Intelligent sort‐timing prediction for image‐activated cell sorting

Abstract

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.

Is AI essential? Examining the need for deep learning in image-activated sorting of Saccharomyces cerevisiae

“…The image processing time affects the event rate that can be employed for sorting experiments, where a shorter processing time allows for a higher event rate with lower probability for sorting errors. 55 The higher the event rate we can employ, the more feasible it would be to sort for increasingly rare cells. Fig.…”

To Die or Not to Die—Regulated Cell Death and Survival in Cyanobacteria

“…We need technologies that allow image-based cell sorting with a sequential application of genomic methods [197,198]. Cell sorting technologies require classifying cells in real-time [199], and complex phenotypes may require machine learning algorithms for analysis [200].…”

Necessary or extravagant? Investigating the worth of artificial intelligence in image-activated sorting of Saccharomyces cerevisiae

“…The image processing time is an important metric to consider as it affects the maximum event rate that can be employed within a given probability for sorting errors. 29 Figure 4A shows the average processing time per image required for a classification decision. While all three classifiers for both studies easily fell under the 32 ms maximum duration allowed for image processing set by the iIACS 2.0 system, feature gating classifiers required by far the shortest time as expected, clocking in at the submillisecond range.…”