CanaryTank: a plug-in husbandry behavior tracking system for health of fish facilities

Project Summary/Abstract Zebrafish, involved in research projects totalling over 450 million dollars of NIH funding in 2020, are the fastest growing animal model of human disease in medical research today. Thus, the health and wellbeing of medical research fish is paramount as the rigor and repeatability of experiments depends on it. Innovation in zebrafish husbandry systems is crucially needed because current state-of-the-art non intrusive systems only track water quality measures. No commercial husbandry system has adopted automatic monitoring of fish behavior using video, despite the fact that most factors crucial in assessing fish health and well being, such as hunger, anxiety, or light changes, produce well known behavioral signatures that a computer vision system could detect. Because many such signatures require high temporal resolution, milliseconds in the case of escape movements, video monitoring has been hampered by the need to create and process enormous data volumes. Here, the proposed effort aims at building upon our Phase I success of prototyping the proof-of-concept system codenamed “CanaryTanks”. We have installed CanaryTank with sentinel zebrafish populations directly into the racks of an existing fish facility and used our original "Remanent Imaging" paradigm to monitor and analyze fish swimming behavior. The system is capable of producing email reports of basic measures of activity, sleep and feeding as well as alerts when light cycles are disrupted. In this Phase II effort, we will improve our initial designs with commercialization in mind. The first aim builds on our current design to improve deployability and enhance behavior detection capabilities by capturing 3D data with a single camera. The second aim is (1) to enhance our system’s ability to build rich email reports and a dashboard for users to explore and replay events as well as historical data, and (2) to develop advanced detection and diagnostic algorithms using machine learning techniques. Sharing of curated data and analysis techniques to the community is also planned in this effort. The future vision is that the CanaryTank technology sets new standards in fish husbandry, real-time classification of complex behavior changes, and provides revolutionary, ubiquitous in-tank recording capabilities that can be leveraged beyond husbandry for collection of actual scientific experimental data.