Retinal Spot Lesion Detection Using Adaptive Multiscale Morphological Processing
We present a new spot lesion detection algorithm for retinal images with background diabetic retinopathy (DR) pathologies. The highlight of this algorithm is its capability to deal with all DR-related spot lesions of various sizes and shapes that is accomplished by a unique adaptive multiscale morphological processing technique. A scale map is generated to delineate lesion areas based an edge model, and it is used to fuse multiscale morphological processing results for lesion enhancements. The local/releative entropy thresholding techniques are employed to segment lesion regions, and a scale-guided validation process is used to remove over-detections based on the scale map. The proposed algorithm is tested on 30 retinal images where all spot lesions are hand-labelled for performance evaluation. Compared with two existing algorithms, the proposed one significantly improves the overall performance of spot lesion detection producing higher sensitivity and/or predictive values.
KeywordsDiabetic Retinopathy Retinal Image Lesion Detection Optimal Scale Early Treatment Diabetic Retinopathy Study
Unable to display preview. Download preview PDF.
- 1.ETDRS Research Group: Grading dabetic retinopathy from seteoscopic color fundus photographos – an extension of the modified Airelie House Classification (ETDRS report number 10). Ophthalmology 98, 786–806 (1991)Google Scholar
- 5.Frame, A.J., Undrill, P.E., Cree, M.J., Olson, J.A., McHardy, K.C., Sharp, P.F., Forrester, J.V.: A comparison of computer based classification methods applied to the detection of microaneurysms in ophthalmic fluorescein angiograms. Computers in Biology and Medicine, 225–238 (1998)Google Scholar
- 8.Zhang, X., Chutatape, O.: Top-down and bottom-up strategies in lesion detection of background diabetic retinopathy. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 422–428 (2005)Google Scholar
- 10.Vincent, L.: Morphological grayscale reconstruction: Definition, efficient algorithms and applications in image analysis. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 633–635 (1992)Google Scholar
- 11.Mukhopadhyay, S., Chanda, B.: An edge preserving noise smoothing technique using multiscale morphology. Signal Processing, 527–544 (2002)Google Scholar
- 12.vanBeck, P.J.L.: Edge-Based Image Representation and Coding. PhD thesis, Delft University of Technology, the Netherlands (1995)Google Scholar