Smartphone-based imaging systems for medical applications: a critical review

Development of a smartphone enabled, paper-based quantitative diagnostic assay using the HueDx color correction system

Color correction is an important methodology where a digital image's colors undergo a transformation to more accurately represent their appearance using a predefined set of illumination conditions. Colorimetric measurements in diagnostics are sensitive to very small changes in colors and therefore require consistent, reproducible illumination conditions to produce accurate results, making color correction a necessity. This paper presents an image color correction pipeline developed by HueDx, Inc., using transfer algorithms that improve upon existing methodologies and demonstrates real-world applications of this pipeline in colorimetric clinical chemistry using a smartphone enabled, paper-based total protein diagnostic assay. Our pipeline is able to compensate for a variety of illumination conditions to provide consistent imaging for quantitative colorimetric measurements using white-balancing, multivariate gaussian distributions and histogram regression via dynamic, non-linear interpolating lookup tables. We empirically demonstrate that each point in the color correction pipeline provides a theoretical basis for achieving consistent and precise color correction. To show this, we measure color difference with deltaE (ΔE00), alongside quantifying performance of the HueDx color correction system, including the phone hardware, color sticker manufacturing quality and software correction capabilities. The results show that the HueDx color correction system is capable of restoring images to near-imperceptible levels of difference independent of their original illumination conditions including brightness and color temperature. Comparisons drawn from the paper-based total protein assay calibrated and quantified with and without using the HueDx color correction pipeline show that the coefficient of variation in precision testing is almost twice as high without color-correcting. Limits of blank, detection and quantitation were also higher without color-correction. Overall, we were able to demonstrate the HueDx platform improves reading and outcome of the total protein diagnostic assay and is useful for the development of smartphone-based quantitative colorimetric diagnostic assays for point-of-care testing.

Artificial intelligence-assisted grading for tear trough deformity

BACKGROUND

Various classification systems for tear trough deformity (TTD) have been published; however, their complexity can pose challenges in clinical use, especially for less experienced surgeons. It is believed that artificial intelligence (AI) technology can address some of these challenges by reducing inadvertent errors and improving the accuracy of medical practice. In this study, we aimed to establish a reliable and precise digital image grading model for TTD using smartphone-based photography enhanced using AI deep learning technology. This model is designed to aid and guide surgeons, particularly those who are less experienced or from younger generations, during clinical examinations and in making decisions regarding further surgical interventions.

MATERIALS AND METHODS

A total of 504 patients and 983 photos were included in the study. We adopted the Barton's grading system for TTD. All photos were taken using the same smartphone and processed and analyzed using the medical AI assistant (MAIA™) software. The photos were then randomly divided into two groups to establish training and testing models.

RESULTS

The confusion matrix for the training model demonstrated a sensitivity of 56%, specificity of 87.3%, F1 score of 0.57, and an area under the curve (AUROC) of 0.85. For the testing group, the sensitivity was 49.3%, specificity was 85%, F1 score was 0.49, and AUROC was 0.83. Representative heatmaps were also generated.

CONCLUSION

Our study is the first to demonstrate that tear trough deformities can be easily categorized using a built-in smartphone camera in conjunction with an AI deep learning program. This approach can reduce errors during clinical patient evaluations, particularly for less experienced practitioners.

Mobile-linked point-of-care diagnostics in community-based healthcare: a scoping review of user experiences

BACKGROUND

While mobile-linked point-of-care diagnostics may circumvent geographical and temporal barriers to efficient communication, the use of such technology in community settings will depend on user experience. We conducted a scoping review to systematically map evidence on user experiences of mobile-linked point-of-care diagnostics in community healthcare settings published from the year 2016 up to the year 2022.

METHODOLOGY

We conducted a comprehensive search of the following electronic databases: Scopus, Web of Science, and EBSCOhost (Medline, CINAHL, Africa-wide, Academic Search Complete). The inter-reviewer agreement was determined using Cohen's kappa statistic. Data quality was appraised using the mixed method appraisal tool version 2018, and the results were reported according to the preferred reporting items for systematic reviews and meta-analyses for scoping reviews (PRISMA-ScR).

RESULTS

Following the abstract and full article screening, nine articles were found eligible for inclusion in data extraction. Following the quality appraisal, one study scored 72.5%, one study scored 95%, and the remaining seven studies scored 100%. Inter-rater agreement was 83.54% (Kappa statistic = 0.51, p < 0.05). Three themes emerged from the articles: approaches to implementing mobile-linked point-of-care diagnostics, user engagement in community-based healthcare settings, and limited user experiences in mobile-linked point-of-care diagnostics. User experiences are key to the sustainable implementation of mobile-linked point-of-care diagnostics. User experiences have been evaluated in small community healthcare settings. There is limited evidence of research aimed at evaluating the usability of mobile-linked diagnostics at the community level.

CONCLUSION

More studies are needed to assess the user experience of mobile-linked diagnostics in larger communities. This scoping review revealed gaps that need to be addressed to improve user experiences of mobile-linked diagnostics, including language barriers, privacy issues, and clear instructions.

ENCoDE - a skin tone and clinical dataset from a prospective trial on acute care patients

Background

Although hypothesized to be the root cause of the pulse oximetry disparities, skin tone and its use for improving medical therapies have yet to be extensively studied. Studies previously used self-reported race as a proxy variable for skin tone. However, this approach cannot account for skin tone variability within race groups and also risks the potential to be confounded by other non-biological factors when modeling data. Therefore, to better evaluate health disparities associated with pulse oximetry, this study aimed to create a unique baseline dataset that included skin tone and electronic health record (EHR) data.

