DOE CODE   /    Search Results   /    pnnl/brain_ohsu

pnnl/brain_ohsu

RESOURCE

Publicly Accessible Repository
https://github.com/pnnl/brain_ohsu
https://doi.org/10.11578/dc.20231004.1

SAVE / SHARE



PNNL Badge

Abstract

Light sheet microscopy has made possible the 3D imaging of both fixed and live biological tissue, with samples as large as the entire mouse brain. We fine-tuned an existing model, TrailMap, using expert labeled data from axonal structures in neocortex. Without changing the network architecture, we implemented nnU-Net framework modifications in data augmentation, data foreground sampling, window learning rate, and the inference overlap method. The resulting model from these combined approaches yielded an improved F1 score
Developers:
Oostrom, Marjolein [1] ;  Bramer, Lisa [1]
  1. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Release Date:
2023-10-04
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Licenses:
BSD 2-clause "Simplified" License
Sponsoring Org.:
Code ID:
114417
Site Accession Number:
Battelle IPID 32777-E
Research Org.:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Country of Origin:
United States

RESOURCE

Publicly Accessible Repository
https://github.com/pnnl/brain_ohsu
https://doi.org/10.11578/dc.20231004.1

SAVE / SHARE



PNNL Badge

Citation Formats

Oostrom, Marjolein, and Bramer, Lisa. pnnl/brain_ohsu. Computer Software. https://github.com/pnnl/brain_ohsu. USDOE. 04 Oct. 2023. Web. doi:10.11578/dc.20231004.1.
Oostrom, Marjolein, & Bramer, Lisa. (2023, October 04). pnnl/brain_ohsu. [Computer software]. https://github.com/pnnl/brain_ohsu. https://doi.org/10.11578/dc.20231004.1.
Oostrom, Marjolein, and Bramer, Lisa. "pnnl/brain_ohsu." Computer software. October 04, 2023. https://github.com/pnnl/brain_ohsu. https://doi.org/10.11578/dc.20231004.1.
@misc{ doecode_114417,
title = {pnnl/brain_ohsu},
author = {Oostrom, Marjolein and Bramer, Lisa},
abstractNote = {Light sheet microscopy has made possible the 3D imaging of both fixed and live biological tissue, with samples as large as the entire mouse brain. We fine-tuned an existing model, TrailMap, using expert labeled data from axonal structures in neocortex. Without changing the network architecture, we implemented nnU-Net framework modifications in data augmentation, data foreground sampling, window learning rate, and the inference overlap method. The resulting model from these combined approaches yielded an improved F1 score},
doi = {10.11578/dc.20231004.1},
url = {https://doi.org/10.11578/dc.20231004.1},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20231004.1}},
year = {2023},
month = {oct}
}