Inter-visit variability of conjunctival microvascular hemodynamic measurements in healthy and diabetic retinopathy subjects

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.

Progress of Bulbar Conjunctival Microcirculation Alterations in the Diagnosis of Ocular Diseases

Bulbar conjunctival microcirculation is a microvascular system distributed in the translucent bulbar conjunctiva near the corneal limbus. Multiple ocular diseases lead to bulbar conjunctival microcirculation alterations, which means that bulbar conjunctival microcirculation alterations would be potential screening and diagnostic indicators for these ocular diseases. In recent years, with the emergence and application of a variety of noninvasive observation devices for bulbar conjunctiva microcirculation and new image processing technologies, studies that explored the potential of bulbar conjunctival microcirculation alterations in the diagnosis of ocular diseases have been emerging. However, the potential of bulbar conjunctival microcirculation alterations as indicators for ocular diseases has not been exploited to full advantage. The observation devices, image processing methods, and algorithms are not unified. And large-scale research is needed to concrete bulbar conjunctival microcirculation alterations as indicators for ocular diseases. In this paper, we provide an update on the progress of bulbar conjunctival microcirculation alterations in the diagnosis of ocular diseases in recent five years (from January 2017 to March 2022). Relevant ocular diseases include contact lens wearing, dry eye, conjunctival malignant melanoma, conjunctival nevus, and diabetic retinopathy.

EVA: Fully automatic hemodynamics assessment system for the bulbar conjunctival microvascular network

BACKGROUND AND OBJECTIVE

Conjunctival microcirculation has been used to quantitatively assess microvascular changes due to systemic disorders. The space between red blood cell clusters in conjunctival microvessels is essential for assessing hemodynamics. However, it causes discontinuities in vessel image segmentation and increases the difficulty of automatically measuring blood velocity. In this study, we developed an EVA system based on deep learning to maintain vessel segmentation continuity and automatically measure blood velocity.

METHODS

The EVA system sequentially performs image registration, vessel segmentation, diameter measurement, and blood velocity measurement on conjunctival images. A U-Net model optimized with a connectivity-preserving loss function was used to solve the problem of discontinuities in vessel segmentation. Then, an automatic measurement algorithm based on line segment detection was proposed to obtain accurate blood velocity. Finally, the EVA system assessed hemodynamic parameters based on the measured blood velocity in each vessel segment.

RESULTS

The EVA system was validated for 23 videos of conjunctival microcirculation captured using functional slit-lamp microscopy. The U-Net model produced the longest average vessel segment length, 158.03 ± 181.87 µm, followed by the adaptive threshold method and Frangi filtering, which produced lengths of 120.05 ± 151.47 µm and 99.94 ± 138.12 µm, respectively. The proposed method and one based on cross-correlation were validated to measure blood velocity for a dataset consisting of 30 vessel segments. Bland-Altman analysis showed that compared with the cross-correlation method (bias: 0.36, SD: 0.32), the results of the proposed method were more consistent with a manual measurement-based gold standard (bias: -0.04, SD: 0.14).

CONCLUSIONS

The proposed EVA system provides an automatic and reliable solution for quantitative assessment of hemodynamics in conjunctival microvascular images, and potentially can be applied to hypoglossal microcirculation images.

Identifying diabetes from conjunctival images using a novel hierarchical multi-task network

Diabetes can cause microvessel impairment. However, these conjunctival pathological changes are not easily recognized, limiting their potential as independent diagnostic indicators. Therefore, we designed a deep learning model to explore the relationship between conjunctival features and diabetes, and to advance automated identification of diabetes through conjunctival images. Images were collected from patients with type 2 diabetes and healthy volunteers. A hierarchical multi-tasking network model (HMT-Net) was developed using conjunctival images, and the model was systematically evaluated and compared with other algorithms. The sensitivity, specificity, and accuracy of the HMT-Net model to identify diabetes were 78.70%, 69.08%, and 75.15%, respectively. The performance of the HMT-Net model was significantly better than that of ophthalmologists. The model allowed sensitive and rapid discrimination by assessment of conjunctival images and can be potentially useful for identifying diabetes.