Methods

Patients admitted to Duke University Hospital were eligible if they had at least one pulse oximetry value recorded within 5 minutes before an arterial blood gas (ABG) value. We collected skin tone data at 16 different body locations using multiple devices, including administered visual scales, colorimetric, spectrophotometric, and photography via mobile phone cameras. All patients' data were linked in Duke's Protected Analytics Computational Environment (PACE), converted into a common data model, and then de-identified before publication in PhysioNet.

Results

Skin tone data were collected from 128 patients. We assessed 167 features per skin location on each patient. We also collected over 2000 images from mobile phones measured in the same controlled environment. Skin tone data are linked with patients' EHR data, such as laboratory data, vital sign recordings, and demographic information.

Conclusions

Measuring different aspects of skin tone for each of the sixteen body locations and linking them with patients' EHR data could assist in the development of a more equitable AI model to combat disparities in healthcare associated with skin tone. A common data model format enables easy data federation with similar data from other sources, facilitating multicenter research on skin tone in healthcare.

Description

A prospectively collected EHR-linked skin tone measurements database in a common data model with emphasis on pulse oximetry disparities.

Application of smartphone-based infrared thermography devices for ocular surface thermal imaging

Infrared thermography (IRT) is a well-known imaging technique that provides a non-invasive displaying of the ocular surface temperature distribution. Currently, compact smartphone-based IRT devices, as well as special software for processing thermal images, have become available. The study aimed to determine the possible use of smartphone-based IRT devices for real-time ocular surface thermal imaging. This study involved 32 healthy individuals (64 eyes); 10 patients (10 eyes) with proliferative diabetic retinopathy (PDR) and absolute glaucoma; 10 patients (10 eyes) with PDR, who underwent vitreoretinal surgery. In all cases, simultaneous ocular surface IRT of both eyes was performed. In healthy individuals, the ocular surface temperature (OST) averaged 34.6 ± 0.8 °C and did not differ substantially between the paired eyes, in different age groups, and after pupil dilation. In our study, high intraocular pressure was accompanied by a decrease in OST in all cases. After vitreoretinal surgery in cases with confirmed subclinical inflammation, the OST was higher than the baseline and differed from that of the paired eye by more than 1.0 °C. These results highlight that smartphone-based IRT imaging could be useful for the non-invasive detection of OST asymmetry between paired eyes due to increased intraocular pressure or subclinical inflammation.

Towards ultra-low-cost smartphone microscopy

The outbreak of COVID-19 exposed the inadequacy of our technical tools for home health surveillance, and recent studies have shown the potential of smartphones as a universal optical microscopic imaging platform for such applications. However, most of them use laboratory-grade optomechanical components and transmitted illuminations to ensure focus tuning capability and imaging quality, which keeps the cost of the equipment high. Here, we propose an ultra-low-cost solution for smartphone microscopy. To realize focus tunability, we designed a seesaw-like structure capable of converting large displacements on one side into small displacements on the other (reduced to ∼9.1%), which leverages the intrinsic flexibility of 3D printing materials. We achieved a focus-tuning accuracy of ∼5 𝜇m, which is 40 times higher than the machining accuracy of the 3D-printed lens holder itself. For microscopic imaging, we used an off-the-shelf smartphone camera lens as the objective and the built-in flashlight as the illumination. To compensate for the resulting image quality degradation, we developed a learning-based image enhancement method. We used the CycleGAN architecture to establish the mapping from smartphone microscope images to benchtop microscope images without pairing. We verified the imaging performance on different biomedical samples. Except for the smartphone, we kept the full costs of the device under 4 USD. We think these efforts to lower the costs of smartphone microscopes will benefit their applications in various scenarios, such as point-of-care testing, on-site diagnosis, and home health surveillance. RESEARCH HIGHLIGHTS: We propose a solution for ultra-low-cost smartphone microscopy. Utilizing the flexibility of 3D-printed material, we can achieve focusing accuracy of ∼5 𝜇m. Such a low-cost device will benefit point-of-care diagnosis and home health surveillance.

Evaluation of a new portable corneal topography system for self-measurement using smartphones: a pilot study

PURPOSE

Herein, we propose the use of the "KeraVio Ring", which is a portable, selfie-based, smartphone-attached corneal topography system that is based on the Placido ring videokeratoscope. The goal of this study was to evaluate and compare corneal parameters between KeraVio Ring and conventional corneal tomography images.

METHODS

We designed the KeraVio Ring as a device comprising 3D-printed LED rings for generating Placido rings that can be attached to a smartphone. Two LED rings are attached to a cone-shaped device, and both corneas are illuminated. Selfies were taken using the KeraVio Ring attached to the smartphone without assistance from any of the examiners. Captured Placido rings on the cornea were analysed by intelligent software to calculate corneal parameters. Patients with normal, keratoconus, or LASIK-treated eyes were included. Anterior segment optical coherence tomography (AS-OCT) was also performed for each subject.

