SynCellFactory: Generative Data Augmentation for Cell Tracking
This addresses data scarcity for researchers in biomedical imaging, but is incremental as it builds on existing ControlNet architecture.
The paper tackles the problem of limited training data for cell tracking in biomedical research by introducing SynCellFactory, a generative data augmentation method that synthesizes realistic cell videos, and shows it boosts deep learning model performance, especially with sparse data.
Cell tracking remains a pivotal yet challenging task in biomedical research. The full potential of deep learning for this purpose is often untapped due to the limited availability of comprehensive and varied training data sets. In this paper, we present SynCellFactory, a generative cell video augmentation. At the heart of SynCellFactory lies the ControlNet architecture, which has been fine-tuned to synthesize cell imagery with photorealistic accuracy in style and motion patterns. This technique enables the creation of synthetic yet realistic cell videos that mirror the complexity of authentic microscopy time-lapses. Our experiments demonstrate that SynCellFactory boosts the performance of well-established deep learning models for cell tracking, particularly when original training data is sparse.