of normal cells

Dataset 2 400 1000 (T:320, V: 80) (T: 800, V:200)

Dataset 3 4000 10,000 (T:3200, V:800) (T:8000, V:2000) Dataset 4 4000 10,000 (T:3200, V:800) (T:8000, V:2000)

The first half (Dataset 1) was used for data augmentation. The second half (Dataset 2) was used for training and testing.

Dataset 3 was obtained using the spatial domain interpolation and Dataset 4 was obtained using the feature domain (via

Training (infected, normal) Validation (infected, normal) Testing (infected, normal) Dataset 3 (3200, 8000) Dataset 3 (800, 2000) Dataset 2 (400, 1000) Dataset 4 (3200, 8000) Dataset 3 (800, 2000) Dataset 2 (400, 1000) Dataset 2 (320, 800) Dataset 2 (80, 200) Dataset 3 (4000, 10,000) Dataset 2 (320, 800) Dataset 2 (80, 200) Dataset 4 (4000, 10,000)

Table 3. Several combinations of datasets used in training, validation and testing of the convolutional neural network.

Simulation results are shown in Figures 8 and 9.

Table 1. The original image dataset is split into two halves.

Table 2. The augmented image dataset from dataset 1 in Table 1.
