Optimal Wavelet Transform for the Detection of Microaneurysms in Retina Photographs

• Published in: IEEE transactions on medical imaging Vol. 27; no. 9; pp. 1230 - 1241
• Main Authors: Quellec, G., Lamard, M., Josselin, P.M., Cazuguel, G., Cochener, B., Roux, C.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2008; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Algorithms; Aneurysm - pathology; Artificial Intelligence; Computer Science; Diabetes; Diabetic retinopathy; Diabetic Retinopathy - pathology; Engineering Sciences; Fluorescein Angiography - methods; genetic algorithm; Genetic algorithms; Human health and pathology; Humans; Image analysis; Image Interpretation, Computer-Assisted - methods; Lesions; Life Sciences; microaneurysms; optimal wavelet transform; Pathology; Pattern Recognition, Automated - methods; Photography - methods; Reproducibility of Results; Retina; Retinal Artery - pathology; Retinopathy; Retinoscopy - methods; Sensitivity and Specificity; Signal and Image processing; Studies; template matching; Wavelet analysis; Wavelet transforms; genetic algorithm; template matching; microaneurysms; diabetic retinopathy; optimal wavelet transform
• ISSN: 0278-0062; 1558-254X; 1558-254X; 1558-0062
• DOI: 10.1109/TMI.2008.920619

In this paper, we propose an automatic method to detect microaneurysms in retina photographs. Microaneurysms are the most frequent and usually the first lesions to appear as a consequence of diabetic retinopathy. So, their detection is necessary for both screening the pathology and follow up (progression measurement). Automating this task, which is currently performed manually, would bring more objectivity and reproducibility. We propose to detect them by locally matching a lesion template in sub- bands of wavelet transformed images. To improve the method performance, we have searched for the best adapted wavelet within the lifting scheme framework. The optimization process is based on a genetic algorithm followed by Powell's direction set descent. Results are evaluated on 120 retinal images analyzed by an expert and the optimal wavelet is compared to different conventional mother wavelets. These images are of three different modalities: there are color photographs, green filtered photographs, and angiographs. Depending on the imaging modality, microaneurysms were detected with a sensitivity of respectively 89.62%, 90.24%, and 93.74% and a positive predictive value of respectively 89.50%, 89.75%, and 91.67%, which is better than previously published methods.