Automated Grading of Diabetic Retinopathy with Ultra-Widefield Fluorescein Angiography and Deep Learning

Figure 4

The confusion matrix of the classification results. The classification results of the original UWFA images achieved 100.00% accuracy for normal eyes, 94.50% for PDR, and 76.61% for NPDR, respectively. The classification results of the 7-SF images achieved 94.12% accuracy for normal eyes, 80.73% for PDR, and 54.97% for NPDR, respectively.

(a)

(b)