Feasibility of Using Improved Convolutional Neural Network to Classify BI-RADS 4 Breast Lesions: Compare Deep Learning Features of the Lesion Itself and the Minimum Bounding Cube of Lesion

Table 1

Tumor classification network parameters.

Layer_name	Input_size	Detailed_parameters	Output_size
conv		, ,
		, ,
3D_CBAM		convolution
conv		, ,
		, ,
3D_CBAM		convolution
conv		, ,
		, ,
3D_CBAM		convolution
conv		, ,
		, ,
3D_CBAM		convolution
conv		, ,
		, ,
3D_CBAM		convolution
Flatten			8192
Full connection	8192		2048
Full connection	2048		512
Softmax	512		2

“res_conv” is a residual convolution block which contains shortcut connection, and “” means the block has convolution blocks that share the same parameters. 3D_CBAM uses convolutions to adjust the channel numbers of the current feature map.