International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 182 - Issue 17 |
Published: Sep 2018 |
Authors: Priyanka Kaushik, S. R. Nirmala |
![]() |
Priyanka Kaushik, S. R. Nirmala . A Study on Speckle Noise Removal and Segmentation of Retinal Layers in OCT Image Analysis. International Journal of Computer Applications. 182, 17 (Sep 2018), 25-33. DOI=10.5120/ijca2018917874
@article{ 10.5120/ijca2018917874, author = { Priyanka Kaushik,S. R. Nirmala }, title = { A Study on Speckle Noise Removal and Segmentation of Retinal Layers in OCT Image Analysis }, journal = { International Journal of Computer Applications }, year = { 2018 }, volume = { 182 }, number = { 17 }, pages = { 25-33 }, doi = { 10.5120/ijca2018917874 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2018 %A Priyanka Kaushik %A S. R. Nirmala %T A Study on Speckle Noise Removal and Segmentation of Retinal Layers in OCT Image Analysis%T %J International Journal of Computer Applications %V 182 %N 17 %P 25-33 %R 10.5120/ijca2018917874 %I Foundation of Computer Science (FCS), NY, USA
The survey paper shows the application of Optical Coherence Tomography images for detection of retinopathy. Image analysis methods enormously help in distinguishing different eye ailments. Currently, determination of retinal diseases depends mostly upon optical imaging techniques. Optical coherence tomography (OCT) is a routine diagnostic imaging method used worldwide in the evaluation of retinal diseases using the cross-sectional view of the retinal layers. The primary challenge in automatic identification and analysis of retinal disease cases is the presence of speckle noise and variation across edge boundaries. Due to the complexity of retinal structures, the tediousness of manual segmentation and variation from different specialists, many methods have been proposed to aid with this analysis. Therefore, efforts are being made to improve clinical decision making based on automated analysis of OCT data which will result in improving the accuracy, precision, and computational speed of segmentation methods, as well as reducing the amount of manual interaction.