RESULTS

We found highly significant correlations between the steepest and flattest keratometry, corneal astigmatism, and vector components obtained with the KeraVio Ring and AS-OCT. In subjects with normal, keratoconus, and LASIK-treated eyes, the mean difference in corneal astigmatism between the two devices was -0.8 ± 1.4 diopters (D) (95% limits of agreement (LoA), -3.6 to 2.0), -1.8 ± 3.7 D (95% LoA, -9.1 to 5.5), and -1.5 ± 1.3 D (95% LoA, -4.0 to 1.1), respectively.

CONCLUSIONS

The experimental results showed that the corneal parameters obtained by the KeraVio Ring were correlated with those obtained with AS-OCT. The KeraVio Ring has the potential to address an unmet need by providing a tool for portable selfie-based corneal topography.

Clinical Applications and Future Directions of Smartphone Fundus Imaging

The advent of smartphone fundus imaging technology has marked a significant evolution in the field of ophthalmology, offering a novel approach to the diagnosis and management of retinopathy. This review provides an overview of smartphone fundus imaging, including clinical applications, advantages, limitations, clinical applications, and future directions. The traditional fundus imaging techniques are limited by their cost, portability, and accessibility, particularly in resource-limited settings. Smartphone fundus imaging emerges as a cost-effective, portable, and accessible alternative. This technology facilitates the early detection and monitoring of various retinal pathologies, including diabetic retinopathy, age-related macular degeneration, and retinal vascular disorders, thereby democratizing access to essential diagnostic services. Despite its advantages, smartphone fundus imaging faces challenges in image quality, standardization, regulatory considerations, and medicolegal issues. By addressing these limitations, this review highlights the areas for future research and development to fully harness the potential of smartphone fundus imaging in enhancing patient care and visual outcomes. The integration of this technology into telemedicine is also discussed, underscoring its role in facilitating remote patient care and collaborative care among physicians. Through this review, we aim to contribute to the understanding and advancement of smartphone fundus imaging as a valuable tool in ophthalmic practice, paving the way for its broader adoption and integration into medical diagnostics.

Mobile App for Enhanced Anterior Cruciate Ligament (ACL) Assessment in Conscious Subjects: "Pivot-Shift Meter"

Anterior cruciate ligament (ACL) instability poses a considerable challenge in traumatology and orthopedic medicine, demanding precise diagnostics for optimal treatment. The pivot-shift test, a pivotal assessment tool, relies on subjective interpretation, emphasizing the need for supplementary imaging. This study addresses this limitation by introducing a machine learning classification algorithm integrated into a mobile application, leveraging smartphones' built-in inertial sensors for dynamic rotational stability assessment during knee examinations. Orthopedic specialists conducted knee evaluations on a cohort of 52 subjects, yielding valuable insights. Quantitative analyses, employing the Intraclass Correlation Coefficient (ICC), demonstrated robust agreement in both intraobserver and interobserver assessments. Specifically, ICC values of 0.94 reflected strong concordance in the timing between maneuvers, while signal amplitude exhibited consistency, with the ICC ranging from 0.71 to 0.66. The introduced machine learning algorithms proved effective, accurately classifying 90% of cases exhibiting joint hypermobility. These quantifiable results underscore the algorithm's reliability in assessing knee stability. This study emphasizes the practicality and effectiveness of implementing machine learning algorithms within a mobile application, showcasing its potential as a valuable tool for categorizing signals captured by smartphone inertial sensors during the pivot-shift test.

A commentary on the development and use of smartphone imaging devices

Current-age smartphones are known for their wide array of functionality and are now being utilized in the field of healthcare and medicine due to their proven capabilities as smartphone imaging devices (SIDs). Recent technical advancements enabled the integration of special add-on lenses with smartphones to transform them into SIDs. With the rising demand for efficient point-of-care (PoC) devices for better diagnostic applications, SIDs will be a one-stop solution. Additionally, portability, user-friendliness and low-cost make it accessible for all even at remote locations. Furthermore, improvements in resolution, magnification and field-of-view (FOV) have attracted the scientific community to use SIDs in various biomedical applications such as disease diagnosis, food quality control and pathogen detection. SIDs can be arranged in various combinational setups by using different illumination sources and optics to achieve suitable contrast and visibility of the specimen under study. This Commentary illustrates the various illumination sources used in SID and also spotlights their design and applications.

A digital image colorimetry system based on smart devices for immediate and simultaneous determination of enzyme-linked immunosorbent assays

Standard enzyme-linked immunosorbent assays based on microplates are frequently utilized for various molecular sensing, disease screening, and nanomedicine applications. Comparing this multi-well plate batched analysis to non-batched or non-standard testing, the diagnosis expenses per patient are drastically reduced. However, the requirement for rather big and pricey readout instruments prevents their application in environments with limited resources, especially in the field. In this work, a handheld cellphone-based colorimetric microplate reader for quick, credible, and novel analysis of digital images of human cancer cell lines at a reasonable price was developed. Using our in-house-developed app, images of the plates are captured and sent to our servers, where they are processed using a machine learning algorithm to produce diagnostic results. Using FDA-approved human epididymis protein of ovary IgG (HE4), prostate cancer cell line (PC3), and bladder cancer cell line (5637) ELISA tests, we successfully examined this mobile platform. The accuracies for the HE4, PC3, and 5637 tests were 93%, 97.5%, and 97.2%, respectively. By contrasting the findings with the measurements made using optical absorption EPOCH microplate readers and optical absorption Tecan microplate readers, this approach was found to be accurate and effective. As a result, digital image colorimetry on smart devices offered a practical, user-friendly, affordable, precise, and effective method for quickly identifying human cancer cell lines. Thus, healthcare providers might use this portable device to carry out high-throughput illness screening, epidemiological investigations or monitor vaccination campaigns.

