NEW OBJECTIVE CLASSIFICATION-SYSTEM FOR NUCLEAR OPACIFICATION

We have developed an autonomous objective classification scheme for de gree of nuclear opacification. The algorithm was developed by using a series of color 35-mm slides acquired with a Topcon photo slit-lamp mi croscope and use of standard camera settings. The photographs were dig itized, and first, and second-order gray-level statistics were extract ed from within circular regions of the nucleus. Classifications of sev erity were performed by using these features as input to a neural netw ork. Training versus classification performance was tested by using ph otographs of different eyes, and test/retest classification reproducib ility was evaluated by using paired photographs of the same eyes; We d emonstrate good performance of the classifier against subjective asses sments rendered by the Wilmer grading system [Invest. Ophthalmol. Visu al Sci. 29, 73 (1988)] and markedly better test/retest reproducibility . (C) 1997 Optical Society of America.