Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images

Oostrom, Marjolein; Muniak, Michael A.; Eichler West, Rogene M.; Akers, Sarah; Pande, Paritosh; Obiri, Moses; Wang, Wei; Bowyer, Kasey; Wu, Zhuhao; Bramer, Lisa M.; Mao, Tianyi; Webb-Robertson, Bobbie M.

doi:10.1371/journal.pone.0293856

Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images

Journal Article · Fri Mar 29 00:00:00 EDT 2024 · PLoS ONE

DOI:https://doi.org/10.1371/journal.pone.0293856· OSTI ID:2331271

^[1]; ^[2]; Eichler West, Rogene M. ^[1]; Akers, Sarah ^[1]; Pande, Paritosh ^[1]; Obiri, Moses ^[1]; Wang, Wei ^[3]; Bowyer, Kasey ^[3]; Wu, Zhuhao ^[3]; ^[1]; Mao, Tianyi ^[2]; ^[1]

Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Oregon Health & Science Univ., Portland, OR (United States)
Weill Cornell Medicine, New York, NY (United States)

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. However, segmentation and quantification of that data remains a time-consuming manual undertaking. Machine learning methods promise the possibility of automating this process. This study seeks to advance the performance of prior models through optimizing transfer learning. We fine-tuned the existing TrailMap model using expert-labeled data from noradrenergic axonal structures in the mouse brain. By changing the cross-entropy weights and using augmentation, we demonstrate a generally improved adjusted F1-score over using the originally trained TrailMap model within our test datasets.

View Accepted Manuscript (DOE)

Research Organization:: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)

Sponsoring Organization:: USDOE Laboratory Directed Research and Development (LDRD) Program; National Institutes of Health (NIH)

Grant/Contract Number:: AC05-76RL01830

OSTI ID:: 2331271

Report Number(s):: PNNL-SA--190650

Journal Information:: PLoS ONE, Journal Name: PLoS ONE Journal Issue: 3 Vol. 19; ISSN 1932-6203

Publisher:: Public Library of ScienceCopyright Statement

Country of Publication:: United States

Language:: English

References (23)

