CellNet -- Localizing Cells using Sparse and Noisy Point Annotations

2026-06-10

AI Summary

This work addresses the high cost and scalability limitations of manual cell counting in high-throughput genomic screening, where existing computational methods rely heavily on densely annotated training data. To alleviate the annotation burden, the authors propose a regression-based deep learning approach that, for the first time, leverages sparse and noisy point annotations from phase-contrast microscopy images for simultaneous cell counting and localization. By training a regression network to estimate cell density maps from such sparse supervisory signals, the method achieves superior performance under low-label conditions compared to current zero-shot alternatives. Experiments on large-scale, real-world genetic screening datasets demonstrate that the proposed approach is both accurate and efficient, effectively mitigating the bottleneck posed by manual image annotation and thereby facilitating functional genomics research in the human genome.

Abstract

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.

Problem

• cell counting
• sparse annotations
• noisy point annotations
• phase-contrast microscopy
• low-data regime

Innovation

• regression-based counting
• sparse point annotations
• cell localization
• low-data regime
• phase-contrast microscopy