Research Article
Macular Lesions Extraction Using Active Appearance Method
@INPROCEEDINGS{10.1007/978-3-319-29236-6_42, author={Jan Kubicek and Iveta Bryjova and Marek Penhaker}, title={Macular Lesions Extraction Using Active Appearance Method}, proceedings={Context-Aware Systems and Applications. 4th International Conference, ICCASA 2015, Vung Tau, Vietnam, November 26-27, 2015, Revised Selected Papers}, proceedings_a={ICCASA}, year={2016}, month={4}, keywords={Macular degeneration Optical coherence tomography Image processing Active contour Medical image segmentation MATLAB Geometrical parameters Macular lesions}, doi={10.1007/978-3-319-29236-6_42} }- Jan Kubicek
Iveta Bryjova
Marek Penhaker
Year: 2016
Macular Lesions Extraction Using Active Appearance Method
ICCASA
Springer
DOI: 10.1007/978-3-319-29236-6_42
Abstract
Age-related macular degeneration (ARMD) is one of the most widespread diseases of the eye fundus and is the most common cause of vision loss for those over the age of 60. There are several ways to diagnose ARMD. One of them is the Fundus Autofluorescence (FAF) method, and is one of the modalities of Heidelberg Engineering diagnostic devices. The BluePeakTM modality utilizes the fluorescence of lipofuscin (a pigment in the affected cells) to display the extent of the disease’s progression. In clinical practice is often quite complicated to perform assessment of precise parameters macular lesions. The main aim of the article is design of the method which is able to locate and consequently perform extraction of these lesions. The algorithm body is composed of several essential parts: image preprocessing, filtration of interested area and segmentation procedure. In the first step, extraction area of interest is performed. Filtration process should suppress adjacent structures. Final step is segmentation procedure. The main advantage is that the whole process is fully automatic. The result of segmentation is closed curve which is formed iteratively to edges of analyzed object. The resulting curve reflects geometrical parameters of analyzed structure. On the base this fact is quite easy to calculate perimeter and area of analyzed area.