TY - GEN
T1 - An Improved Convolutional Neural Network for 3D Unsupervised Medical Image Registration
AU - Cai, Gangcheng
AU - Wang, Jiajun
AU - Chi, Zheru
N1 - Publisher Copyright:
© 2020 IEEE.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2020/12/11
Y1 - 2020/12/11
N2 - In recent years, convolutional neural networks have been widely used in medical image registration. VTN network has been the most popular architecture in medical registration community. Although the structure has outstanding overall performance in medical image registration, the VTN architecture seems to own drawbacks in focusing on the areas of interest and extracting features efficiently. Therefore, we propose an improved version called CIRVTN based on the traditional VTN model where global Residual paths, the Inception module and the CBAM attention module are introduced. The introduction of global Residual path can not only alleviate the problem of gradient disappearance, but also improve the reusability of medical image features. Upon introducing the Inception and CBAM attention modules, the adaptability of the network to the diversities in shapes and locations of tissue contents in medical images are improved. Extensive experiments on three professional medical liver datasets showed that the network proposed in this paper outperforms the traditional VTN both in Dice score and computing efficiency.
AB - In recent years, convolutional neural networks have been widely used in medical image registration. VTN network has been the most popular architecture in medical registration community. Although the structure has outstanding overall performance in medical image registration, the VTN architecture seems to own drawbacks in focusing on the areas of interest and extracting features efficiently. Therefore, we propose an improved version called CIRVTN based on the traditional VTN model where global Residual paths, the Inception module and the CBAM attention module are introduced. The introduction of global Residual path can not only alleviate the problem of gradient disappearance, but also improve the reusability of medical image features. Upon introducing the Inception and CBAM attention modules, the adaptability of the network to the diversities in shapes and locations of tissue contents in medical images are improved. Extensive experiments on three professional medical liver datasets showed that the network proposed in this paper outperforms the traditional VTN both in Dice score and computing efficiency.
KW - convolutional neural network
KW - medical image
KW - registration
KW - unsupervised
UR - http://www.scopus.com/inward/record.url?scp=85101689546&partnerID=8YFLogxK
U2 - 10.1109/ICCC51575.2020.9344977
DO - 10.1109/ICCC51575.2020.9344977
M3 - Conference article published in proceeding or book
AN - SCOPUS:85101689546
T3 - 2020 IEEE 6th International Conference on Computer and Communications, ICCC 2020
SP - 1908
EP - 1914
BT - 2020 IEEE 6th International Conference on Computer and Communications, ICCC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th IEEE International Conference on Computer and Communications, ICCC 2020
Y2 - 11 December 2020 through 14 December 2020
ER -