CellSighter: a neural network to classify cells in highly multiplexed images

Multiplexed imaging enables measurement of multiple proteins in situ, offering an unprecedented opportunity to chart various cell types and states in tissues. However, cell classification, the task of identifying the type of individual cells, remains challenging, labor-intensive, and limiting to throughput. Here, we present CellSighter, a deep-learning based pipeline to accelerate cell classification in multiplexed images. Given a small training set of expert-labeled images, CellSighter outputs the label probabilities for all cells in new images. CellSighter achieves over 80% accuracy for major cell types across imaging platforms, which approaches inter-observer concordance. Ablation studies and simulations show that CellSighter is able to generalize its training data and learn features of protein expression levels, as well as spatial features such as subcellular expression patterns. CellSighter's design reduces overfitting, and it can be trained with only thousands or even hundreds of labeled examples. CellSighter also outputs a prediction confidence, allowing downstream experts control over the results. Altogether, CellSighter drastically reduces hands-on time for cell classification in multiplexed images, while improving accuracy and consistency across datasets. Identification and classification of cells in multiplexed microscopy remain challenging. Here, the authors propose CellSighter, which uses neural networks to perform cell classification directly on multiplexed images, thus leveraging the spatial expression characteristics of proteins.

Automated summary

CellSighter is a deep-learning based pipeline that accelerates cell classification in multiplexed images. It achieves over 80% accuracy for major cell types and can be trained with only thousands or even hundreds of labeled examples. CellSighter's design reduces overfitting and provides prediction confidence for downstream experts.