Leveraging a smartphone to perform time-gated luminescence measurements

Empowered by advanced on-board sensors, high-performance optics packages and ever-increasing computational power, smartphones have democratized data generation, collection, and analysis. Building on this capacity, many platforms have been developed to enable its use as an optical sensing platform for colorimetric and fluorescence measurements. In this paper, we report the ability to enable a smartphone to perform laboratory quality time-resolved analysis of luminescent samples via the exploitation of the rolling shutter mechanism of the native CMOS imager. We achieve this by leveraging the smartphone's standard image capture applications, commercially available image analysis software, and housing the device within a UV-LED containing case. These low-cost modifications enable us to demonstrate the smartphone's analytical potential by performing tasks ranging from authentication and encryption to the interrogation of packaging, compounds, and physical phenomena. This approach underscores the power of repurposing existing technologies to extend the reach and inclusivity of scientific exploration, opening new avenues for data collection and analysis.

Outcomes of Emergency Trauma Patients After the Implementation of Web Application Operating Systems

PURPOSE

Trauma has significant impacts on the livelihoods and well-being of patients. Prompt emergency, medical, and nursing care is the key to reducing mortality rates. Digital platforms have become important for patient care. This research aimed to evaluate patient outcomes after implementing a novel web application operating system in trauma care.

METHODS

A descriptive comparative study was conducted on trauma patients. The patients were divided into two groups: those who used the developed application (n = 70) and those who did not (n = 70). The patients' characteristics, the time of the trauma team's arrival at the emergency department (ED) and the length of stay in the ED, and patients' outcomes were collected from electronic medical records and the application database. A statistical analysis was performed to evaluate this data. Sixty registered nurses who used the application completed the survey on the feasibility of the application.

RESULTS

The activated trauma intervals for the non-application-used group and the application-used group were 5.0 ± 1.1 and 3.1 ± 0.4 minutes, respectively (p = .010). The length of stay in the ED for the non-application-used group and the application-used group were 30.1 ± 5.1 and 18.3 ± 6.2 minutes, respectively. A high level of agreement confirms the feasibility of the application.

CONCLUSIONS

This application improves patient outcomes in terms of length of stay. This mobile application can improve the cooperation and communication and efficacy of the trauma care team.

Smartphone-based dual radiometric fluorescence and white-light imager for quantification of protoporphyrin IX in skin

Significance

The quantification of protoporphyrin IX (PpIX) in skin can be used to study photodynamic therapy (PDT) treatments, understand porphyrin mechanisms, and enhance preoperative mapping of non-melanoma skin cancers.

Aim

We aim to develop a smartphone-based imager for performing simultaneous radiometric fluorescence (FL) and white light (WL) imaging to study the baseline levels, accumulation, and photobleaching of PpIX in skin.

Approach

A smartphone-based dual FL and WL imager (sDUO) is introduced alongside new radiometric calibration methods for providing SI-units of measurements in both pre-clinical and clinical settings. These radiometric measurements and corresponding PpIX concentration estimations are applied to clinical measurements to understand mechanistic differences between PDT treatments, accumulation differences between normal tissue and actinic keratosis lesions, and the correlation of photosensitizer concentrations to treatment outcomes.

Results

The sDUO alongside the developed methods provided radiometric FL measurements (nW / cm 2 ) with a demonstrated sub nanomolar PpIX sensitivity in 1% intralipid phantoms. Patients undergoing PDT treatment of actinic keratosis (AK) lesions were imaged, capturing the increase and subsequent decrease in FL associated with the incubation and irradiation timepoints of lamp-based PDT. Furthermore, the clinical measurements showed mechanistic differences in new daylight-based treatment modalities alongside the selective accumulation of PpIX within AK lesions. The use of the radiometric calibration enabled the reporting of detected PpIX FL in units of nW / cm 2 with the use of liquid phantom measurements allowing for the estimation of in-vivo molar concentrations of skin PpIX.

Conclusions

The phantom, pre-clinical, and clinical measurements demonstrated the capability of the sDUO to provide quantitative measurements of PpIX FL. The results demonstrate the use of the sDUO for the quantification of PpIX accumulation and photobleaching in a clinical setting, with implications for improving the diagnosis and treatment of various skin conditions.

Comparison of sway meter and Kinovea software as a tool of measurement for the sway parameters during quiet standing: An observational study

BACKGROUND

Several attempts have been made to quantify postural sway, from simple observational techniques to advanced computer technology. Measuring sway using commercial motion tracking devices and force plates are expensive and not feasible in evaluation on non-standardised surfaces. Video cameras can be used as an affordable alternative to perform human motion capturing, and this data can be analysed using motion tracking software like Kinovea; a free, reliable software that provides valid data, and an acceptable level of accuracy in angular and linear measurements. This study evaluated the reliability of Kinovea software to measure the sway amplitude in comparison with sway meter.

