A self-supervised learning approach for high throughput and high content cell segmentation

In principle, ML/AI-based algorithms should enable rapid and accurate cell segmentation in high-throughput settings. However, reliance on large training datasets, human input, computational expertise, and limited generalizability has prevented this goal of completely automated, high-throughput segmentation from being achieved. To overcome these roadblocks, we introduce an innovative self-supervised learning method (SSL) for pixel classification that does not require parameter tuning or curated data sets, and instead trains itself on the end-users' own data in a completely automated fashion, thus providing a more efficient cell segmentation approach for high-throughput, high-content image analysis. We demonstrate that our algorithm meets the criteria of being fully automated with versatility across various magnifications, optical modalities, and cell types. Moreover, our SSL algorithm is capable of identifying complex cellular structures and organelles, which are otherwise easily missed, thereby broadening the machine learning applications to high-content imaging. Our SSL technique displayed consistently high F1 scores across segmented cell images, with scores ranging from 0.771 to 0.888, matching or outperforming the popular Cellpose algorithm, which showed a greater F1 variance of 0.454 to 0.882, primarily due to more false negatives.