Effect of software manipulation (Photoshop) of digitised retinal images onthe grading of diabetic retinopathy

Aims-To determine whether processing of digitised retinal Images using a "s harpen" filter improves the ability to grade diabetic retinopathy. Methods-150 macula centred retinal images were taken as 35 mm colour transp arencies representing a spectrum of diabetic retinopathy, digitised, and gr aded in random order before and after the application of a sharpen filter ( Adobe Photoshop). Digital enhancement of contrast and brightness was perfor med and a X2 digital zoom was utilised. The grades from the unenhanced and enhanced digitised images were compared with the same retinal fields viewed as slides. Results-Overall agreement in retinopathy grade from the digitised images im proved from 83.3% (125/150) to 94.0% (141/150) with sight threatening diabe tic retinopathy (STDR) correctly identified in 95.5% (84/88) and 98.9% (87/ 88) of cases when using unenhanced and enhanced images respectively. In tot al, five images were overgraded and four undergraded from the enhanced imag es compared with 17 and eight images respectively when using unenhanced ima ges. Conclusion-This study demonstrates that the already good agreement in gradi ng performance can be further improved by software manipulation or processi ng of digitised retinal images.