Abstract
Purpose::
To compare accuracy of plus disease diagnosis by retinopathy of prematurity (ROP) experts to that of a computer-based image analysis system, Retinal Image multiScale Analysis (RISA).
Methods::
Twenty-two recognized ROP experts independently interpreted a set of 34 wide-angle retinal photographs for presence of plus disease. A reference standard was defined based on majority vote of experts. Images were analyzed using individual and linear combinations of computer-based system parameters for arterioles and venules: integrated curvature (IC), diameter, and tortuosity index (TI). Sensitivity, specificity, and receiver operating characteristic areas under the curve (AUC) for plus disease diagnosis compared to the reference standard were determined for each expert, and for the computer-based system.
Results::
Among the 22 experts, sensitivity ranged from 0.308-1.000, specificity ranged from 0.571-1.000, and AUC ranged from 0.784-1.000. Among individual computer system parameters, venular IC had highest AUC (0.821). Among linear combinations of computer system parameters, the combination of arteriolar IC, arteriolar TI, venular IC, venular diameter, and venular TI had highest AUC (0.967).
Conclusions::
Accuracy of recognized ROP experts for plus disease diagnosis is imperfect. A computer-based image analysis system can be modeled to diagnose plus disease with comparable or better accuracy than that of human experts.
Keywords: retinopathy of prematurity • imaging/image analysis: clinical • clinical (human) or epidemiologic studies: systems/equipment/techniques