Preprint
A deep learning network with differentiable dynamic programming for retina OCT surface segmentation
ArXiv.org
10/08/2022
DOI: 10.48550/arXiv.2210.06335
Abstract
Multiple-surface segmentation in Optical Coherence Tomography (OCT) images is
a challenge problem, further complicated by the frequent presence of weak image
boundaries. Recently, many deep learning (DL) based methods have been developed
for this task and yield remarkable performance. Unfortunately, due to the
scarcity of training data in medical imaging, it is challenging for DL networks
to learn the global structure of the target surfaces, including surface
smoothness. To bridge this gap, this study proposes to seamlessly unify a U-Net
for feature learning with a constrained differentiable dynamic programming
module to achieve an end-to-end learning for retina OCT surface segmentation to
explicitly enforce surface smoothness. It effectively utilizes the feedback
from the downstream model optimization module to guide feature learning,
yielding a better enforcement of global structures of the target surfaces.
Experiments on Duke AMD (age-related macular degeneration) and JHU MS (multiple
sclerosis) OCT datasets for retinal layer segmentation demonstrated very
promising segmentation accuracy.
Details
- Title: Subtitle
- A deep learning network with differentiable dynamic programming for retina OCT surface segmentation
- Creators
- Hui XieWeiyu XuXiaodong Wu
- Resource Type
- Preprint
- Publication Details
- ArXiv.org
- DOI
- 10.48550/arXiv.2210.06335
- ISSN
- 2331-8422
- Language
- English
- Date posted
- 10/08/2022
- Academic Unit
- Electrical and Computer Engineering; Radiation Oncology; The Iowa Institute for Biomedical Imaging
- Record Identifier
- 9984303930102771
Metrics
36 Record Views