Rapid segmentation and sensitive analysis of CRP with paper-based microfluidic device using machine learning

Paper-based microchannels are important components in paper-based microfluidic devices. Paper-based microchannels are usually manufactured by creating lines with hydrophobic patterns enclosing an area of hydrophilic paper inside. Among the many techniques for making hydrophobic lines, the printing method in general and inkjet printing in particular have become more common because of their advantages in terms of material saving, high precision, low-cost, etc. In this paper, the electrohydrodynamic (EHD) inkjet printing method, which has been studied and developed in recent years, has been used to drop glycol ether solvent-based ink onto a nitrocellulose paper. The results of the field emission scanning electron microscope (FE-SEM) show that the solvent based ink could dissolve through membrane and form a transparent hydrophobic layer on the created space. The width of the barrier lines can be controlled from about 200 μm to 260 μm, which is quite small when compared to other manufacturing methods. Based on this fabrication process, paper-based microfluidic analytical devices have been designed and fabricated for use in analytical biochemistry assays. Human chorionic gonadotropin (hCG) was selected as the biological target for this assay. Initial results have shown that the target for hCG can be quantitatively determined by these devices with a coefficient of determination (R2) of approximately 0.99. Therefore, EHD inkjet printing technology can be used for the manufacture of paper-based microfluidic analytical devices (μPADs) that may be applied in the future for analytical biochemistry assays.

ABSTRACT. Two easy-to-use, rapid, and inexpensive colorimetric-based assays for the detection of active constituent in nasal decongestant phenylephrine hydrochloride (PHP), in solution and their respective pharmaceutical preparations were reported. The assay principle depends on the diazotized sulfadimidine (DSDM) coupling with PHP active pharmaceutical compound under alkaline conditions to produce a colored azo-dye product. A UV/VIS spectrophotometry method was utilized to monitor the color absorbance change at 460 nm, with a linear calibration graph in the concentration range of 1-20 mg L-1 and a limit of detection of 0.22 mg L-1 and limit of quantification of 0.72 mg L-1. A comparison was done using a paper-based microfluidic analytical device (µPADs) and color intensity change was measured using a Samsung note 9 camera to capture digital images and Image J software to analyze the color intensity development. A linear trend was observed above approximately 10 mg L-1. Thus, paper-based microfluidic analytical devices (µPADs) can be used as an alternative platform to conventional methods to perform a semi-quantitative PHP drug analysis. The proposed method was applied for the determination of PHP in commercial pharmaceutical preparations. KEY WORDS: Phenylephrine hydrochloride, Spectrophotometry, Paper-based microfluidic analytical devices (µPADs), Pharmaceutical preparations, Colorimetric detection Bull. Chem. Soc. Ethiop. 2022, 36(4), 727-736. DOI: https://dx.doi.org/10.4314/bcse.v36i4.1

Electrochromatographic separations of three metal complexes were achieved through observing the visualization evolution process of moving chelation boundaries (MCBs) on microfluidic paper-based analytical devices (μPADs). A simplified photolithography was developed to pattern the μPADs within 5–10 min with three steps only, manually gelatinize, expose and develop, through thinning SU-8 2150 with trichloromethane. With a cutting method, many bubbles were clearly observed in the single-component MCB system on the μPADs, but were not found with this photolithography method under the same voltages. It was demonstrated that this photolithography for patterning narrow paper channels rejected Joule heating more effectively than the cutting paper method did. It was observed simultaneously that the apparent distances of electrophoretic and electroosmotic migrations of the blue [Cu-EDTA]2− chelation boundary increased with increasing electrical field strength and width of the paper channels, respectively. The higher the Cu2+ concentrations were, the slower the electrophoretic migrations of the blue boundary were, and the faster the electroosmotic migrations of the blue boundary were on the μPADs with this photolithography. The separations and concentrations of the coloured zones, pink [Co–EDTA]2−, blue [Cu–EDTA]2− and yellow [Fe–EDTA]2−, were clearly observed in the applied electric fields on the μPADs. The studies benefit extending the application of μPADs as low-cost, disposable analysis tools and deepen understanding of the comprehensive mechanisms concerning MCBs, partition adsorption and electroosmotic flow on μPADs.

