SynCellFactory: Generative Data Augmentation for Cell Tracking

TL;DR

SynCellFactory is a novel generative approach using ControlNet to produce realistic synthetic cell videos, significantly enhancing deep learning-based cell tracking performance with limited training data.

Contribution

It introduces SynCellFactory, a new method leveraging ControlNet for photorealistic synthetic cell video augmentation to improve cell tracking.

Findings

Boosts cell tracking accuracy with synthetic data

Effective in scenarios with limited original training data

Generates realistic cell videos mirroring authentic microscopy patterns

Abstract

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.