Share Email Print

Proceedings Paper

New loss functions for medical image registration based on VoxelMorph
Author(s): Yongpei Zhu; Zicong Zhou Sr.; Guojun Liao Sr.; Kehong Yuan
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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 Lsim (Φ) and a smoothing term Lsmooth(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 Lsmooth (Φ) by the Laplacian of Φ. In the second step, we add the term control function F to the Lsmooth (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.

Paper Details

Date Published: 10 March 2020
PDF: 8 pages
Proc. SPIE 11313, Medical Imaging 2020: Image Processing, 113132E (10 March 2020); doi: 10.1117/12.2550030
Show Author Affiliations
Yongpei Zhu, Tsinghua Univ. (China)
Zicong Zhou Sr., The Univ. of Texas at Arlington (United States)
Guojun Liao Sr., The Univ. of Texas at Arlington (United States)
Kehong Yuan, Tsinghua Univ. (China)

Published in SPIE Proceedings Vol. 11313:
Medical Imaging 2020: Image Processing
Ivana Išgum; Bennett A. Landman, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?