Independent Component Analysis for Vision-inspired Classification of Retinal Images with Age-related Macular Degeneration

The purpose of this paper is to present a novel approach for extracting image-based features for classifying age-related macular degeneration (AMD) in digital retinal images. 100 retinal images were classified by an ophthalmologist into 12 categories based on the visual characteristics of the disease. Independent Component Analysis (ICA) was used to extract features at different spatial scales to be used as input to a classifier. The classification used a type of regression, partial least squares. In this experiment ICA replicated the ophthalmologist's visual classification by correctly assigning all 12 images from two of the classes.

[1]  T. Adali,et al.  Unmixing fMRI with independent component analysis , 2006, IEEE Engineering in Medicine and Biology Magazine.

[2]  H. Wold.  Nonlinear Iterative Partial Least Squares (NIPALS) Modelling: Some Current Developments , 1973 .

[3]  Peter Soliz,et al.  Detection of low-amplitude in vivo intrinsic signals from an optical imager of retinal function , 2006, SPIE BiOS.

[4]  Robert F. Mullins,et al.  An Integrated Hypothesis That Considers Drusen as Biomarkers of Immune-Mediated Processes at the RPE-Bruch's Membrane Interface in Aging and Age-Related Macular Degeneration , 2001, Progress in Retinal and Eye Research.

[5]  N. Bressler,et al.  Relationship of drusen and abnormalities of the retinal pigment epithelium to the prognosis of neovascular macular degeneration. The Macular Photocoagulation Study Group. , 1990, Archives of ophthalmology.

[6]  David S. Shin,et al.  Computer-assisted, interactive fundus image processing for macular drusen quantitation. , 1999, Ophthalmology.

[7]  Michalis E. Zervakis,et al.  Detection and segmentation of drusen deposits on human retina: Potential in the diagnosis of age-related macular degeneration , 2003, Medical Image Anal..

[8]  Thomas J. Liesegang,et al.  An integrated hypothesis that considers drusen as biomarkers of immune-mediated processes at the RPE-Bruch’s membrane interface in aging and age-related macular degeneration.Hageman GS,∗ Luthert PJ, Chong NHV, Johnson LV, Anderson DH, Mullins RF. Prog Ret Eye Res 2001:20:705–732. , 2002 .

[9]  Zachary Roth,et al.  Age-related macular degeneration: economic burden and value-based medicine analysis. , 2005, Canadian journal of ophthalmology. Journal canadien d'ophtalmologie.

[10]  Max A. Viergever,et al.  Matching and integrated display of brain images from multiple modalities , 1995, Medical Imaging.

[11]  C. Curcio,et al.  Basal linear deposit and large drusen are specific for early age-related maculopathy. , 1999, Archives of ophthalmology.

[12]  Marios S. Pattichis,et al.  Spatiotemporal Independent Component Analysis for the Detection of Functional Responses in Cat Retinal Images , 2007, IEEE Transactions on Medical Imaging.

[13]  Young H. Kwon,et al.  Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features. , 2007, Investigative ophthalmology & visual science.

[14]  Bram van Ginneken,et al.  Automatic detection of red lesions in digital color fundus photographs , 2005, IEEE Transactions on Medical Imaging.

[15]  R L Cooper,et al.  Automated extraction and quantification of macular drusen from fundal photographs. , 1994, Australian and New Zealand journal of ophthalmology.

[16]  Sunanda Mitra,et al.  Full automation of morphological segmentation of retinal images: a comparison with human-based analysis , 2003, SPIE Medical Imaging.