Smartphone-based point-of-care testing (POCT) is rapidly emerging as an alternative to traditional screening and laboratory testing, particularly in resource-limited settings. In this proof-of-concept study, we present a smartphone- and cloud-based artificial intelligence quantitative analysis system (SCAISY) for relative quantification of SARS-CoV-2-specific IgG antibody lateral flow assays that enables rapid evaluation (<60 s) of test strips. By capturing an image with a smartphone camera, SCAISY quantitatively analyzes antibody levels and provides results to the user. We analyzed changes in antibody levels over time in more than 248 individuals, including vaccine type, number of doses, and infection status, with a standard deviation of less than 10%. We also tracked antibody levels in six participants before and after SARS-CoV-2 infection. Finally, we examined the effects of lighting conditions, camera angle, and smartphone type to ensure consistency and reproducibility. We found that images acquired between 45° and 90° provided accurate results with a small standard deviation and that all illumination conditions provided essentially identical results within the standard deviation. A statistically significant correlation was observed (Spearman correlation coefficient: 0.59, p = 0.008; Pearson correlation coefficient: 0.56, p = 0.012) between the OD450 values of the enzyme-linked immunosorbent assay and the antibody levels obtained by SCAISY. This study suggests that SCAISY is a simple and powerful tool for real-time public health surveillance, enabling the acceleration of quantifying SARS-CoV-2-specific antibodies generated by either vaccination or infection and tracking of personal immunity levels.

Accurate and efficient classification and quantification of CD34+ cells are essential for the diagnosis and monitoring of leukemia. Current methods, such as flow cytometry, are complex, time-consuming, and require specialized expertise and equipment. This study proposes a novel approach for the label-free identification of CD34+ cells using a deep learning model and lens-free shadow imaging technology (LSIT). LSIT is a portable and user-friendly technique that eliminates the need for cell staining, enhances accessibility to nonexperts, and reduces the risk of sample degradation. The study involved three phases: sample preparation, dataset generation, and data analysis. Bone marrow and peripheral blood samples were collected from leukemia patients, and mononuclear cells were isolated using Ficoll density gradient centrifugation. The samples were then injected into a cell chip and analyzed using a proprietary LSIT-based device (Cellytics). A robust dataset was generated, and a custom AlexNet deep learning model was meticulously trained to distinguish CD34+ from non-CD34+ cells using the dataset. The model achieved a high accuracy in identifying CD34+ cells from 1929 bone marrow cell images, with training and validation accuracies of 97.3% and 96.2%, respectively. The customized AlexNet model outperformed the Vgg16 and ResNet50 models. It also demonstrated a strong correlation with the standard fluorescence-activated cell sorting (FACS) technique for quantifying CD34+ cells across 13 patient samples, yielding a coefficient of determination of 0.81. Bland–Altman analysis confirmed the model’s reliability, with a mean bias of −2.29 and 95% limits of agreement between 18.49 and −23.07. This deep-learning-powered LSIT offers a groundbreaking approach to detecting CD34+ cells without the need for cell staining, facilitating rapid CD34+ cell classification, even by individuals without prior expertise.

Morphological changes in leukocytes are valuable markers for diseases and immune responses. In our earlier work, we presented Cellytics, a device that uses lens-free shadow imaging technology (LSIT) to monitor natural killer cell activity. Here, we present an improved Cellytics system that has been upgraded to a four-channel configuration to achieve higher throughput while maintaining robust reproducibility for rapid and cost-effective leukocyte analysis. The performance of this multi-channel Cellytics system was improved through refinements to the micro-pinhole chip. Etched pinholes provided better image resolution and clarity compared to drilled pinholes. To stimulate leukocytes, we used an activation stimulator cocktail (ASC) and quantified the resulting morphological changes using shadow-based metrics, including peak-to-peak distance (PPD) and maxima-to-minima standard deviation (MMD-SD). In addition, we developed a new leukocyte activation parameter (LAP) to specifically assess these activation-induced morphological changes. After ASC stimulation, leukocytes showed significantly increased PPD and LAP values and decreased MMD-SD compared to non-activated leukocytes. These results are consistent with the results of the flow cytometric analysis. These results emphasize the potential of Cellytics for the rapid and accurate assessment of leukocyte activation and provide a valuable tool for both clinical diagnostics and basic immunological research.

Natural killer (NK) cells are important effectors of innate immunity that eliminate virus-infected and malignant cells. Monitoring NK cell activity is essential for assessing immune function. However, conventional methods, such as flow cytometry, are labor-intensive and time-consuming. This protocol describes a label-free technique for the rapid analysis of natural killer (NK) cell activity using lens-free shadow imaging technology (LSIT). NK cells isolated from peripheral blood and stimulated with a proprietary activator were analyzed using the LSIT platform within 5 min. The LSIT platform captures holographic images, known as shadow images, created by the interference of light with NK cells, and monitors their activation status by analyzing changes in shadow parameters. Key parameters derived from the shadow images, including the peak-to-peak distance (PPD) and standard deviation of the secondary maxima width (WSM-SD), quantitatively reflected the cell morphology and internal complexity. These parameters were integrated into the combined shadow parameter (CSP) and innate immunity index (I3) to provide a comprehensive assessment and quantification of NK cell activity based on morphological changes in the cells. I3, calculated as the percentage change in CSP after activation, served as a direct measure of NK cell activity. NK cells from healthy individuals consistently showed significantly higher I3 values than those from immunocompromised individuals. The LSIT platform enables fast and cost-effective immune profiling that is suitable for point-of-care diagnostics.

Morphological changes in white blood cells (WBCs) are valuable markers of disease and immune response. This study introduces a multi-channel Lens-free Shadow Imaging Technology (LSIT) device for rapid, cost-effective leukocyte analysis. Device performance was optimized by evaluating micro-pinhole chip parameters, with etched pinholes demonstrating superior image quality and sharpness compared to drilled pinholes. Using an activation stimulator cocktail (ASC), WBC activation was induced, and resulting morphological changes were quantified using shadow parameters, including peak-to-peak distance (PPD) and maxima-to-minima standard deviation (MMD-SD). A novel leukocyte activation parameter (LAP) was developed to measure these activation-induced changes comprehensively. Results showed that ASC-stimulated WBCs exhibited increased PPD and LAP values and decreased MMD-SD, consistent with flow cytometry findings. These results highlight the potential of LSIT and LAP for rapid and accurate assessment of leukocyte activation, offering a valuable tool for clinical diagnostics and immunological research.