METHODS

Thirty-six young women were recruited by convenience to this prospective observational study. Sway amplitude of the participants were measured using a sway meter on three different surfaces, with eyes opened and closed conditions, using modified Lords sway meter and videography. Videos were later analysed using Kinovea motion analysing software. The quantitative data of sway parameters were analysed for reliability using intraclass-correlation co-efficient and Bland Altman plot.

RESULTS

There was an excellent correlation (>0.90) between the sway measurement values obtained from both methods irrespective of the surfaces. But the reliability was greater for the medio-lateral sway on the pebbled surfaces (0.981), and least for the anterior posterior sway on the same surface.

CONCLUSION

This study concludes that, there is an excellent reliability for the video based sway analysis using Kinovea software. Hence this method can be used as an affordable alternative to measure the sway parameters.

SmartOCT: smartphone-integrated optical coherence tomography

Smartphone devices have seen unprecedented technical innovation in computational power and optical imaging capabilities, making them potentially invaluable tools in scientific imaging applications. The smartphone's compact form-factor and broad accessibility has motivated researchers to develop smartphone-integrated imaging systems for a wide array of applications. Optical coherence tomography (OCT) is one such technique that could benefit from smartphone-integration. Here, we demonstrate smartOCT, a smartphone-integrated OCT system that leverages built-in components of a smartphone for detection, processing and display of OCT data. SmartOCT uses a broadband visible-light source and line-field OCT design that enables snapshot 2D cross-sectional imaging. Furthermore, we describe methods for processing smartphone data acquired in a RAW data format for scientific applications that improves the quality of OCT images. The results presented here demonstrate the potential of smartphone-integrated OCT systems for low-resource environments.

Deep learning-assisted ultra-accurate smartphone testing of paper-based colorimetric ELISA assays

Smartphone has long been considered as one excellent platform for disease screening and diagnosis, especially when combined with microfluidic paper-based analytical devices (μPADs) that feature low cost, ease of use, and pump-free operations. In this paper, we report a deep learning-assisted smartphone platform for ultra-accurate testing of paper-based microfluidic colorimetric enzyme-linked immunosorbent assay (c-ELISA). Different from existing smartphone-based μPAD platforms, whose sensing reliability is suffered from uncontrolled ambient lighting conditions, our platform is able to eliminate those random lighting influences for enhanced sensing accuracy. We first constructed a dataset that contains c-ELISA results (n = 2048) of rabbit IgG as the model target on μPADs under eight controlled lighting conditions. Those images are then used to train four different mainstream deep learning algorithms. By training with these images, the deep learning algorithms can well eliminate the influences of lighting conditions. Among them, the GoogLeNet algorithm gives the highest accuracy (>97%) in quantitative rabbit IgG concentration classification/prediction, which also provides 4% higher area under curve (AUC) value than that of the traditional curve fitting results analysis method. In addition, we fully automate the whole sensing process and achieve the "image in, answer out" to maximize the convenience of the smartphone. A simple and user-friendly smartphone application has been developed that controls the whole process. This newly developed platform further enhances the sensing performance of μPADs for use by laypersons in low-resource areas and can be facilely adapted to the real disease protein biomarkers detection by c-ELISA on μPADs.

mHealth hyperspectral learning for instantaneous spatiospectral imaging of hemodynamics

Hyperspectral imaging acquires data in both the spatial and frequency domains to offer abundant physical or biological information. However, conventional hyperspectral imaging has intrinsic limitations of bulky instruments, slow data acquisition rate, and spatiospectral trade-off. Here we introduce hyperspectral learning for snapshot hyperspectral imaging in which sampled hyperspectral data in a small subarea are incorporated into a learning algorithm to recover the hypercube. Hyperspectral learning exploits the idea that a photograph is more than merely a picture and contains detailed spectral information. A small sampling of hyperspectral data enables spectrally informed learning to recover a hypercube from a red-green-blue (RGB) image without complete hyperspectral measurements. Hyperspectral learning is capable of recovering full spectroscopic resolution in the hypercube, comparable to high spectral resolutions of scientific spectrometers. Hyperspectral learning also enables ultrafast dynamic imaging, leveraging ultraslow video recording in an off-the-shelf smartphone, given that a video comprises a time series of multiple RGB images. To demonstrate its versatility, an experimental model of vascular development is used to extract hemodynamic parameters via statistical and deep learning approaches. Subsequently, the hemodynamics of peripheral microcirculation is assessed at an ultrafast temporal resolution up to a millisecond, using a conventional smartphone camera. This spectrally informed learning method is analogous to compressed sensing; however, it further allows for reliable hypercube recovery and key feature extractions with a transparent learning algorithm. This learning-powered snapshot hyperspectral imaging method yields high spectral and temporal resolutions and eliminates the spatiospectral trade-off, offering simple hardware requirements and potential applications of various machine learning techniques.

Moving toward smart biomedical sensing

The development of novel biomedical sensors as highly promising devices/tools in early diagnosis and therapy monitoring of many diseases and disorders has recently witnessed unprecedented growth; more and faster than ever. Nonetheless, on the eve of Industry 5.0 and by learning from defects of current sensors in smart diagnostics of pandemics, there is still a long way to go to achieve the ideal biomedical sensors capable of meeting the growing needs and expectations for smart biomedical/diagnostic sensing through eHealth systems. Herein, an overview is provided to highlight the importance and necessity of an inevitable transition in the era of digital health/Healthcare 4.0 towards smart biomedical/diagnostic sensing and how to approach it via new digital technologies including Internet of Things (IoT), artificial intelligence, IoT gateways (smartphones, readers), etc. This review will bring together the different types of smartphone/reader-based biomedical sensors, which have been employing for a wide variety of optical/electrical/electrochemical biosensing applications and paving the way for future eHealth diagnostic devices by moving towards smart biomedical sensing. Here, alongside highlighting the characteristics/criteria that should be met by the developed sensors towards smart biomedical sensing, the challenging issues ahead are delineated along with a comprehensive outlook on this extremely necessary field.

