach. We detect the optic disc by means of morphological filtering techniques and the watershed transformation. The algorithm has been tested on a small image data base and compared with the performance of a human grader. As a result, we obtain a mean sensitivity of 92.8% and a mean predictive value of 92.4%. Robustness with respect to changes of the parameters of the algorithm has been evaluated.