CellNet -- Localizing Cells using Sparse and Noisy Point Annotations
This work addresses the bottleneck of annotation effort for cell counting in biological research, enabling high-throughput screening with minimal manual labeling.
The authors developed a regression-based deep learning method for counting cells in phase-contrast microscopy images using only sparse point annotations, reducing annotation effort. Their approach showed promising results compared to state-of-the-art 0-shot methods in low data regimes.
Counting living cells is an important step in many biological research workflows. Our collaborators at the Wellcome Sanger Institute study vital genes in humans via large scale saturation genome editing screening, which requires repeatedly counting cells a great number of times. Computer Vision based automation is crucial for high throughput and resource efficiency. In this work, we develop a regression-based deep learning computer vision algorithm to detect and count cells in phase-contrast microscopy images. To reduce annotation effort, which in practice often becomes a bottleneck, we focus on counting cells only using sparse point annotations, which are fast and easy to acquire. By comparison to state-of-the-art 0-shot methods, we show that regression-based counting is a promising alternative in low data regimes. Through developing methods to automatically count living cells in microscopy images, we contribute to valuable research on the human genome. The code is available at https://github.com/beijn/cellnet.