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

T cells play a pivotal role in cancer research, particularly in immunotherapy, which harnesses the immune system to target malignancies. However, conventional expansion methods face limitations such as high reagent consumption, contamination risks, and difficulties in maintaining suspension cells in dynamic culture environments. This study presents a microfluidic system for long-term culture of non-adherent cells, featuring automated perfusion and image acquisition. The system integrates deep learning-based image analysis, which quantifies cell coverage and estimates cell numbers, and efficiently processes large volumes of data. The performance of this deep learning approach was benchmarked against the widely used Trainable Weka Segmentation (TWS) plugin for Fiji. 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 the proliferation of Jurkat cells and primary human T cells without significant loss during medium exchange. Each platform proved suitable for long-term expansion while offering distinct advantages in terms of design, cell seeding and recovery, and reusability. This integrated approach enables extended experiments with minimal manual intervention, stable perfusion, and supports multi-reagent administration, offering a powerful platform for advancing suspension cell research in immunotherapy.