Cargando…
Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images
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 au...
Autores principales: | , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Cold Spring Harbor Laboratory
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10634742/ https://www.ncbi.nlm.nih.gov/pubmed/37961439 http://dx.doi.org/10.1101/2023.10.23.563546 |
_version_ | 1785146233183010816 |
---|---|
author | 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 Jo |
author_facet | 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 Jo |
author_sort | Oostrom, Marjolein |
collection | PubMed |
description | 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 fine-tuning the final two layers of the neural network at a lower learning rate of the TrailMap model, we demonstrate an improved recall and an occasionally improved adjusted F1-score within our test dataset over using the originally trained TrailMap model. |
format | Online Article Text |
id | pubmed-10634742 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Cold Spring Harbor Laboratory |
record_format | MEDLINE/PubMed |
spelling | pubmed-106347422023-11-13 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 Jo bioRxiv Article 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 fine-tuning the final two layers of the neural network at a lower learning rate of the TrailMap model, we demonstrate an improved recall and an occasionally improved adjusted F1-score within our test dataset over using the originally trained TrailMap model. Cold Spring Harbor Laboratory 2023-10-23 /pmc/articles/PMC10634742/ /pubmed/37961439 http://dx.doi.org/10.1101/2023.10.23.563546 Text en https://creativecommons.org/publicdomain/zero/1.0/This article is a US Government work. It is not subject to copyright under 17 USC 105 and is also made available for use under a CC0 license (https://creativecommons.org/publicdomain/zero/1.0/) . |
spellingShingle | Article 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 Jo Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images |
title | Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images |
title_full | Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images |
title_fullStr | Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images |
title_full_unstemmed | Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images |
title_short | Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images |
title_sort | fine-tuning trailmap: the utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10634742/ https://www.ncbi.nlm.nih.gov/pubmed/37961439 http://dx.doi.org/10.1101/2023.10.23.563546 |
work_keys_str_mv | AT oostrommarjolein finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages AT muniakmichaela finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages AT eichlerwestrogenem finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages AT akerssarah finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages AT pandeparitosh finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages AT obirimoses finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages AT wangwei finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages AT bowyerkasey finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages AT wuzhuhao finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages AT bramerlisam finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages AT maotianyi finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages AT webbrobertsonbobbiejo finetuningtrailmaptheutilityoftransferlearningtoimprovetheperformanceofdeeplearninginaxonsegmentationoflightsheetmicroscopyimages |