Cataracts are the leading cause of blindness worldwide. Cataract surgery is the number one surgery performed in the United States on the Medicare population with approximately 1.3 million per year; the number two performed intervention with associated costs is YAG capsulotomy. Research into the natural history of different types of cataract and factors that may prevent or promote cataractogenesis therefore is a high priority. Such research demands a valid reproducible system for determining the severity of lens opacities that is consistent over time. Furthermore, because cataracts develop slowly over time, a system with sufficient sensitivity to assess small changes is highly desirable. The PI has developed the means of classifying degree of nuclear cataract based on analysis of slitlamp microscope imagery, and of cortical and PSC cataract based on retro-illumination imagery. The nuclear classifier, which is a neural network that uses first and second order gray level features within the image of the nucleus, demonstrates reproducibility that significantly exceeds that of the subjective human assessment. The cortical/PSC classifier shows reliability in differentiating between regions of opacification and various artifacts associated with retro-illumination imagery, and employs some novel processing algorithms developed by us. He proposes to continue our development of the capability to assess cataract type and degree of severity. Specifically the PI proposes to perform an evaluation of the sensitivity of our nuclear, cortical, and PSC cataract classification system to detect change over time, further develop our capabilities by simple modifications to a commercially available electronic retro-illumination camera to allow the capture of image sequences at known longitudinal positions, and to perform preliminary clinical evaluation of the ability of this new system along with previously developed classification algorithms to track very small changes in post-operative posterior capsule opacification (PCO). The evaluation of the existing classification systems for nuclear, cortical, and PSC cataract will establish their sensitivity to detect small changes. The resulting comprehensive classification system will have wide applicability in prospective clinical trials of anti-cataract agents and in epidemiologic studies of risk factors and preventive measures in cataractogenesis. The PCO classification system should find wide applicability in studies of the natural history, risk factors, and interventions related to reducing the rate and severity of this complication.

Agency
National Institute of Health (NIH)
Institute
National Eye Institute (NEI)
Type
Research Project (R01)
Project #
2R01EY010857-03
Application #
2396889
Study Section
Visual Sciences A Study Section (VISA)
Project Start
1995-05-01
Project End
1999-05-31
Budget Start
1997-09-01
Budget End
1999-05-31
Support Year
3
Fiscal Year
1997
Total Cost
Indirect Cost
Name
Johns Hopkins University
Department
Type
Organized Research Units
DUNS #
045911138
City
Baltimore
State
MD
Country
United States
Zip Code
21218
Friedman, D S; Duncan, D D; Munoz, B et al. (1999) Digital image capture and automated analysis of posterior capsular opacification. Invest Ophthalmol Vis Sci 40:1715-26
Duncan, D D; Shukla, O B; West, S K et al. (1997) New objective classification system for nuclear opacification. J Opt Soc Am A Opt Image Sci Vis 14:1197-204