This paper presents a method to determine the number of visible layers in the outer retina and perform segmentation. Each layer in the outer retina is represented by a Gaussian function, and multiple models with a different number of layers are used to form the outer retina. Parameters of competing models are calculated by using maximum likelihood estimation after which the model that best describes the data is selected. Model selection is based on the goodness of fit and model complexity thereby ensuring that the model that best represents the data is chosen. The method was applied to in-vivo macular images of human retinas acquired by optical coherence tomography after conversion to attenuation coefficients. Examples of detected number of visible layers and corresponding segmentation results are shown in both normal and retinitis pigmentosa affected retinas.
|Number of pages
|Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
|Published - Aug 2015
- Likelihood Functions
- Retinitis Pigmentosa
- Tomography, Optical Coherence