Abstract
Deep learning is emerging as a powerful approach for bioimage analysis. Its use in cell tracking is limited by the scarcity of annotated data for the training of deep-learning models. Moreover, annotation, training, prediction, and proofreading currently lack a unified user interface. We present ELEPHANT, an interactive platform for 3D cell tracking that addresses these challenges by taking an incremental approach to deep learning. ELEPHANT provides an interface that seamlessly integrates cell track annotation, deep learning, prediction, and proofreading. This enables users to implement cycles of incremental learning starting from a few annotated nuclei. Successive prediction-validation cycles enrich the training data, leading to rapid improvements in tracking performance. We test the software's performance against state-of-the-art methods and track lineages spanning the entire course of leg regeneration in a crustacean over 1 week (504 timepoints). ELEPHANT yields accurate, fully-validated cell lineages with a modest investment in time and effort.
Highlights
Recent progress in deep learning has led to significant advances in bioimage analysis (Moen et al, 2019; Ouyang et al, 2018; Weigert et al, 2018)
We have addressed these challenges by establishing ELEPHANT (Efficient learning using sparse human annotations for nuclear tracking), an interactive web-friendly platform for cell tracking, which seamlessly integrates manual annotation with deep learning and proofreading of the results
ELEPHANT employs the tracking-b y-d etection paradigm (Maška et al, 2014), which involves initially the detection of nuclei in 3D and subsequently their linking over successive timepoints to generate tracks
Summary
Recent progress in deep learning has led to significant advances in bioimage analysis (Moen et al, 2019; Ouyang et al, 2018; Weigert et al, 2018). Because the quality and quantity of the training data are crucial for the performance of deep learning, users must invest significant time and effort in annotation at the start of the project (Moen et al, 2019). Deep learning applications are often limited by accessibility to computing power (high-e nd GPU) We have addressed these challenges by establishing ELEPHANT (Efficient learning using sparse human annotations for nuclear tracking), an interactive web-friendly platform for cell tracking, which seamlessly integrates manual annotation with deep learning and proofreading of the results. ELEPHANT is implemented as an extension of Mastodon (https://github.com/mastodon-sc/mastodon; Mastodon Science, 2021), an open-source framework for large-scale tracking deployed in Fiji (Schindelin et al, 2012) It implements a client- server architecture, in which the server provides a deep learning environment equipped with sufficient GPU (Figure 1—figure supplement 1)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
