No abstract

The widespread availability of electronic imaging devices throughout the medical community is leading to a growing body of research on image processing and analysis to diagnose retinal disease such as diabetic retinopathy (DR). Productive computer-based screening of large, at-risk populations at low cost requires robust, automated image analysis. In this paper we present results for the automatic detection of the optic nerve and localization of the macula using digital red-free fundus photography. Our method relies on the accurate segmentation of the vasculature of the retina followed by the determination of spatial features describing the density, average thickness, and average orientation of the vasculature in relation to the position of the optic nerve. Localization of the macula follows using knowledge of the optic nerve location to detect the horizontal raphe of the retina using a geometric model of the vasculature. We report 90.4% detection performance for the optic nerve and 92.5% localization performance for the macula for red-free fundus images representing a population of 345 images corresponding to 269 patients with 18 different pathologies associated with DR and other common retinal diseases such as age-related macular degeneration.

Three-wavelength digital holography is applied to obtain surface height measurements over several microns of range, while simultaneously maintaining the low noise precision of the single wavelength phase measurement. The precision is preserved by the use of intermediate synthetic wavelength steps generated from the three wavelengths and the use of hierarchical optical phase unwrapping. As the complex wave-front of each wavelength can be captured simultaneously in one digital image, real-time performance is achievable.

Diabetic macular edema (DME) is a common vision threatening complication of diabetic retinopathy. In a large scale screening environment DME can be assessed by detecting exudates (a type of bright lesions) in fundus images. In this work, two new methods for the detection of exudates are presented. The methods do not require a lesion training set so the need to ground-truth data is avoided with significant time savings and independence from human error. We evaluate our algorithm with a new publicly available dataset from various ethnic groups and levels of DME. Also, we compare our results with two recent exudate segmentation algorithms on the same dataset. In all of our tests, our algorithms are either outperforming or in line with existing methods. Additionally, the computational time is one order of magnitude less than similar methods.

The probabilistic nature of content-based image retrieval permits us to make statistically relevant predictions regarding the presence, severity, and manifestations of common retinal diseases from digital images in an automated and deterministic manner.