TY - JOUR
T1 - Fine-tuning TrailMap
T2 - The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images
AU - Oostrom, Marjolein
AU - Muniak, Michael A.
AU - Eichler West, Rogene M.
AU - Akers, Sarah
AU - Pande, Paritosh
AU - Obiri, Moses
AU - Wang, Wei
AU - Bowyer, Kasey
AU - Wu, Zhuhao
AU - Bramer, Lisa M.
AU - Mao, Tianyi
AU - Webb-Robertson, Bobbie Jo M.
N1 - Publisher Copyright:
© 2024 Public Library of Science. All rights reserved.
PY - 2024/3
Y1 - 2024/3
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85188914092&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85188914092&partnerID=8YFLogxK
U2 - 10.1371/journal.pone.0293856
DO - 10.1371/journal.pone.0293856
M3 - Article
C2 - 38551935
AN - SCOPUS:85188914092
SN - 1932-6203
VL - 19
JO - PloS one
JF - PloS one
IS - 3 March
M1 - e0293856
ER -