New loss functions for medical image registration based on VoxelMorph

Yongpei Zhu; Zicong Zhou Sr.; Guojun Liao Sr.; Kehong Yuan

doi:10.1117/12.2550030

10 March 2020 New loss functions for medical image registration based on VoxelMorph

Yongpei Zhu, Zicong Zhou Sr., Guojun Liao Sr., Kehong Yuan

Proceedings Volume 11313, Medical Imaging 2020: Image Processing; 113132E (2020) https://doi.org/10.1117/12.2550030
Event: SPIE Medical Imaging, 2020, Houston, Texas, United States

Abstract

Optimization of loss function is one of the research directions in medical image registration. A loss function of registration is the sum of two terms: a similarity term L_sim (Φ) and a smoothing term L_smooth(Φ). From variational method in differential geometry, control function is essential to generate better registration field Φ. Here, we propose a new registration loss function with novel smoothing terms using VoxelMorph based on control function and Laplacian operator. We divide the process into two steps. The first step is based on Laplacian operator. We replace the gradient of registration field Φ in L_smooth (Φ) by the Laplacian of Φ. In the second step, we add the term control function F to the L_smooth (Φ) in the first step, which is the key contribution of our method. We verify our method on two datasets including ADNI and IBSR, and obtain excellent improvement on MR image registration, with better convergence and gets higher average Dice and lower percentage of non-positive Jacobian locations compared with original loss function.

Citation Download Citation

Yongpei Zhu, Zicong Zhou Sr., Guojun Liao Sr., and Kehong Yuan "New loss functions for medical image registration based on VoxelMorph", Proc. SPIE 11313, Medical Imaging 2020: Image Processing, 113132E (10 March 2020); https://doi.org/10.1117/12.2550030

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available