Artificial intelligence-enabled multipurpose smart detection in active-matrix electrowetting-on-dielectric digital microfluidics.

ABSTRACT: An active-matrix electrowetting-on-dielectric (AM-EWOD) system integrates hundreds of thousands of active electrodes for sample droplet manipulation, which can enable simultaneous, automatic, and parallel on-chip biochemical reactions. A smart detection system is essential for ensuring a fully automatic workflow and online programming for the subsequent experimental steps. In this work, we demonstrated an artificial intelligence (AI)-enabled multipurpose smart detection method in an AM-EWOD system for different tasks. We employed the U-Net model to quantitatively evaluate the uniformity of the applied droplet-splitting methods. We used the YOLOv8 model to monitor the droplet-splitting process online. A 97.76% splitting success rate was observed with 18 different AM-EWOD chips. A 99.982% mo

SUBMITTER: Jia Z 

PROVIDER: S-EPMC11427566 | biostudies-literature | 2024 Sep

REPOSITORIES: biostudies-literature