TY - JOUR
T1 - Liver semantic segmentation algorithm based on improved deep adversarial networks in combination of weighted loss function on abdominal CT images
AU - Xia, Kaijian
AU - Yin, Hongsheng
AU - Qian, Pengjiang
AU - Jiang, Yizhang
AU - Wang, Shuihua
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2019
Y1 - 2019
N2 - Due to the space inconsistency between benchmark image and segmentation result in many existing semantic segmentation algorithms for abdominal CT images, an improved model based on the basic framework of DeepLab-v3 is proposed, and Pix2pix network is introduced as the generation adversarial model. Our proposed model realizes the segmentation framework combining deep feature with multi-scale semantic feature. In order to improve the generalization ability and training accuracy of the model, this paper proposes a combination of the traditional multi-classification cross-entropy loss function with the content loss function of generator output and the adversarial loss function of discriminator output. A large number of qualitative and quantitative experimental results show that the performance of our proposed semantic segmentation algorithm is better than the existing algorithms, and can improve the segmentation efficiency while ensuring the space consistency of the semantics segmentation for abdominal CT images.
AB - Due to the space inconsistency between benchmark image and segmentation result in many existing semantic segmentation algorithms for abdominal CT images, an improved model based on the basic framework of DeepLab-v3 is proposed, and Pix2pix network is introduced as the generation adversarial model. Our proposed model realizes the segmentation framework combining deep feature with multi-scale semantic feature. In order to improve the generalization ability and training accuracy of the model, this paper proposes a combination of the traditional multi-classification cross-entropy loss function with the content loss function of generator output and the adversarial loss function of discriminator output. A large number of qualitative and quantitative experimental results show that the performance of our proposed semantic segmentation algorithm is better than the existing algorithms, and can improve the segmentation efficiency while ensuring the space consistency of the semantics segmentation for abdominal CT images.
KW - Semantic segmentation
KW - atrous space pyramid pooling
KW - game adversarial
KW - generation adversarial networks
KW - multi-scale features
KW - weighted loss function
UR - http://www.scopus.com/inward/record.url?scp=85070257589&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2019.2929270
DO - 10.1109/ACCESS.2019.2929270
M3 - Article
AN - SCOPUS:85070257589
SN - 2169-3536
VL - 7
SP - 96349
EP - 96358
JO - IEEE Access
JF - IEEE Access
M1 - 8764548
ER -