Utility of color information for segmentation of digital retinal images: neural-network-based approach

Paul W. Truitt; Peter Soliz; Denise Farnath M.D.; Sheila Coyne Nemeth

doi:10.1117/12.310879

Translator Disclaimer

24 June 1998 Utility of color information for segmentation of digital retinal images: neural-network-based approach

Paul W. Truitt, Peter Soliz, Denise Farnath M.D., Sheila Coyne Nemeth

Author Affiliations +

Proceedings Volume 3338, Medical Imaging 1998: Image Processing; (1998) https://doi.org/10.1117/12.310879
Event: Medical Imaging '98, 1998, San Diego, CA, United States

Abstract

The goal of this study was to determine the utility of red, green and blue color information in segmenting fundus images for two general categories of retinal tissue: anatomically normal and pathological. The pathologies investigated were microaneurysms and dot blot hemorrhages.

Citation Download Citation

Paul W. Truitt, Peter Soliz, Denise Farnath M.D., and Sheila Coyne Nemeth "Utility of color information for segmentation of digital retinal images: neural-network-based approach", Proc. SPIE 3338, Medical Imaging 1998: Image Processing, (24 June 1998); https://doi.org/10.1117/12.310879

ACCESS THE FULL ARTICLE