Data Homogeneity Effect in Deep Learning-Based Prediction of Type 1 Diabetic Retinopathy

Figure 5

The images present the original (a) and superimposed Grad-CAM activation maps ((b)–(i)) of the selected normal color fundus image. All models gave a true-negative prediction. There was a high variation in the activation map when given a normal fundus image. Some models focus on the optic disc ((e) and (g)), whereas others highlight the retinal vessels ((b), (c), and (g)), or macular region ((d), (h), (f), and (i)).