Retinal Imaging and Image Analysis

To estimate the prevalence and distribution of age-related macular degeneration (AMD) in the United States by age, race/ethnicity, and gender. Summary prevalence estimates of drusen 125 microm or larger, neovascular AMD, and geographic atrophy were prepared separately for black and white persons in 5-year age intervals starting at 40 years. The estimated rates were based on a meta-analysis of recent population-based studies in the United States, Australia, and Europe. These rates were applied to 2000 US Census data and to projected US population figures for 2020 to estimate the number of the US population with drusen and AMD. The overall prevalence of neovascular AMD and/or geographic atrophy in the US population 40 years and older is estimated to be 1.47% (95% confidence interval, 1.38%-1.55%), with 1.75 million citizens having AMD. The prevalence of AMD increased dramatically with age, with more than 15% of the white women older than 80 years having neovascular AMD and/or geographic atrophy. More than 7 million individuals had drusen measuring 125 microm or larger and were, therefore, at substantial risk of developing AMD. Owing to the rapidly aging population, the number of persons having AMD will increase by 50% to 2.95 million in 2020. Age-related macular degeneration was far more prevalent among white than among black persons. Age-related macular degeneration affects more than 1.75 million individuals in the United States. Owing to the rapid aging of the US population, this number will increase to almost 3 million by 2020.

After [15], [31], [19], [8], [25], [5], minimum cut/maximum flow algorithms on graphs emerged as an increasingly useful tool for exact or approximate energy minimization in low-level vision. The combinatorial optimization literature provides many min-cut/max-flow algorithms with different polynomial time complexity. Their practical efficiency, however, has to date been studied mainly outside the scope of computer vision. The goal of this paper is to provide an experimental comparison of the efficiency of min-cut/max flow algorithms for applications in vision. We compare the running times of several standard algorithms, as well as a new algorithm that we have recently developed. The algorithms we study include both Goldberg-Tarjan style "push-relabel" methods and algorithms based on Ford-Fulkerson style "augmenting paths." We benchmark these algorithms on a number of typical graphs in the contexts of image restoration, stereo, and segmentation. In many cases, our new algorithm works several times faster than any of the other methods, making near real-time performance possible. An implementation of our max-flow/min-cut algorithm is available upon request for research purposes.

A method is presented for automated segmentation of vessels in two-dimensional color images of the retina. This method can be used in computer analyses of retinal images, e.g., in automated screening for diabetic retinopathy. The system is based on extraction of image ridges, which coincide approximately with vessel centerlines. The ridges are used to compose primitives in the form of line elements. With the line elements an image is partitioned into patches by assigning each image pixel to the closest line element. Every line element constitutes a local coordinate frame for its corresponding patch. For every pixel, feature vectors are computed that make use of properties of the patches and the line elements. The feature vectors are classified using a kappaNN-classifier and sequential forward feature selection. The algorithm was tested on a database consisting of 40 manually labeled images. The method achieves an area under the receiver operating characteristic curve of 0.952. The method is compared with two recently published rule-based methods of Hoover et al. and Jiang et al. The results show that our method is significantly better than the two rule-based methods (p < 0.01). The accuracy of our method is 0.944 versus 0.947 for a second observer.