Paper-based microfluidic devices have many advantages such as low cost, flexibility, light weight and easy disposability. Especially, since they can intrinsically generate capillary-driven flow (no pumps are needed), paper-based microfluidic devices are widely used in analytical or diagnostic platforms. Along with advancements in microfluidic paper-based analytical devices (μPADs), energy generation using paper materials has received significant attention. In this study, environment-friendly and flexible paper-based energy harvesting with a simple configuration is demonstrated by using the principle of reverse electrodialysis (RED). RED is a promising clean energy generation method, which converts Gibbs free energy into electricity by salinity gradients without discharging any pollutants. However, the power efficiency in a conventional RED device is limited by the essential requirement of active pumping for providing high and low concentration electrolytes. Capillary pumping from the proposed paper-based RED can save this waste of energy, and moreover, the flexible device is realized with cost effective materials and a simple fabrication step, and is environmentally friendly. By thoughtful analysis of voltage-current experiments and capillary flow rates in paper channels, the optimized channel width interfacing with a selective membrane is determined as 2 mm and the maximum power and power density are achieved as 55 nW and 275 nW cm(-2), respectively. 25.8% of the generated maximum power is successfully saved by realizing the pumpless RED system. This paper-based RED device can be integrated directly with μPADs as a practical application.

The presence of chironomid larvae in tap water has sparked public concern regarding the water supply system in South Korea. Despite ongoing efforts to establish a safe water supply system, entirely preventing larval occurrences remains a significant challenge. Therefore, we developed a real-time chironomid larva detection system (RT-CLAD) based on deep learning technology, which was implemented in drinking water treatment plants. The acquisition of larval images was facilitated by a multi-spectral camera with a wide spectral range, enabling the capture of unique wavelet bands associated with larvae. Three state-of-the-art deep learning algorithms, namely the convolutional neural network (CNN), you only look once (YOLO), and residual neural network (ResNet), renowned for their exceptional performance in object detection tasks, were employed. Following a comparative analysis of these algorithms, the most accurate and rapid model was selected for RT-CLAD. To achieve the efficient and accurate detection of larvae, the original images were transformed into a specific wavelet format, followed by preprocessing to minimize data size. Consequently, the CNN, YOLO, and ResNet algorithms successfully detected larvae with 100% accuracy. In comparison to YOLO and ResNet, the CNN algorithm demonstrated greater efficiency because of its faster processing and simpler architecture. We anticipate that our RT-CLAD will address larva detection challenges in water treatment plants, thereby enhancing water supply security.

and AI-assisted image manipulation tools, which The emergence of advanced image manipulation techniques in the digital age has made it extremely difficult to detect and categorize forged images. In order to identify and classify image forgeries, this study proposes a deep learning-based method that combines a Convolutional Neural Network (CNN) classifier with the You Only Look Once (YOLO) object detection model. The suggested system uses sophisticated feature extraction techniques to categorize images into authentic, copy-move, spliced, and deepfake forgeries after being trained on a custom dataset of manipulated images. While CNN-based classification offers accurate categorization, our experimental results show how reliable and effective YOLO is at locating forgery regions. Because of its high accuracy, the suggested model is a useful tool for security and digital forensics applications. Keywords: Image Forgery, YOLO, CNN, Deep Learning, Classification, Digital Forensics

Automatic target recognition (ATR) is a challenging task for several computer vision applications. It requires efficient, accurate, and robust methods for target detection and target identification. Deep learning has shown great success in many computer vision applications involving color RGB images. However, the performance of these networks in ATR with infrared sensor data needs further investigation. In this paper, we propose a multistage automatic target detection and recognition (ATDR) system that performs both target detection and target classification on infrared (IR) imagery using deep learning. Our system processes large IR image frames where targets take <1 % of the total number of pixels. First, we train a state-of-the-art object detector you only look once (YOLO) to localize all potential targets in the input image frame. Then, we train a convolutional neural network (CNN) to identify these detections as targets or false alarms. In this second phase, we adapt and analyze the performance of three CNN architectures: a compact and fully connected CNN, VGG16 with batch normalization, and a wide residual neural network (WRN). We also explore the use of a loss function that optimizes directly the area under the receiver operating characteristic (ROC) curve (AUC), and adapt it to our ATR application. To enhance the robustness of the proposed ATR to perturbation and variations introduced during the detection stage, we train our CNN classifiers on automatically detected targets using YOLO, in addition to ground truth bounding boxes and apply selected data augmentation techniques. To simulate real testing environments, where the spatial location of the targets within the image frame is unknown, only YOLO-detected boxes are used during validation. We evaluate our ATDR on a real benchmark dataset that includes different vehicles captured at different resolutions. Our experiments have shown that YOLO can detect most of the targets at the expense of generating a high number of false alarms. We show that the VGG-16 network with batch normalization, which is the best performing model, can correctly identify the classes of the targets, as well as classify the majority of YOLO’s false detections into an additional nontarget class. We also show that the proposed training modification to optimize an AUC-based loss function for ATR proved to be advantageous mainly in identifying difficult targets.

