Superimposition of eye fundus images for longitudinal analysis from large public health databasesReportar como inadecuado

Superimposition of eye fundus images for longitudinal analysis from large public health databases - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

1 IPRI - International Prevention Research Institute 2 Swansea University 3 DESW - Diabetic Eye Screening Wales 4 SIGPH@iPRI - Strathclyde Institute of Global Public Health at iPRI

Abstract : In this paper, we present a method for superimposition i.e. registration of eye fundus images from persons with diabetes screened over many years for Diabetic Retinopathy. The method is fully automatic and robust to camera changes and colour variations across the images both in space and time. All the stages of the process are designed for longitudinal analysis of cohort public health databases. The method relies on a model correcting two radial distortions and an affine transformation between pairs of images which is robustly fitted on salient points. Each stage involves linear estimators followed by non-linear optimisation. The model of image warping is also invertible for fast computation. The method has been validated 1. on a simulated montage with an average error of 0.81 pixels for one distortion respectively 1.08 pixels for two distortions and a standard deviation of 1.36 pixels resp. 3.09 in images of 1568 x 2352 pixels in both directions and 2 on public health databases with 69 patients with high quality images with 271 pairs and 268 pairs with a success rates of 96 % and 97 % and 5 patients with 20 pairs with low quality images with a success rate of 100%.

Keywords : eye fundus images image registration radial distortion invertible model longitudinal analysis public health databases

Autor: Guillaume Noyel - Rebecca Thomas - Gavin Bhakta - Andrew Crowder - David Owens - Peter Boyle -



Documentos relacionados