Stochastic optimization with randomized smoothing for image registration
详细信息 查看全文
- 作者：Wei Sun ; a ; d ; sunwei@ieee.org" class="auth_mail" title="E-mail the corresponding author ; sunweidemail@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Dirk H.J. Poota ; b ; Ihor Smala ; Xuan Yangc ; Wiro J. Niessena ; b ; Stefan Kleina
- 关键词：Image registration ; Local minima ; Stochastic gradient descent ; Randomized smoothing
- 刊名：Medical Image Analysis
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：35
- 期：Complete
- 页码：146-158
- 全文大小：3858 K
文摘
- •
To suppress local minima, we smooth the cost function of image registration with a randomized smoothing (RS) technique.
- •
A convolution-based smoothing technique in which the original cost function is convolved by a Gaussian distribution with an efficient randomized optimization procedure.
- •
The RS technique is applied to translation, rigid, affine and B-spline transformation models.
- •
Experiments on 2D artificial images, 2D cell images, 3D lung CT, and 3D brain MRI scans confirm the benefits of the method.