Authors:
Masato Ito
and
Fumihiko Ino
Affiliation:
Osaka University, Japan
Keyword(s):
Image Registration, Nonrigid Registration, Deep Learning, Training Data.
Abstract:
In this paper, we propose an automated method for generating training sets required for realizing deep learning
based image registration. The proposed method minimizes effort for supervised learning by automatically
generating thousands of training sets from a small number of seed sets, i.e., tens of deformation vector fields
obtained with a conventional registration method. To automate this procedure, we solve an inverse problem
instead of a direct problem; we produce a floating image by applying a deformation vector fieldFto a reference
image and let the inverse vector of F be the ground truth for these images. In experiments, the proposed
method took 33 minutes to produce 169,890 training sets from approximately 670,000 2-D magnetic resonance
(MR) images and 30 seed sets. We further trained GoogLeNet with these training sets and performed holdout
validation to compare the proposed method with the conventional registration method in terms of recall and
precision. As a resu
lt, the proposed method increased recall and precision from 50% to 80%, demonstrating
the impact of deep learning for image registration problems.
(More)