AI-aided high-throughput profiling of single-cell migration and proliferation on addressable dual-nested microwell arrays

High-throughput microfluidic systems accelerated by artificial intelligence for biomedical applications

“…The abundance of data could serve as a valuable resource for training and optimizing AI models. The synergy of high-throughput microfluidics and AI holds immense potential (e.g., AI-assisted high-throughput singlecell analysis) 18 in advancing our understanding of biomedical systems and driving innovative applications in various domains. 25,118 3 How can high-throughput microfluidic systems benefit from AI?…”

“…The synergy of high-throughput microfluidics and AI holds immense potential ( e.g. , AI-assisted high-throughput single-cell analysis) 18 in advancing our understanding of biomedical systems and driving innovative applications in various domains. 25,118…”

“…For instance, for a microfluidic platform with 1000 parallel cell culture units, automatic time-lapse fluorescence microscopy imaging will generate over 1 TB of image data (1 bright-field and 3 fluorescence images per unit, 72 time points, 5 MB per image). 18 Analyzing such big data would be labor intensive, time consuming and error prone if not impossible, which seriously hampers the improvement of system throughput. Besides, some important hidden patterns and unexpected trends in data might be hard to discover by manual analysis.…”

Enhancing single-cell biology through advanced AI-powered microfluidics

“…Huang et al 33 propose a high-throughput system featuring an addressable dual-nested microwell array chip (DNMA chip) combined with a Mask R-CNN model trained for image analysis. The DNMA chips allow single-cell capture, label-free encoding, and long-term incubation, facilitating non-destructive evaluation of the migration and proliferation of individual tumor cells under normal culture conditions or chemotherapy.…”

Artificial intelligence-accelerated high-throughput screening of antibiotic combinations on a microfluidic combinatorial droplet system

“…It provides a new approach, which is able to identify the features and reveal the implicit relationships from the raw data (e.g., RGB images) by building a multilayer network. [36][37][38][39] To date, it is widely used in image processing, including image classification, 40 region segmentation 41 and super-resolution reconstruction. 42,43 In our work, the AI-based module was developed to automatically identify and segment the droplets in images, extract the average gray values of the droplets and background, respectively, and calculate the time-dependent density of bacteria in the droplets.…”