Deep Reinforcement Learning for Subpixel Neural Tracking

Tianhong Dai, Magda Dubois, Kai Arulkumaran, Jonathan Campbell, Cher Bass, Benjamin Billot, Fatmatulzehra Uslu, Vincenzo de Paola, Claudia Clopath, Anil Anthony Bharath

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

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.
Original languageEnglish
Title of host publicationProceedings of Machine Learning Research
EditorsTom Vercauteren
Pages130-150
Number of pages21
Volume102
Publication statusPublished - 1 Aug 2019

Bibliographical note

International Conference on Medical Imaging with Deep Learning

Fingerprint

Dive into the research topics of 'Deep Reinforcement Learning for Subpixel Neural Tracking'. Together they form a unique fingerprint.

Cite this