Artificial intelligence-based classification of peripheral blood nucleated cells using label-free imaging flow cytometry

Artificial intelligence-enabled microfluidic cytometer using gravity-driven slug flow for rapid CD4+ T cell quantification in whole blood

The quantification of immune cell subpopulations in blood is important for the diagnosis, prognosis and management of various diseases and medical conditions. Flow cytometry is currently the gold standard technique for cell quantification; however, it is laborious, time-consuming and relies on bulky/expensive instrumentation, limiting its use to laboratories in high-resource settings. Microfluidic cytometers offering enhanced portability have been developed that are capable of rapid cell quantification; however, these platforms involve tedious sample preparation and processing protocols and/or require the use of specialized/expensive instrumentation for flow control and cell detection. Here, we report an artificial intelligence-enabled microfluidic cytometer for rapid CD4+ T cell quantification in whole blood requiring minimal sample preparation and instrumentation. CD4+ T cells in blood are labeled with anti-CD4 antibody-coated microbeads, which are driven through a microfluidic chip via gravity-driven slug flow, enabling pump-free operation. A video of the sample flowing in the chip is recorded using a microscope camera, which is analyzed using a convolutional neural network-based model that is trained to detect bead-labeled cells in the blood flow. The functionality of this platform was evaluated by analyzing fingerprick blood samples obtained from healthy donors, which revealed its ability to quantify CD4+ T cells with similar accuracy as flow cytometry (<10% deviation between both methods) while being at least 4× faster, less expensive, and simpler to operate. We envision that this platform can be readily modified to quantify other cell subpopulations in blood by using beads coated with different antibodies, making it a promising tool for performing cell count measurements outside of laboratories and in low-resource settings.

Imaging Flow Cytometry: Development, Present Applications, and Future Challenges

Imaging flow cytometry (ImFC) represents a significant technological advancement in the field of cytometry, effectively merging the high-throughput capabilities of flow analysis with the detailed imaging characteristics of microscopy. In our comprehensive review, we adopt a historical perspective to chart the development of ImFC, highlighting its origins and current state of the art and forecasting potential future advancements. The genesis of ImFC stemmed from merging the hydraulic system of a flow cytometer with advanced camera technology. This synergistic coupling facilitates the morphological analysis of cell populations at a high-throughput scale, effectively evolving the landscape of cytometry. Nevertheless, ImFC's implementation has encountered hurdles, particularly in developing software capable of managing its sophisticated data acquisition and analysis needs. The scale and complexity of the data generated by ImFC necessitate the creation of novel analytical tools that can effectively manage and interpret these data, thus allowing us to unlock the full potential of ImFC. Notably, artificial intelligence (AI) algorithms have begun to be applied to ImFC, offering promise for enhancing its analytical capabilities. The adaptability and learning capacity of AI may prove to be essential in knowledge mining from the high-dimensional data produced by ImFC, potentially enabling more accurate analyses. Looking forward, we project that ImFC may become an indispensable tool, not only in research laboratories, but also in clinical settings. Given the unique combination of high-throughput cytometry and detailed imaging offered by ImFC, we foresee a critical role for this technology in the next generation of scientific research and diagnostics. As such, we encourage both current and future scientists to consider the integration of ImFC as an addition to their research toolkit and clinical diagnostic routine.

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

High-throughput microfluidic systems are widely used in biomedical fields for tasks like disease detection, drug testing, and material discovery. Despite the great advances in automation and throughput, the large amounts of data generated by the high-throughput microfluidic systems generally outpace the abilities of manual analysis. Recently, the convergence of microfluidic systems and artificial intelligence (AI) has been promising in solving the issue by significantly accelerating the process of data analysis as well as improving the capability of intelligent decision. This review offers a comprehensive introduction on AI methods and outlines the current advances of high-throughput microfluidic systems accelerated by AI, covering biomedical detection, drug screening, and automated system control and design. Furthermore, the challenges and opportunities in this field are critically discussed as well.

Real-time fluorescence imaging flow cytometry enabled by motion deblurring and deep learning algorithms

Fluorescence imaging flow cytometry (IFC) has been demonstrated as a crucial biomedical technique for analyzing specific cell subpopulations from heterogeneous cellular populations. However, the high-speed flow of fluorescent cells leads to motion blur in cell images, making it challenging to identify cell types from the raw images. In this study, we present a real-time single-cell imaging and classification system based on a fluorescence microscope and deep learning algorithm, which is able to directly identify cell types from motion-blur images. To obtain annotated datasets of blurred images for deep learning model training, we developed a motion deblurring algorithm for the reconstruction of blur-free images. To demonstrate the ability of this system, deblurred images of HeLa cells with various fluorescent labels and HeLa cells at different cell cycle stages were acquired. The trained ResNet achieved a high accuracy of 96.6% for single-cell classification of HeLa cells in three different mitotic stages, with a short processing time of only 2 ms. This technology provides a simple way to realize single-cell fluorescence IFC and real-time cell classification, offering significant potential in various biological and medical applications.

Microsystem Advances through Integration with Artificial Intelligence

Microfluidics is a rapidly growing discipline that involves studying and manipulating fluids at reduced length scale and volume, typically on the scale of micro- or nanoliters. Under the reduced length scale and larger surface-to-volume ratio, advantages of low reagent consumption, faster reaction kinetics, and more compact systems are evident in microfluidics. However, miniaturization of microfluidic chips and systems introduces challenges of stricter tolerances in designing and controlling them for interdisciplinary applications. Recent advances in artificial intelligence (AI) have brought innovation to microfluidics from design, simulation, automation, and optimization to bioanalysis and data analytics. In microfluidics, the Navier-Stokes equations, which are partial differential equations describing viscous fluid motion that in complete form are known to not have a general analytical solution, can be simplified and have fair performance through numerical approximation due to low inertia and laminar flow. Approximation using neural networks trained by rules of physical knowledge introduces a new possibility to predict the physicochemical nature. The combination of microfluidics and automation can produce large amounts of data, where features and patterns that are difficult to discern by a human can be extracted by machine learning. Therefore, integration with AI introduces the potential to revolutionize the microfluidic workflow by enabling the precision control and automation of data analysis. Deployment of smart microfluidics may be tremendously beneficial in various applications in the future, including high-throughput drug discovery, rapid point-of-care-testing (POCT), and personalized medicine. In this review, we summarize key microfluidic advances integrated with AI and discuss the outlook and possibilities of combining AI and microfluidics.

Optofluidic imaging meets deep learning: from merging to emerging

Propelled by the striking advances in optical microscopy and deep learning (DL), the role of imaging in lab-on-a-chip has dramatically been transformed from a silo inspection tool to a quantitative "smart" engine. A suite of advanced optical microscopes now enables imaging over a range of spatial scales (from molecules to organisms) and temporal window (from microseconds to hours). On the other hand, the staggering diversity of DL algorithms has revolutionized image processing and analysis at the scale and complexity that were once inconceivable. Recognizing these exciting but overwhelming developments, we provide a timely review of their latest trends in the context of lab-on-a-chip imaging, or coined optofluidic imaging. More importantly, here we discuss the strengths and caveats of how to adopt, reinvent, and integrate these imaging techniques and DL algorithms in order to tailor different lab-on-a-chip applications. In particular, we highlight three areas where the latest advances in lab-on-a-chip imaging and DL can form unique synergisms: image formation, image analytics and intelligent image-guided autonomous lab-on-a-chip. Despite the on-going challenges, we anticipate that they will represent the next frontiers in lab-on-a-chip imaging that will spearhead new capabilities in advancing analytical chemistry research, accelerating biological discovery, and empowering new intelligent clinical applications.