Automated T-Cell Proliferation in Lab-on-Chip Devices Integrating Microfluidics and Deep Learning-Based Image Analysis for Long-Term Experiments

Abstract

T cells play a pivotal role in cancer research, particularly in immunotherapy, which harnessesthe immune system to target malignancies. However, conventional expansionmethods face limitations such as high reagent consumption, contamination risks, anddifficulties in maintaining suspension cells in dynamic culture environments. This studypresents a microfluidic system for long-term culture of non-adherent cells, featuring automatedperfusion and image acquisition. The system integrates deep learning-basedimage analysis, which quantifies cell coverage and estimates cell numbers, and efficientlyprocesses large volumes of data. The performance of this deep learning approach wasbenchmarked against the widely used Trainable Weka Segmentation (TWS) plugin forFiji. Additionally, two distinct lab-on-a-chip (LOC) devices were evaluated independently:the commercial ibidi® LOC and a custom-made PDMS LOC. The setup supported theproliferation of Jurkat cells and primary human T cells without significant loss duringmedium exchange. Each platform proved suitable for long-term expansion while offeringdistinct advantages in terms of design, cell seeding and recovery, and reusability. Thisintegrated approach enables extended experiments with minimal manual intervention,stable perfusion, and supports multi-reagent administration, offering a powerful platformfor advancing suspension cell research in immunotherapy.