Intelligent sort‐timing prediction for image‐activated cell sorting

• Published in: Cytometry. Part A Vol. 103; no. 1; pp. 88 - 97
• Main Authors: Zhao, Yaqi, Isozaki, Akihiro, Herbig, Maik, Hayashi, Mika, Hiramatsu, Kotaro, Yamazaki, Sota, Kondo, Naoko, Ohnuki, Shinsuke, Ohya, Yoshikazu, Nitta, Nao, Goda, Keisuke
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.01.2023; Wiley Subscription Services, Inc
• Subjects: Actuation; Algorithms; Artificial Intelligence; Cell morphology; Cell Separation; cell sorting; Cytology; Flow Cytometry - methods; Fluorescence microscopy; Image acquisition; Image processing; image‐activated cell sorting; imaging flow cytometry; Latency; Machine Learning; Microfluidics; Morphology; Predictions; Sorting algorithms; Yeast; imaging flow cytometry; machine learning; cell sorting; image-activated cell sorting
• ISSN: 1552-4922; 1552-4930; 1552-4930
• DOI: 10.1002/cyto.a.24664

Intelligent image‐activated cell sorting (iIACS) has enabled high‐throughput image‐based sorting of single cells with artificial intelligence (AI) algorithms. This AI‐on‐a‐chip technology combines fluorescence microscopy, AI‐based image processing, sort‐timing prediction, and cell sorting. Sort‐timing prediction is particularly essential due to the latency on the order of milliseconds between image acquisition and sort actuation, during which image processing is performed. The long latency amplifies the effects of the fluctuations in the flow speed of cells, leading to fluctuation and uncertainty in the arrival time of cells at the sort point on the microfluidic chip. To compensate for this fluctuation, iIACS measures the flow speed of each cell upstream, predicts the arrival timing of the cell at the sort point, and activates the actuation of the cell sorter appropriately. Here, we propose and demonstrate a machine learning technique to increase the accuracy of the sort‐timing prediction that would allow for the improvement of sort event rate, yield, and purity. Specifically, we trained an algorithm to predict the sort timing for morphologically heterogeneous budding yeast cells. The algorithm we developed used cell morphology, position, and flow speed as inputs for prediction and achieved 41.5% lower prediction error compared to the previously employed method based solely on flow speed. As a result, our technique would allow for an increase in the sort event rate of iIACS by a factor of ~2. Sort‐timing prediction is particularly essential for intelligent image‐activated cell sorting (iIACS) in order to achieve sorting at a high event rate. We propose and demonstrate a machine‐learning technique to increase the accuracy of sort‐timing prediction by taking into account cell morphology, position, and flow speed. We use timing data and images from morphologically heterogeneous budding yeast cells to assess our method and show the predicted improvement of event rate, yield, and purity.