Skip to main content

Table 4 Distribution of lesion types of ISIC-2019 before and after Augmentation

From: Skin-Net: a novel deep residual network for skin lesions classification using multilevel feature extraction and cross-channel correlation with detection of outlier

Lesion Type

No. of original images (Before Augmentation)

Augmentation

No. of augmented images (after Augmentation)

MEL

4522

No

4522

NV

12875

No

12875

BCC

3323

No

3323

AK

867

Yes

3476

BKL

2624

No

2624

DF

239

Yes

3549

VASC

253

Yes

4281

SCC

628

Yes

3423

 

Total No. of images 25331

 

Total No. of images 38073