Skip to main content

Automatic grading of nuclear cataracts from slit-lamp lens images using group sparsity regression.

Publication ,  Journal Article
Xu, Y; Gao, X; Lin, S; Wong, DWK; Liu, J; Xu, D; Cheng, C-Y; Cheung, CY; Wong, TY
Published in: Med Image Comput Comput Assist Interv
2013

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

Med Image Comput Comput Assist Interv

DOI

Publication Date

2013

Volume

16

Issue

Pt 2

Start / End Page

468 / 475

Location

Germany

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

APA
Chicago
ICMJE
MLA
NLM
Xu, Y., Gao, X., Lin, S., Wong, D. W. K., Liu, J., Xu, D., … Wong, T. Y. (2013). Automatic grading of nuclear cataracts from slit-lamp lens images using group sparsity regression. Med Image Comput Comput Assist Interv, 16(Pt 2), 468–475. https://doi.org/10.1007/978-3-642-40763-5_58
Xu, Yanwu, Xinting Gao, Stephen Lin, Damon Wing Kee Wong, Jiang Liu, Dong Xu, Ching-Yu Cheng, Carol Y. Cheung, and Tien Yin Wong. “Automatic grading of nuclear cataracts from slit-lamp lens images using group sparsity regression.Med Image Comput Comput Assist Interv 16, no. Pt 2 (2013): 468–75. https://doi.org/10.1007/978-3-642-40763-5_58.
Xu Y, Gao X, Lin S, Wong DWK, Liu J, Xu D, et al. Automatic grading of nuclear cataracts from slit-lamp lens images using group sparsity regression. Med Image Comput Comput Assist Interv. 2013;16(Pt 2):468–75.
Xu, Yanwu, et al. “Automatic grading of nuclear cataracts from slit-lamp lens images using group sparsity regression.Med Image Comput Comput Assist Interv, vol. 16, no. Pt 2, 2013, pp. 468–75. Pubmed, doi:10.1007/978-3-642-40763-5_58.
Xu Y, Gao X, Lin S, Wong DWK, Liu J, Xu D, Cheng C-Y, Cheung CY, Wong TY. Automatic grading of nuclear cataracts from slit-lamp lens images using group sparsity regression. Med Image Comput Comput Assist Interv. 2013;16(Pt 2):468–475.

Published In

Med Image Comput Comput Assist Interv

DOI

Publication Date

2013

Volume

16

Issue

Pt 2

Start / End Page

468 / 475

Location

Germany

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