Automatic grading of nuclear cataracts from slit-lamp lens images using group sparsity regression.
Cataracts, which result from lens opacification, are the leading cause of blindness worldwide. Current methods for determining the severity of cataracts are based on manual assessments that may be weakened by subjectivity. In this work, we propose a system to automatically grade the severity of nuclear cataracts from slit-lamp images. We introduce a new feature for cataract grading together with a group sparsity-based constraint for linear regression, which performs feature selection, parameter selection and regression model training simultaneously. In experiments on a large database of 5378 images, our system outperforms the state-of-the-art by yielding with respect to clinical grading a mean absolute error (epsilon) of 0.336, a 69.0% exact integral agreement ratio (R0), a 85.2% decimal grading error < or = 0.5 (Re0.5), and a 98.9% decimal grading error < or = 1.0 (Re1.0). Through a more objective grading of cataracts using our proposed system, there is potential for better clinical management of the disease.
Duke Scholars
Altmetric Attention Stats
Dimensions Citation Stats
Published In
DOI
Publication Date
Volume
Issue
Start / End Page
Location
Related Subject Headings
- Severity of Illness Index
- Sensitivity and Specificity
- Reproducibility of Results
- Regression Analysis
- Pattern Recognition, Automated
- Ophthalmoscopy
- Lighting
- Image Interpretation, Computer-Assisted
- Image Enhancement
- Humans
Citation
Published In
DOI
Publication Date
Volume
Issue
Start / End Page
Location
Related Subject Headings
- Severity of Illness Index
- Sensitivity and Specificity
- Reproducibility of Results
- Regression Analysis
- Pattern Recognition, Automated
- Ophthalmoscopy
- Lighting
- Image Interpretation, Computer-Assisted
- Image Enhancement
- Humans