Value Proposition
· High Throughput Research Assay: perform experiments on the order of hours, compared to the order of months with existing methods.
· Adaptable Algorithm: method evolves as cell motility understanding expands, preventing obsolescence through new discoveries.
· Accessible and Integrable: label-free tracking using conventional microscopy equipment enables most research labs to implement the technology.
Technology Description
· Cell tracking methods are low throughput and face challenges in single-cell resolution and assessment of temporal data.
· Researchers at Johns Hopkins have developed a machine-vision and deep learning analysis method to automatically detect and track the migration of individual cells from time-lapsed videos without cell-labeling.
Unmet Need
· Cell migration plays a key role in normal development and disease processes; however, tools for rapid analysis of cell motility are lacking.
· Current assays do not allow for single cell analysis and require extensive time for manual tracking and thereby introduce user bias or require the use of fluorescently labeled cells which limit the manipulations and conditions for examination.
· Therefore, there is a strong need for a high-throughput analysis method to track individual cells in an unbiased and time-efficient manner.
Stage of Development
· Proof of concept
· Future work will entail training a more generalized deep learning model for a wider and more general deployment
Data Availability
N/A
Publication
Chu T, Lim Y, Sun Y, Wirtz D, Wu PH. Accelerated Discovery of Cell Migration Regulators Using Label-Free Deep Learning-Based Automated Tracking. bioRxiv [Preprint]. 2025 Apr 5:2025.04.01.646705. doi: 10.1101/2025.04.01.646705. PMID: 40236190; PMCID: PMC11996530.
