Skip to main content

Table 1 Configurations designed and tested for the semantic segmentation of the full image

From: A comparison between two semantic deep learning frameworks for the autosomal dominant polycystic kidney disease segmentation based on magnetic resonance images

Network ID

Number of layers per encoder

Number of convolutional filters per layer

Learner

VGG-16

[2 2 3 3 3]

[64 128 256 512 512]

ADAM

S-CNN-1

[3 2 3 3 3]

[64 128 256 512 512]

ADAM

S-CNN-2

[3 2 3 3 3]

[96 128 256 512 512]

ADAM

  1. Each layer is a sequence of a convolutional layer, a batch normalization layer and a ReLu layer