Cancer is a fatal disease and a significant cause of millions of deaths. Traditional methods for cancer detection often have limitations in identifying the disease in its early stages, and they can be expensive and time-consuming. Since cancer typically lacks symptoms and is often only detected at advanced stages, it is crucial to use affordable technologies that can provide quick results at the point of care for early diagnosis. Biosensors that target specific biomarkers associated with different types of cancer offer an alternative diagnostic approach at the point of care. Recent advancements in manufacturing and design technologies have enabled the miniaturization and cost reduction of point-of-care devices, making them practical for diagnosing various cancer diseases. Furthermore, machine learning (ML) algorithms have been employed to analyze sensor data and extract valuable information through the use of statistical techniques. In this review paper, we provide details on how various machine learning algorithms contribute to the ongoing development of advanced data processing techniques for biosensors, which are continually emerging. We also provide information on the various technologies used in point-of-care cancer diagnostic biosensors, along with a comparison of the performance of different ML algorithms and sensing modalities in terms of classification accuracy.

Transformation of a benchtop fluorescence microscope to a smartphone 3D printed microscope with high accuracy of sensing enabled by HIST-DIP method.

Micro–nanoparticle and leukocyte imaging find significant applications in the areas of infectious disease diagnostics, cellular therapeutics, and biomanufacturing. Portable fluorescence microscopes have been developed for these measurements, however, quantitative assessment of the quality of images (micro–nanoparticles, and leukocytes) captured using these devices remains a challenge. Here, we present a novel method for automated quality assessment of fluorescent images (AQAFI) captured using smartphone fluorescence microscopes (SFM). AQAFI utilizes novel feature extraction methods to identify and measure multiple features of interest in leukocyte and micro–nanoparticle images. For validation of AQAFI, fluorescent particles of different diameters (8.3, 2, 1, 0.8 μm) were imaged using custom-designed SFM at a range of excitation voltages (3.8–4.5 V). Particle intensity, particle vicinity intensity, and image background noise were chosen as analytical parameters of interest and measured by the AQAFI algorithm. A control method was developed by manual calculation of these parameters using ImageJ which was subsequently used to validate the performance of the AQAFI method. For micro–nanoparticle images, correlation coefficients with R² > 0.95 were obtained for each parameter of interest while comparing AQAFI vs. control (ImageJ). Subsequently, key performance indicators (KPIs) i.e., signal difference to noise ratio (SDNR) and contrast to noise ratio (CNR) were defined and calculated for these micro-nano particle images using both AQAFI and control methods. Finally, we tested the performance of the AQAFI method on the fluorescent images of human peripheral blood leukocytes captured using our custom SFM. Correlation coefficients of R² = 0.99 were obtained for each parameter of interest (leukocyte intensity, vicinity intensity, background noise) calculated using AQAFI and control (ImageJ). A high correlation was also found between the CNR and SDNR values calculated using both methods. The developed AQAFI method thus presents an automated and precise way to quantify and assess the quality of fluorescent images (micro–nano particles and leukocytes) captured using portable SFMs. Similarly, this study finds broader applicability and can also be employed with benchtop microscopes for the quantitative assessment of their imaging performance.

Fluorescence microscopes are widely used to detect fluore-scent objects in a biological sample. However, traditional benchtop fluorescence microscopes are limited to high cost and nonportability. Recently, smartphone-based fluorescence microscopes (SFMs) have been developed, which capture images using a smartphone camera with the help of an external optical device and serve as an inexpensive and portable alternative. However, to analyze the images and get the accurate count of bioparticles, external software and computational resources are required; moreover, the lack of single and clustered count capabilities in SFMs without relying on an image library limits the use of SFMs. Here, we present an automated method as a mobile application with the ability to provide the bioparticle counts at the point of care by imaging human leukocytes and fluorescent microparticles. The application employs efficient image processing techniques that result in faster automated counting and reduced computational cost while providing comparable counts to industrial and academic standards. Compared with counting results calculated by ImageJ, a correlation coefficient of ${{R}^2}$ > 0.99 was observed along with the average relative error of ∼0.5% on different kinds of fluorescent images.

Cellular surface receptors monitoring enabled by machine learning and impedance cytometry.

This study uses time-frequency transformed data and deep learning (DL) models to identify the groups of metal oxide nano-coated micro-particles using an impedance cytometer. The nano-coated bioparticles generate distinct electrical signals in a multifrequency electric field and can be used in biosensing applications. The current machine learning-enabled sensing modalities are unable to accurately differentiate different bioparticles as the feature selection and feature engineering techniques are ineffective in selecting useful and informative features. Here, we use Wigner-Vile Distribution to transform the time series data into the time-frequency domain and employ three deep learning models to evaluate the ability of time-frequency transformed data to accurately represent the most important features. A classification accuracy of 75% for (10nm and 30nm) coated particles was achieved on the simplest DL model. This combination of time-frequency representation and the DL model will be sufficient to differentiate bioparticles by acting as an alternative to other ML-based techniques.