Artificial intelligence-driven enhanced skin cancer diagnosis: leveraging convolutional neural networks with discrete wavelet transformation

Egyptian Journal of Medical Human Genetics

Table 1 Dataset, recent methods used with number of classes and size of the data used to detect skin cancer

Dataset	Data size	Methods Used	Total no. of classes	References
HAM10000	300	CNN with XGBoost	5	[14, 14]
HAM10000	10015	CNN	7	[33]
HAM10000	10015	AlexNet	7	[34]
HAM10000	1323	InsiNet	2	[35]
HAM10000	7470	ReNet50	7	[36]
HAM10000	6705	DCNN	2	[37]
HAM10000	16170	Anisotropic diffusion Filtering	2	[38]
ImageNet	279	DCNN VGG-16	2	[39]
ImageNet	3753	ECOC SVM	2	[40]
DermNet, Dermofit Image library, ISIC Archive	48373	MobileNetV2	2	[41]
ISIC	1000	SVM + RF	8	[42]
ISIC-2016		1280
ISIC-2017	2000	Region-based CNN	2	[43]
PH²	200

The dataset, recent methods employed, along with the number of classes and the dataset size utilized for skin cancer detection