An Automatic System for Classification of Nuclear Sclerosis from Slit-Lamp Photographs

Abstract

A robust and automatic system has been developed to detect the visual axis and extract important feature landmarks from slit-lamp photographs, and objectively grade the severity of nuclear sclerosis based on the intensities of those landmarks. Using linear regression, we first select the features that play important roles in classification, and then fit a linear grading function. We evaluated the grading function using human grades as error bounds for “ground truth” grades, and compared the machine grades with the human grades. As expected, the automatic system significantly speeds up the process of grading, and grades computed are consistent and reproducible. Machine grading time for one image is less than 2 seconds on a Pentium III 996MHz machine while human grading takes about 2 minutes. Statistical results show that the predicted grades by the system are very reliable. For the testing set of 141 images, with correct grading defined by a tolerance of one grade level difference from the human grade, the automated system has a grading accuracy of 95.8% based on the AREDS grading scale.

We would like to thank Dennis Hafford and Jane Armstrong for providing assistance and the slit-lamp photographs, Dr. Grace Wahba for discussions on statistical analysis methods, Dr. Nicola Ferrier for early collaborative discussions on feature detection methods, and Xin Qi for help in R programming. The support of the National Eye Institute of the National Institutes of Health under Grant Nos. N01-EY-0-2130 and EY-12652 is gratefully acknowledged.

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.