Unsupervised multi-modal style transfer for cardiac MR segmentation
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
In this work, we present a fully automatic method to segment cardiac structures from late-gadolinium enhanced (LGE) images without using labelled LGE data for training, but instead by transferring the anatomical knowledge and features learned on annotated balanced steady-state free precession (bSSFP) images, which are easier to acquire. Our framework mainly consists of two neural networks: a multi-modal image translation network for style transfer and a cascaded segmentation network for image segmentation. The multi-modal image translation network generates realistic and diverse synthetic LGE images conditioned on a single annotated bSSFP image, forming a synthetic LGE training set. This set is then utilized to fine-tune the segmentation network pre-trained on labelled bSSFP images, achieving the goal of unsupervised LGE image segmentation. In particular, the proposed cascaded segmentation network is able to produce accurate segmentation by taking both shape prior and image appearance into account, achieving an average Dice score of 0.92 for the left ventricle, 0.83 for the myocardium, and 0.88 for the right ventricle on the test set.
Date Issued
2020-01-23
Date Acceptance
2019-07-01
Citation
2020, pp.209-219
ISBN
9783030390730
ISSN
0302-9743
Publisher
Springer International Publishing
Start Page
209
End Page
219
Copyright Statement
© Springer Nature Switzerland AG 2020. The final publication is available at Springer via https://doi.org/10.1007/978-3-030-39074-7_22
Identifier
https://link.springer.com/chapter/10.1007%2F978-3-030-39074-7_22
Source
MICCAI STACOM Workshop
Subjects
eess.IV
eess.IV
cs.CV
cs.LG
Artificial Intelligence & Image Processing
Publication Status
Published
Start Date
2019-10-13
Finish Date
2019-10-13
Coverage Spatial
Shenzhen, China
Date Publish Online
2020-01-23