A Novel Hybrid Deep Learning Model for Metastatic Cancer Detection

Table 5

Comparative study of the proposed model with recent ML/DL models.

Publication	Cancer type	Models	Classification type	Data set	Accuracy (%)
[45]	Breast cancer	ANN	Binary class	SNPs	69%
[46]	Colon carcinomatosis	BN	Binary class	Clinical, pathologic	71%
[47]	Multiple myeloma	SVM, DCNN	Multi-class	DDSM (CBIS-DDSM)	71%, 93%
[48]	Breast cancer	DCNNs	Bi-multi-class	Kaggle	90%, 93%
[49]	Breast cancer	DCNNs	Multi-class	Wisconsin diagnostic breast cancer (WDBC)	88%
[50]	Breast cancer	ResNet	Multi-class	Kaggle	85%
[51]	Breast cancer	Pretrained CNN	Binary class	Kaggle	90%
Proposed model	Breast cancer	AlexNet-GRU	Binary class	Kaggle	99.50%