A Novel Hybrid Convolutional Neural Network Approach for the Stomach Intestinal Early Detection Cancer Subtype Classification

Algorithm 1

The Proposed Algorithm.

	Input: Image label pairs {(Xi, Yi)}i = 1 − N, Bag-label pairs {(Bi,Yi-ins)}i = 1 − N
	Training:
	For n = 1 to N do
	For s = 1 to S do
	Multi-scale Transform: Gs : { (Xi, Yi) }i = 1 − N
	For b = 1 to Bn do
	Feature extractor: Gfeatures : { (Bi-s,Yi-ins) }i = 1 − N
	yij = arg max {P (yij = k)}
	Training end till last epoch
	End