Iodine is an essential micronutrient for humans due to its fundamental role in the biosynthesis of thyroid hormones. As a key parameter to assess health conditions, iodine intake needs to be monitored to ascertain and prevent iodine deficiency. Iodine is available from various food sources (such as seaweed, fish, and seafood, among others) and dietary supplements (multivitamins or mineral supplements). In this work, a microfluidic paper-based analytical device (μPAD) to quantify iodide in seaweed and dietary supplements is described. The developed μPAD is a small microfluidic device that emerges as quite relevant in terms of its analytical capacity. The quantification of iodide is based on the oxidation of 3,3',5,5'-tetramethylbenzidine (TMB) by hydrogen peroxide in the presence of iodine, which acts as the catalyst to produce the blue form of TMB. Additionally, powder silica was used to intensify and uniformize the colour of the obtained product. Following optimization, the developed μPAD enabled iodide quantification within the range of 10-100 µM, with a detection limit of 3 µM, and was successfully applied to seaweeds and dietary supplements. The device represents a valuable tool for point-of-care analysis, can be used by untrained personnel at home, and is easily disposable, low-cost, and user-friendly.

YOLO Based Breast Masses Detection and Classification in Full-Field Digital Mammograms

While basic concepts of paper-based microfluidic analytical devices (μPADs) have appeared considerably, elemental technology development is worth working from different specialized points of view. Herein, we show that 2,2,6,6-tetramethylpiperidine-1-oxyl radical (TEMPO)-oxidized cellulose nanofiber (TOCN) can be reasonably used as a module of μPADs; we adopted a biochemical reaction of indigo formation by oxidation of indoxyl acetate (IDA) via its hydrolysis with acetylcholinesterase (AChE) as an example. First, we demonstrate that TOCN stably stores unstable AChE and IDA when dried and acts as a biochemical reaction field when wet. The thixotropic nature of TOCN aqueous dispersion gave inkjet printability, which will facilitate the μPADs production. The exchange of substances in the wet TOCN network took more time than in solution, but this can be read as control of reaction kinetics. Finally, we constructed semiquantitative μPADs for an organic phosphorus pesticide. We illustrate that by mounting TOCN, various functions can be incorporated on one sheet of paper to lead to the extension of design flexibility and universal use for μPADs.

A transformation of the healthcare industry is necessary and imminent: hospital-centered, reactive care will soon give way to proactive, person-centered care which focuses on individuals' well-being. However, this transition will only be made possible through scientific innovation. Next-generation technologies will be the key to developing affordable and accessible care, while also lowering the costs of healthcare. A promising solution to this challenge is low-cost continuous health monitoring; this approach allows for effective screening, analysis, and diagnosis and facilitates proactive medical intervention. Urine has great promise for being a key resource for health monitoring; unlike blood, it can be collected effortlessly on a daily basis without pain or the need for special equipment. Unfortunately, the commercial rapid urine analysis tests that exist today can only go so far-this is where the promise of microfluidic devices lies. Microfluidic devices have a proven record of being effective analytical devices, capable of controlling the flow of fluid samples, containing reaction and detection zones, and displaying results, all within a compact footprint. Moving past traditional glass- and polymer-based microfluidics, paper-based microfluidic devices possess the same diagnostic ability, with the added benefits of facile manufacturing, low-cost implementation, and disposability. Hence, we review the recent progress in the application of paper-based microfluidics to urine analysis as a solution to providing continuous health monitoring for proactive care. First, we present important considerations for point-of-care diagnostic devices. We then discuss what urine is and how paper functions as the substrate for urine analysis. Next, we cover the current commercial rapid tests that exist and thereby demonstrate where paper-based microfluidic urine analysis devices may fit into the commercial market in the future. Afterward, we discuss various fabrication techniques that have been recently developed for paper-based microfluidic devices. Transitioning from fabrication to implementation, we present some of the clinically implemented urine assays and their importance in healthcare and clinical diagnosis, with a focus on paper-based microfluidic assays. We then conclude by providing an overview of select biomarker research tailored towards urine diagnostics. This review will demonstrate the applicability of paper-based assays for urine analysis and where they may fit into the commercial healthcare market.

