Top-down and bottom-up strategies in lesion detection of background diabetic retinopathy

Bright lesions in the form of exudates and cotton wool spots while dark lesions consisting of hemorrhages are main evidences of background diabetic retinopathy that require early detection and precise classification. Based on different properties of bright lesions and dark lesions, bottom-up and top-down strategies are applied respectively to cope with the main difficulties in lesions detection such as inhomogeneous illumination. In bright lesion detection, a three-stage, bottom-up approach is applied. After local contrast enhancement preprocessing stage, two-step Improved Fuzzy C-Means is applied in Luv color space to segment candidate bright lesion areas. Finally, a hierarchical SVM classification structure is applied to classify bright non-lesion areas, exudates and cotton wool spots. In hemorrhage detection, a top-down strategy is adopted. The hemorrhages are located in the ROI firstly by calculating the evidence value of every pixel using SVM. Then their boundaries can be accurately segmented in the post-processing stage.

[1]  C. J. Taylor,et al.  Image analysis of fundus photographs. The detection and measurement of exudates associated with diabetic retinopathy. , 1989, Ophthalmology.

[2]  Lloyd Paul Aiello,et al.  Preventive Eye Care in People With Diabetes Is Cost-Saving to the Federal Government: Implications for health-care reform , 1994, Diabetes Care.

[3]  Huiqi. Li.  Model-based approach for automated feature extraction in color fundus images , 2003 .

[4]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[5]  David Keating,et al.  Automatic detection ofdiabetic retinopathy using anartificial neural network: ascreening tool , 1996 .

[6]  Aly A. Farag,et al.  A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data , 2002, IEEE Transactions on Medical Imaging.

[7]  Chanjira Sinthanayothin,et al.  Image analysis for automatic diagnosis of diabetic retinopathy. , 1999 .

[8]  Mong-Li Lee,et al.  An effective approach to detect lesions in color retinal images , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[9]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Sankar K. Pal,et al.  Fuzzy models for pattern recognition , 1992 .

[11]  Majid Mirmehdi,et al.  Automatic Recognition of Exudative Maculopathy using Fuzzy C- Means Clustering and Neural Networks , 2001 .

[12]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  S.C. Lee,et al.  A general algorithm for recognizing small, vague, and imager-alike objects in a nonuniformly illuminated medical diagnostic image , 1998, Conference Record of Thirty-Second Asilomar Conference on Signals, Systems and Computers (Cat. No.98CH36284).

[14]  P. Sharp,et al.  Automated detection and quantification of retinal exudates , 1993, Graefe's Archive for Clinical and Experimental Ophthalmology.