Towards an Accurate MRI Acute Ischemic Stroke Lesion Segmentation Based on Bioheat Equation and U-Net Model

Table 2

Detail of the architecture of U-Net.

Layers	Architectures	Output
Input	Image ()
conv1	2@Conv ()/
	conv2	2@Conv ()/
conv3		2@Conv ()/
	conv4	2@Conv ()/
drop4	Dropout ()
	conv5	2@Conv ()/
drop5	Dropout ()
up6	Upsampling conv ()/Relu
Concatination	[drop4, up6]
conv6	2@Conv ()/
up7	Upsampling conv ()/Relu
Concatination	[conv3, up7]
conv7	2@Conv ()/
up8	Up-sampling conv ()/Relu
Concatination	[conv2, up8]
conv8	2@Conv ()/
up9	Upsampling conv ()/Relu
Concatination	[conv1, up9]
conv9	2@Conv ()/
conv10	Conv () Sigmoid
Output	Segmentation map