Smartphone imaging repository: a novel method for creating a CT image bank

BACKGROUND

Imaging repositories are commonly attached to ongoing clinical trials, but capturing, transmitting, and storing images can be complicated and labor-intensive. Typical methods include outdated technologies such as compact discs. Electronic file transfer is becoming more common, but even this requires hours of staff time on dedicated computers in the radiology department.

METHODS

We describe and test an image capture method using smartphone camera video-derived images of brain computed tomography (CT) scans of traumatic intracranial hemorrhage. The deidentified videos are emailed or uploaded from the emergency department for central adjudication. We selected eight scans, mild moderate, and severe subdural and multicompartmental hematomas and mild and moderate intraparenchymal hematomas. Ten users acquired data using seven different smartphones. We measured the time in seconds it took to capture and send the files. The primary outcomes were hematoma volume measured by ABC/2, Marshall scale, midline shift measurement, image quality by a contrast-to-noise ratio (CNR), and time to capture. A radiologist and an imaging scientist applied the ABC/2 method and calculated the Marshall scale and midline shift on the data acquired on different smartphones and the PACS in a randomized order. We calculate the intraclass correlation coefficient (ICC). We measured image quality by calculating the contrast-to-noise ratio (CNR). We report summary statistics on time to capture in the smartphone group without a comparator.

RESULTS

ICC for lesion volume, midline shift, and Marshall score were 0.973 (95% CI 0.931, 0.994), 0.998 (95% CI: 0.996, 0.999), and 0.973 (0.931, 0.994), respectively. Lesion conspicuity was not different among the image types via assessment of CNR using the Friedman test, [Formula: see text] of 24.8, P =  < .001, with a small Kendall's W effect size (0.591). Mean (standard deviation) time to capture and email the video was 60.1 (24.3) s.

CONCLUSIONS

Typical smartphones may produce video image quality high enough for use in a clinical trial imaging repository. Video capture and transfer takes only seconds, and hematoma volumes, Marshall scales, and image quality measured on the videos did not differ significantly from those calculated on the PACS.

Analysis of Polarization Images in the Microphysical Blood Parameters Research for the Hematocrit Diagnostics

The development of non-invasive optoelectronic technologies for human blood monitoring is one of the important research areas for medicine. A critical analysis of optoelectronic methods of blood research and the micromechanical systems based on them is carried out in this article. A design realization of a polarizing portable system for non-invasive monitoring of hematocrit as one of the basic homeostatic constants of the human body containing information about the microphysical parameters of blood cells has been substantiated. A physical model of polarized radiation conversion in a video information system of laser sensing of a biological research object has been formed. Visual and quantitative differences in the spatial distribution of polarization parameters of the scattered radiation for the states of the body with different hematocrit levels have been revealed. A scheme of a multichannel imaging portable system, based on a smartphone using miniature optical and microelectronic components of information conversion for non-invasive monitoring of microphysical blood parameters, has been created. The system implements the principle of polarimetric blood photometry and a multiparametric analysis of the polarization properties of the laser radiation scattered by blood. The developed portable optoelectronic system, based on a smartphone, can be used for rapid blood diagnostics in disaster medicine and the presence of clinical contraindications to the formation of invasive tests. The proposed polarization-based approach is a promising automated alternative to traditional devices and systems for the research of microphysical blood parameters.

Flash Characterization of Smartphones Used in Point-of-Care Diagnostics

Rapidly growing interest in smartphone cameras as the basis of point-of-need diagnostic and bioanalytical technologies increases the importance of quantitative characterization of phone optical performance under real-world operating conditions. In the context of our development of lateral-flow immunoassays based on phosphorescent nanoparticles, we have developed a suite of tools for characterizing the temporal and spectral profiles of smartphone torch and flash emissions, and their dependence on phone power state. In this work, these tools are described and documented to make them easily available to others, and demonstrated by application to characterization of Apple iPhone 5s, iPhone 6s, iPhone 8, iPhone XR, and Samsung Note8 flash performance as a function of time and wavelength, at a variety of power settings. Flash and torch intensity and duration vary with phone state and among phone models. Flash has high variability when the battery charge is below 10%, thus, smartphone-based Point-of-Care (POC) tests should only be performed at a battery level of at least 15%. Some output variations could substantially affect the results of assays that rely on the smartphone flash.

