A Self-Supervised Learning Approach for High Throughput and High Content Cell Segmentation

In principle, 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, have 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 requires no parameter tuning or curated data sets, thus providing a more efficient cell segmentation approach for high-throughput, high-content research. 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 images, with scores ranging from 0.831 to 0.876; outperforming the popular Cellpose algorithm, which showed a greater F1 variance of 0.645 to 0.8815, mainly due to segmentation errors. This novel SSL methodology advances segmentation accuracy, requires no curated training imagery or computational expertise and eliminates cloud-based data security concerns, thereby streamlining the process of applying machine learning to large data sets.