April 2, 2024
Journal Article

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

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. 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.

Published: April 2, 2024

Citation

Oostrom M.T., M. Muniak, R.M. Eichler West, S.M. Akers, P. Pande, M.Y. Obiri, and W. Wang, et al. 2024. Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images. PLoS One 19, no. 3:Art. No. e0293856. PNNL-SA-190650. doi:10.1371/journal.pone.0293856

Research topics