Diagnosis of Diabetic Retinopathy through Retinal Fundus Images and 3D Convolutional Neural Networks with Limited Number of Samples
Table 8
Class-wise MCC values for the multiclass classification tasks without augmentation, with random weak Gaussian blurred augmentation, with random shift augmentation, and with combined augmentations.
Method
MCC (mild)
MCC (moderate)
MCC (no)
MCC (proliferate)
MCC (severe)
Without augmentation
0.1803
0.043
0.1599
0.4756
0.1484
With random weak Gaussian blurred augmentation
0.1238
0.0639
0.0773
0.3103
0.1093
With random shifted augmentation
0.077
-0.0176
0.0821
0.3933
0.1194
With combined augmentations
0.1264
0.0695
0.1051
0.4232
0.097
Test set validated on the model trained without augmentation