Abstract
Deep learning has been applied with great success to the segmentation of 3D X-Ray Computed Tomography (CT) scans. Establishing the credibility of these segmentations requires uncertainty quantification (UQ) to identify problem areas. Bayesian neural networks (BNNs), which use variational inference to learn the posterior distribution of the neural network weights, have been proposed to incorporate UQ into deep learning models. This software is an implementation of a novel 3D Bayesian convolutional neural network (BCNN) that provides accurate binary segmentations and uncertainty maps for 3D volumes. In particular, the uncertainty maps generated by this BCNN capture continuity and visual gradients, making them interpretable as confidence intervals for segmentation usable in numerical simulations. SAND2019-12927 M
Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy's National Nuclear Security Administration under contract DE-NA0003525.
- Developers:
-
LaBonte, Tyler [1]
- Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA (United States)
- Release Date:
- 2019-10-30
- Project Type:
- Open Source, Publicly Available Repository
- Software Type:
- Scientific
- Programming Languages:
-
Python
- Version:
- v.1
- Licenses:
-
MIT License
- Sponsoring Org.:
-
USDOEPrimary Award/Contract Number:NA0003525
- Code ID:
- 33206
- Site Accession Number:
- SCR#2432
- Research Org.:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Country of Origin:
- United States
Citation Formats
LaBonte, Tyler M.
Bayesian Segmentation (BCNN) v.1.
Computer Software.
https://github.com/sandialabs/bcnn.
USDOE.
30 Oct. 2019.
Web.
doi:10.11578/dc.20201104.7.
LaBonte, Tyler M.
(2019, October 30).
Bayesian Segmentation (BCNN) v.1.
[Computer software].
https://github.com/sandialabs/bcnn.
https://doi.org/10.11578/dc.20201104.7.
LaBonte, Tyler M.
"Bayesian Segmentation (BCNN) v.1." Computer software.
October 30, 2019.
https://github.com/sandialabs/bcnn.
https://doi.org/10.11578/dc.20201104.7.
@misc{
doecode_33206,
title = {Bayesian Segmentation (BCNN) v.1},
author = {LaBonte, Tyler M.},
abstractNote = {Deep learning has been applied with great success to the segmentation of 3D X-Ray Computed Tomography (CT) scans. Establishing the credibility of these segmentations requires uncertainty quantification (UQ) to identify problem areas. Bayesian neural networks (BNNs), which use variational inference to learn the posterior distribution of the neural network weights, have been proposed to incorporate UQ into deep learning models. This software is an implementation of a novel 3D Bayesian convolutional neural network (BCNN) that provides accurate binary segmentations and uncertainty maps for 3D volumes. In particular, the uncertainty maps generated by this BCNN capture continuity and visual gradients, making them interpretable as confidence intervals for segmentation usable in numerical simulations. SAND2019-12927 M
Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy's National Nuclear Security Administration under contract DE-NA0003525.},
doi = {10.11578/dc.20201104.7},
url = {https://doi.org/10.11578/dc.20201104.7},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20201104.7}},
year = {2019},
month = {oct}
}