Construction of ratiometric fluorescence sensor and test strip with smartphone based on molecularly imprinted dual-emission quantum dots for the selective and sensitive detection of domoic acid

Domoic acid (DA), a highly neurotoxic metabolite produced by phytoplankton, contaminates seafood products and threats humankind. Herein, we have proposed a molecular imprinting fluorescence sensor with internal standard ratiometric mode for sensing of DA in seafood and seawater. In this study, the silicon-coated blue luminous carbon dots (B-CDs@SiO₂) and CdTe acted as reference probe (430 nm) and response probe (610 nm), respectively. Subsequently, the two probes were assembled and the molecularly imprinted polymer (MIP) was introduced as the recognition element to construct the core component of the sensor (B-CDs@SiO₂/CdTe MIP). When DA exists, it can be specifically adsorbed by the amino-rich imprinted sites on surface of B-CDs@SiO₂/CdTe MIP and further assembled into the hydrogen-bonds complex, which can lead to the decrease in the fluorescence signal of MIP at 610 nm owing to the electron transfer from CdTe to DA. However, the fluorescence signal of MIP at 430 nm is not affected because of the protection of silica layer. Based on this principle, the designed internal standard ratiometric fluorescence sensor reveals high sensitivity, excellent selectivity, and wide linear range of 0.03-1 μM with a detection limit of 18 nM. Further, the portable fluorescent test strip with smartphone has been designed for semi-quantitative sensing of DA, which has potential application prospects for field analysis.

Simplifying the complex: accessible microfluidic solutions for contemporary processes within in vitro diagnostics

In vitro diagnostics (IVDs) form the cornerstone of modern medicine. They are routinely employed throughout the entire treatment pathway, from initial diagnosis through to prognosis, treatment planning, and post-treatment surveillance. Given the proven links between high quality diagnostic testing and overall health, ensuring broad access to IVDs has long been a focus of both researchers and medical professionals. Unfortunately, the current diagnostic paradigm relies heavily on centralized laboratories, complex and expensive equipment, and highly trained personnel. It is commonly assumed that this level of complexity is required to achieve the performance necessary for sensitive and specific disease diagnosis, and that making something affordable and accessible entails significant compromises in test performance. However, recent work in the field of microfluidics is challenging this notion. By exploiting the unique features of microfluidic systems, researchers have been able to create progressively simple devices that can perform increasingly complex diagnostic assays. This review details how microfluidic technologies are disrupting the status quo, and facilitating the development of simple, affordable, and accessible integrated IVDs. Importantly, we discuss the advantages and limitations of various approaches, and highlight the remaining challenges within the field.

Calibration Methods of a Portable Polarizing System for Monitoring Optically Inhomogeneous Media

Theoretical aspects of methods for calibrating Stokes polarimeters are considered. The prospects and opportunities for implementing the presented methods for calibrating portable polarization systems used in biology and medicine are determined. Based on a comparative analysis, a method for calibrating a portable Stokes polarimeter for medical applications is proposed. The chosen method provides the smallest error in measuring the parameters of the Stokes vector for calculating the parameters of optical anisotropy and researching the polarization properties of biological tissues. A series of experimental research and statistical analysis of the spatial distributions of the polarization parameters of the calibration sample was carried out to use the results for forming the instrument matrix of the developed Stokes polarimeter during calibration.

Smart Mushroom-Inspired Imprintable and Lightly Detachable (MILD) Microneedle Patterns for Effective COVID-19 Vaccination and Decentralized Information Storage

The key to controlling the spread of the coronavirus disease 2019 (COVID-19) and reducing mortality is highly dependent on the safe and effective use of vaccines for the general population. Current COVID-19 vaccination practices (intramuscular injection of solution-based vaccines) are limited by heavy reliance on medical professionals, poor compliance, and laborious vaccination recording procedures, resulting in a waste of health resources and low vaccination coverage, etc. In this study, we developed a smart mushroom-inspired imprintable and lightly detachable (MILD) microneedle platform for the effective and convenient delivery of multidose COVID-19 vaccines and decentralized vaccine information storage. The mushroom-like structure allows the MILD system to be easily pressed into the skin and detached from the patch base, acting as a "tattoo" to record the vaccine counts in situ without any storage equipment, offering quick accessibility and effortless readout, saving a great deal of valuable time and energy for both patients and health professionals. After loading inactivated SARS-CoV-2 virus-based vaccines, MILD system induced a high level of antibodies against the SARS-CoV-2 receptor-binding domain (RBD) in vivo without eliciting systemic toxicity and local damage. Collectively, this smart delivery platform serves as a promising carrier to improve COVID-19 vaccination efficacy through its dual capabilities of vaccine delivery and in situ data storage, thus exhibiting great potential for helping to contain the COVID-19 pandemic or a resurgence.

A Comprehensive Review of Methods and Equipment for Aiding Automatic Glaucoma Tracking

Glaucoma is a chronic optic neuropathy characterized by irreversible damage to the retinal nerve fiber layer (RNFL), resulting in changes in the visual field (VC). Glaucoma screening is performed through a complete ophthalmological examination, using images of the optic papilla obtained in vivo for the evaluation of glaucomatous characteristics, eye pressure, and visual field. Identifying the glaucomatous papilla is quite important, as optical papillary images are considered the gold standard for tracking. Therefore, this article presents a review of the diagnostic methods used to identify the glaucomatous papilla through technology over the last five years. Based on the analyzed works, the current state-of-the-art methods are identified, the current challenges are analyzed, and the shortcomings of these methods are investigated, especially from the point of view of automation and independence in performing these measurements. Finally, the topics for future work and the challenges that need to be solved are proposed.

