DART: A design-aware microfluidic chip paradigm for real-time live-cell image analysis

2026-06-16

AI Summary

This study addresses the bottleneck in high-throughput microfluidic live-cell imaging, where conventional semi-automated approaches suffer from analysis delays due to reliance on manual intervention for processing numerous regions of interest (RoIs). To overcome this limitation, the authors propose DART—a novel paradigm that enables real-time image analysis co-designed with microfluidic chip architecture. By integrating embedded fiducial markers, deep learning–driven marker detection, and CAD-to-physical chip alignment, DART automatically localizes RoIs of arbitrary geometry and removes microfluidic structures without human input. Validated on a Swiss Army Knife chip containing 1,164 RoIs, the framework achieves full RoI localization in under five minutes, structural removal in 40 ms per image, and end-to-end analysis—including cell segmentation—in less than 1.1 seconds, thereby breaking the scalability barrier and paving the way for closed-loop intelligent microscopy.

Abstract

High-throughput microfluidic live-cell imaging generates rich single-cell data. Yet semi-automated procedures for locating regions of interest (RoIs), each containing one cell population, and removing surrounding microfluidic structures from recorded images, scale with the number of RoIs. This prevents real-time image analysis and delays time-to-insight by hours to days. We introduce the Design-Aware and Real-Time capable (DART) paradigm for microfluidic cultivation chips, which aligns the CAD blueprint with the physical chip and thereby enables throughput-independent localization of all RoIs and fully automated image processing across diverse RoI geometries and chip layouts. DART establishes this alignment through embedded fiducial markers and deep-learning-based marker detection. We validate DART using the Swiss Army Knife chip, which combines eight structurally distinct RoI designs across 1164 RoI locations. DART localizes all RoIs in five minutes, removes microfluidic structures from raw microscopy images in 40 ms, and performs fully automated image analysis, including cell segmentation, in under 1.1 s per image. Together, these capabilities establish DART as an end-to-end hardware-software paradigm with real-time-capable analysis that paves the way toward closed-loop and outcome-driven smart microscopy.

Problem

• microfluidic live-cell imaging
• region of interest localization
• real-time image analysis
• high-throughput
• image processing

Innovation

• design-aware
• real-time image analysis
• microfluidic chip
• fiducial markers
• deep learning