Deep reinforcement learning for subpixel neural tracking
File(s)
Published version
Author(s)
Type
Conference Paper
Abstract
Automatically tracing elongated structures, such as axons and blood vessels, is a challenging problem in the field of biomedical imaging, but one with many downstream applications. Real, labelled data is sparse, and existing algorithms either lack robustness to different datasets, or otherwise require significant manual tuning. Here, we instead learn a tracking algorithm in a synthetic environment, and apply it to tracing axons. To do so, we formulate tracking as a reinforcement learning problem, and apply deep reinforcement learning techniques with a continuous action space to learn how to track at the subpixel level. We train our model on simple synthetic data and test it on mouse cortical two-photon microscopy images. Despite the domain gap, our model approaches the performance of a heavily engineered tracker from a standard analysis suite for neuronal microscopy. We show that fine-tuning on real data improves performance, allowing better transfer when real labelled data is available. Finally, we demonstrate that our model's uncertainty measure-a feature lacking in hand-engineered trackers-corresponds with how well it tracks the structure.
Date Issued
2019-01-01
Date Acceptance
2019-02-01
Citation
Proceedings of Machine Learning Research, 2019, 102, pp.130-150
Publisher
OpenReview
Start Page
130
End Page
150
Journal / Book Title
Proceedings of Machine Learning Research
Volume
102
Copyright Statement
© 2019 The Author(s). Creative Commons Attribution license (CC BY 4.0)
License URL
Identifier
https://openreview.net/forum?id=HJxrNvv0JN
Source
Medical Imaging with Deep Learning
Publication Status
Published
Start Date
2019-07-08
Finish Date
2019-07-10
Coverage Spatial
London, UK
Date Publish Online
2019-02-28