Automated Affective Computing Based on Bio-Signals Analysis and Deep Learning Approach

Extensive possibilities of applications have rendered emotion recognition ineluctable and challenging in the fields of computer science as well as in human-machine interaction and affective computing. Fields that, in turn, are increasingly requiring real-time applications or interactions in everyday life scenarios. However, while extremely desirable, an accurate and automated emotion classification approach remains a challenging issue. To this end, this study presents an automated emotion recognition model based on easily accessible physiological signals and deep learning (DL) approaches. As a DL algorithm, a Feedforward Neural Network was employed in this study. The network outcome was further compared with canonical machine learning algorithms such as random forest (RF). The developed DL model relied on the combined use of wearables and contactless technologies, such as thermal infrared imaging. Such a model is able to classify the emotional state into four classes, derived from the linear combination of valence and arousal (referring to the circumplex model of affect’s four-quadrant structure) with an overall accuracy of 70% outperforming the 66% accuracy reached by the RF model. Considering the ecological and agile nature of the technique used the proposed model could lead to innovative applications in the affective computing field.

Smartphone-based corneal topography with null-screens

To measure the shape of the fast corneal surface of the human eye, we propose the design and characterization of a compact corneal topographer using the capabilities of a smartphone. The performance evaluation of the compact corneal topographer includes the calculation and compensation of the distortion introduced by the smartphone lens used to acquire the images and the evaluation of a reference surface. To demonstrate the feasibility of our proposal, we performed surface topography measurements on some human corneas and compared the results with those obtained by a commercial corneal topographer. We showed that the results obtained with our algorithms were consistent with other methods that analyze the corneal surface.

Skin chromophore mapping by smartphone RGB camera under spectral band and spectral line illumination

SIGNIFICANCE

Multispectral imaging enables mapping of chromophore content changes in skin neoplasms, which helps to diagnose a pathology. Different types of light sources can be used for the imaging. Design of laser-based illuminators is more complicated and, consequently, they are more expensive than LED-based illuminators. On the other hand, spectral line illumination has the advantage of less complicated calculations, since only the discrete maximum wavelengths need to be considered. Spectral band and spectral line approaches for multispectral skin diagnostics have not been compared so far. This can help to evaluate the accuracy and effectiveness of both approaches.

AIM

To compare two specific illumination modalities-spectral band and spectral line illumination-from the point of performance for mapping of in vivo skin chromophores.

APPROACH

Three spectral images of the same skin malformations were captured by a smartphone RGB camera with two different add-on illuminators comprising LED emitters and laser emitters, respectively. Five types of benign skin neoplasms were included in our study. Concentrations of skin melanin, oxy- and deoxy-hemoglobin at image pixel groups were calculated using the Beer-Lambert law.

RESULTS

Skin chromophore maps and statistical analysis of mean concentrations' changes in the neoplasms compared to the surrounding skin are presented and discussed. The data of the laser emitters led to significantly higher (∼10 times) increase of the oxy-hemoglobin values in vascular neoplasms and much lower deoxy-hemoglobin values, if compared to the data obtained by the LED emitters.

CONCLUSIONS

Analysis of the obtained chromophore distribution maps and concentration variations in neoplasms led to conclusion that the spectral line illumination approach is more appropriate for this application. Considering only the peak wavelengths of illumination spectral bands leads to essentially different results if compared to those obtained by spectral line illumination and may cause misinterpretations in the clinical assessment of skin neoplasms.

Ultracompact fluorescence smartphone attachment using built-in optics for protoporphyrin-IX quantification in skin

Smartphone-based fluorescence imaging systems have the potential to provide convenient quantitative image guidance at the point of care. However, common approaches have required the addition of complex optical attachments, which reduce translation potential. In this study, a simple clip-on attachment appropriate for fluorescence imaging of protoporphyrin-IX (PpIX) in skin was designed using the built-in light source and ultrawide camera sensor of a smartphone. Software control for image acquisition and quantitative analysis was developed using the 10-bit video capability of the phone. Optical performance was characterized using PpIX in liquid tissue phantoms and endogenously produced PpIX in mice and human skin. The proposed system achieves a very compact form factor (<30 cm3) and can be readily fabricated using widely available low-cost materials. The limit of detection of PpIX in optical phantoms was <10 nM, with good signal linearity from 10 to 1000 nM (R2 >0.99). Both murine and human skin imaging verified that in vivo PpIX fluorescence was detected within 1 hour of applying aminolevulinic acid (ALA) gel. This ultracompact handheld system for quantification of PpIX in skin is well-suited for dermatology clinical workflows. Due to its simplicity and form factor, the proposed system can be readily adapted for use with other smartphone devices and fluorescence imaging applications. Hardware design and software for the system is made freely available on GitHub (https://github.com/optmed/CompactFluorescenceCam).

Paper-based analytical devices for virus detection: Recent strategies for current and future pandemics

The importance of user-friendly, inexpensive, sensitive, and selective detection of viruses has been highlighted again due to the recent Coronavirus disease 2019 (COVID-19) pandemic. Among the analytical tools, paper-based devices (PADs) have become a leading alternative for point-of-care (POC) testing. In this review, we discuss the recent development strategies and applications in nucleic acid-based, antibody/antigen-based and other affinity-based PADs using optical and electrochemical detection methods for sensing viruses. In addition, advantages and drawbacks of presented PADs are identified. Current state and insights towards future perspectives are presented regarding developing POC diagnosis platform for COVID-19. This review considers state-of-the-art technologies for further development and improvement in PADs performance for virus detection.