Fine Tuning U-Net for Ultrasound Image Segmentation: Which Layers? Amiri, Mina; Brooks, Rupert; Rivaz, Hassan Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data https://doi.org/10.1007/978-3-030-33391-1_27	book	October 2019
PyTorch Imambi, Sagar; Prakash, Kolla Bhanu; Kanagachidambaresan, G. R. Programming with TensorFlow, p. 87-104 https://doi.org/10.1007/978-3-030-57077-4_10	book	January 2021
Elimination of galanin synthesis in noradrenergic neurons reduces galanin in select brain areas and promotes active coping behaviors Tillage, Rachel P.; Sciolino, Natale R.; Plummer, Nicholas W. Brain Structure and Function, Vol. 225, Issue 2 https://doi.org/10.1007/s00429-020-02035-4	journal	February 2020
Multimodal 3D Mouse Brain Atlas Framework with the Skull-Derived Coordinate System Perens, Johanna; Salinas, Casper Gravesen; Roostalu, Urmas Neuroinformatics, Vol. 21, Issue 2 https://doi.org/10.1007/s12021-023-09623-9	journal	February 2023
Neural Networks of the Mouse Neocortex Zingg, Brian; Hintiryan, Houri; Gou, Lin Cell, Vol. 156, Issue 5 https://doi.org/10.1016/j.cell.2014.02.023	journal	February 2014
Saturated Reconstruction of a Volume of Neocortex Kasthuri, Narayanan; Hayworth, Kenneth Jeffrey; Berger, Daniel Raimund Cell, Vol. 162, Issue 3 https://doi.org/10.1016/j.cell.2015.06.054	journal	July 2015
Three-Dimensional Adipose Tissue Imaging Reveals Regional Variation in Beige Fat Biogenesis and PRDM16-Dependent Sympathetic Neurite Density Chi, Jingyi; Wu, Zhuhao; Choi, Chan Hee J. Cell Metabolism, Vol. 27, Issue 1 https://doi.org/10.1016/j.cmet.2017.12.011	journal	January 2018
Geometry processing of conventionally produced mouse brain slice images Agarwal, Nitin; Xu, Xiangmin; Gopi, M. Journal of Neuroscience Methods, Vol. 306 https://doi.org/10.1016/j.jneumeth.2018.04.008	journal	August 2018
High-Speed and Scalable Whole-Brain Imaging in Rodents and Primates Seiriki, Kaoru; Kasai, Atsushi; Hashimoto, Takeshi Neuron, Vol. 94, Issue 6 https://doi.org/10.1016/j.neuron.2017.05.017	journal	June 2017
Mesoscale microscopy and image analysis tools for understanding the brain Tyson, Adam L.; Margrie, Troy W. Progress in Biophysics and Molecular Biology, Vol. 168 https://doi.org/10.1016/j.pbiomolbio.2021.06.013	journal	January 2022
Fiji: an open-source platform for biological-image analysis Schindelin, Johannes; Arganda-Carreras, Ignacio; Frise, Erwin Nature Methods, Vol. 9, Issue 7 https://doi.org/10.1038/nmeth.2019	journal	June 2012
From the connectome to brain function Bargmann, Cornelia I.; Marder, Eve Nature Methods, Vol. 10, Issue 6 https://doi.org/10.1038/nmeth.2451	journal	May 2013
A comprehensive thalamocortical projection map at the mesoscopic level Hunnicutt, Barbara J.; Long, Brian R.; Kusefoglu, Deniz Nature Neuroscience, Vol. 17, Issue 9 https://doi.org/10.1038/nn.3780	journal	August 2014
Morphological diversity of single neurons in molecularly defined cell types Peng, Hanchuan; Xie, Peng; Liu, Lijuan Nature, Vol. 598, Issue 7879 https://doi.org/10.1038/s41586-021-03941-1	journal	October 2021
nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation Isensee, Fabian; Jaeger, Paul F.; Kohl, Simon A. A. Nature Methods, Vol. 18, Issue 2 https://doi.org/10.1038/s41592-020-01008-z	journal	December 2020
Mapping mesoscale axonal projections in the mouse brain using a 3D convolutional network Friedmann, Drew; Pun, Albert; Adams, Eliza L. Proceedings of the National Academy of Sciences, Vol. 117, Issue 20 https://doi.org/10.1073/pnas.1918465117	journal	May 2020
The light-sheet microscopy revolution Girkin, J. M.; Carvalho, M. T. Journal of Optics, Vol. 20, Issue 5 https://doi.org/10.1088/2040-8986/aab58a	journal	April 2018
Automatic 3D neuron tracing using all-path pruning Peng, H.; Long, F.; Myers, G. Bioinformatics, Vol. 27, Issue 13 https://doi.org/10.1093/bioinformatics/btr237	journal	June 2011
The human connectome: a complex network Sporns, Olaf Annals of the New York Academy of Sciences, Vol. 1224, Issue 1 https://doi.org/10.1111/j.1749-6632.2010.05888.x	journal	January 2011
TeraStitcher - A tool for fast automatic 3D-stitching of teravoxel-sized microscopy images Bria, Alessandro; Iannello, Giulio BMC Bioinformatics, Vol. 13, Issue 1 https://doi.org/10.1186/1471-2105-13-316	journal	November 2012
Light-sheet microscopy: a tutorial Olarte, Omar E.; Andilla, Jordi; Gualda, Emilio J. Advances in Optics and Photonics, Vol. 10, Issue 1 https://doi.org/10.1364/AOP.10.000111	journal	January 2018
Light Sheet Fluorescence Microscopy: A Review Santi, Peter A. Journal of Histochemistry & Cytochemistry, Vol. 59, Issue 2 https://doi.org/10.1369/0022155410394857	journal	February 2011
TrakEM2 Software for Neural Circuit Reconstruction Cardona, Albert; Saalfeld, Stephan; Schindelin, Johannes PLoS ONE, Vol. 7, Issue 6 https://doi.org/10.1371/journal.pone.0038011	journal	June 2012

Similar Records

Data-driven Mapping of the Mouse Connectome: The utility of transfer learning to improve the performance of deep learning models performing axon segmentation on light-sheet microscopy images

Technical Report · Mon Sep 19 00:00:00 EDT 2022 · OSTI ID:1985702

pnnl/brain_ohsu

Software · Tue Oct 03 20:00:00 EDT 2023 · OSTI ID:code-114417

Data for The utility of transfer learning to improve the performance of deep learning in axon segmentation

Dataset · Mon Feb 05 23:00:00 EST 2024 · OSTI ID:2308772

Related Subjects

97 MATHEMATICS AND COMPUTING

Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images

Citation Formats

References (23)

Similar Records

Related Subjects