Microfluidic paper-based analytical devices (μPADs) are simple but powerful analytical tools that are gaining significant recent attention due to their many advantages over more traditional monitoring tools. These include being inexpensive, portable, pump-free, and having the ability to store reagents. One major limitation of these devices is slow flow rates, which are controlled by capillary action in the hydrophilic pores of cellulosic paper. Recent investigations have advanced the flow rates in μPADs through the generation of a gap or channel between two closely spaced paper sheets. This multilayered format has opened up μPADs to new applications and detection schemes, where large gap sizes (>300 μm) provide at least 169× faster flow rates than single-layer μPADs, but do not conform to established mathematical models for fluid transport in porous materials, such as the classic Lucas-Washburn equation. In the present study, experimental investigations and analytical modeling are applied to elucidate the driving forces behind the rapid flow rates in these devices. We investigate a range of hypotheses for the systems fluid dynamics and establish a theoretical model to predict the flow rate in multilayered μPADs that takes into account viscous dissipation within the paper. Device orientation, sample addition method, and the gap height are found to be critical concerns when modeling the imbibition in multilayered devices.

A simple double-layered three-dimensional (3D) microfluidic paper-based analytical device (μPAD) was designed for the simultaneous determination of six metal ions-Fe(III), Ni(II), Cr(VI), Cu(II), Al(III), and Zn(II)-for the first time. The 3D μPAD was composed of two paper layers: a top pretreatment layer and a bottom colorimetric detection layer. The sample solution added to the central sample reservoir of the 3D μPAD could be automatically divided into eight flow pathways and be automatically pretreated while flowing through the pretreatment zones located in the microfluidic channels, and automatically carried out the chromogenic reactions after reaching the detection zones. Random diffusion of the chromogenic reagents was effectively prevented by transport of the pretreated sample solution to the detection zones through 3D microfluidic channels with an L-type circuitous flow route design, resulting in highly increased color uniformity and reproducibility. Combined with use of a flat LED lamp as an upward lighting source and a smartphone as a convenient detector, improved color perception, highly enhanced sensitivity, and an extended detection range were obtained. Finally, the double-layered 3D μPAD was applied to the multiplexed determination of the six metal ions in mixtures and environmental samples with satisfactory results. Detection limits as low as 0.2, 0.3, 0.1, 0.03, 0.08, and 0.04 mg/L for Fe(III), Ni(II), Cr(VI), Cu(II), Al(III), and Zn(II) detection, respectively, were achieved, which are about one order of magnitude lower than obtained with previously reported μPADs for the detection of metal ions. The present 3D μPAD is simple, fast, selective, sensitive, and user-friendly, and holds great application potential for multiplexed on-site analysis.

In this work, two microfluidic paper-based analytical devices (μPADs) were developed for the quantification of urea and NHx in human saliva to aid in the diagnosis/monitoring of chronic kidney disease (CKD). The NHx determination was based on the conversion of ammonium to ammonia, followed by its diffusion through a hydrophobic membrane and then the color change of bromothymol blue (BTB) indicator. In the urea determination, prior to the ammonium conversion and BTB color change, the enzymatic conversion of urea into ammonium was produced, using urease. Several optimization studies were carried out to attain a quantification range of 0.10–5.0 mM with 0.032 mM limit of detection for the NHx μPAD, and a determination range of 0.16–5.0 mM with 0.049 mM limit of detection for the urea μPAD. The method accuracy was assessed, and the measurements obtained with NHx μPAD were compared with the ones obtained from an ammonia ion selective electrode; while the measurements of the urea μPAD were compared with the ones obtained from a commercially available kit. There were no statistically significant differences between methods, proving that both NHx and urea μPAD were effective on-hand tools for CKD monitoring in saliva. To evaluate their functionality as point-of-care devices, stability studies were also performed and revealed that both NHx and urea μPAD were stable when stored in a vacuum for 2 and 1 month, respectively. After the sample introduction, the NHx μPAD could be scanned within the first 2 h and the urea μPAD within 1 h.

We present a novel microfluidic paper-based analytical device (μPAD) which utilizes the native high electroosmotic flow (EOF) in nitrocellulose to achieve stationary isotachophoresis (ITP) focusing. This approach decouples sample accumulation from the length of the channel, resulting in significant focusing over short channel lengths. We provide a brief theory for EOF-balanced ITP focusing under continuous injection from a depleting reservoir and present the design of a short (7 mm) paper-based microfluidic channel, which allows a 200 μL sample to be processed in approximately 6 min, resulting in a 20 000-fold increase in concentration - a full order of magnitude improvement compared to previous paper-based ITP devices. We show the stability of the assay over longer (40 min) durations of time, and using Morpholino probes, we present the applicability of the device for amplification-free detection of nucleic acids, with a limit-of-detection (LoD) of 5 pM in 10 min. Finally, we utilize the small footprint of the channel and show a multiplexed platform in which 12 assays operate in parallel in a 24-well plate format.