Noninvasive Hemoglobin Level Prediction in a Mobile Phone Environment: State of the Art Review and Recommendations

BACKGROUND

There is worldwide demand for an affordable hemoglobin measurement solution, which is a particularly urgent need in developing countries. The smartphone, which is the most penetrated device in both rich and resource-constrained areas, would be a suitable choice to build this solution. Consideration of a smartphone-based hemoglobin measurement tool is compelling because of the possibilities for an affordable, portable, and reliable point-of-care tool by leveraging the camera capacity, computing power, and lighting sources of the smartphone. However, several smartphone-based hemoglobin measurement techniques have encountered significant challenges with respect to data collection methods, sensor selection, signal analysis processes, and machine-learning algorithms. Therefore, a comprehensive analysis of invasive, minimally invasive, and noninvasive methods is required to recommend a hemoglobin measurement process using a smartphone device.

OBJECTIVE

In this study, we analyzed existing invasive, minimally invasive, and noninvasive approaches for blood hemoglobin level measurement with the goal of recommending data collection techniques, signal extraction processes, feature calculation strategies, theoretical foundation, and machine-learning algorithms for developing a noninvasive hemoglobin level estimation point-of-care tool using a smartphone.

METHODS

We explored research papers related to invasive, minimally invasive, and noninvasive hemoglobin level measurement processes. We investigated the challenges and opportunities of each technique. We compared the variation in data collection sites, biosignal processing techniques, theoretical foundations, photoplethysmogram (PPG) signal and features extraction process, machine-learning algorithms, and prediction models to calculate hemoglobin levels. This analysis was then used to recommend realistic approaches to build a smartphone-based point-of-care tool for hemoglobin measurement in a noninvasive manner.

RESULTS

The fingertip area is one of the best data collection sites from the body, followed by the lower eye conjunctival area. Near-infrared (NIR) light-emitting diode (LED) light with wavelengths of 850 nm, 940 nm, and 1070 nm were identified as potential light sources to receive a hemoglobin response from living tissue. PPG signals from fingertip videos, captured under various light sources, can provide critical physiological clues. The features of PPG signals captured under 1070 nm and 850 nm NIR LED are considered to be the best signal combinations following a dual-wavelength theoretical foundation. For error metrics presentation, we recommend the mean absolute percentage error, mean squared error, correlation coefficient, and Bland-Altman plot.

CONCLUSIONS

We addressed the challenges of developing an affordable, portable, and reliable point-of-care tool for hemoglobin measurement using a smartphone. Leveraging the smartphone's camera capacity, computing power, and lighting sources, we define specific recommendations for practical point-of-care solution development. We further provide recommendations to resolve several long-standing research questions, including how to capture a signal using a smartphone camera, select the best body site for signal collection, and overcome noise issues in the smartphone-captured signal. We also describe the process of extracting a signal's features after capturing the signal based on fundamental theory. The list of machine-learning algorithms provided will be useful for processing PPG features. These recommendations should be valuable for future investigators seeking to build a reliable and affordable hemoglobin prediction model using a smartphone.

Assessment of the conjunctival microcirculation for patients presenting with acute myocardial infarction compared to healthy controls

Microcirculatory dysfunction occurs early in cardiovascular disease (CVD) development. Acute myocardial infarction (MI) is a late consequence of CVD. The conjunctival microcirculation is readily-accessible for quantitative assessment and has not previously been studied in MI patients. We compared the conjunctival microcirculation of acute MI patients and age/sex-matched healthy controls to determine if there were differences in microcirculatory parameters. We acquired images using an iPhone 6s and slit-lamp biomicroscope. Parameters measured included diameter, axial velocity, wall shear rate and blood volume flow. Results are for all vessels as they were not sub-classified into arterioles or venules. The conjunctival microcirculation was assessed in 56 controls and 59 inpatients with a presenting diagnosis of MI. Mean vessel diameter for the controls was 21.41 ± 7.57 μm compared to 22.32 ± 7.66 μm for the MI patients (p < 0.001). Axial velocity for the controls was 0.53 ± 0.15 mm/s compared to 0.49 ± 0.17 mm/s for the MI patients (p < 0.001). Wall shear rate was higher for controls than MI patients (162 ± 93 s-1 vs 145 ± 88 s-1, p < 0.001). Blood volume flow did not differ significantly for the controls and MI patients (153 ± 124 pl/s vs 154 ± 125 pl/s, p = 0.84). This pilot iPhone and slit-lamp assessment of the conjunctival microcirculation found lower axial velocity and wall shear rate in patients with acute MI. Further study is required to correlate these findings further and assess long-term outcomes in this patient group with a severe CVD phenotype.

Improved conjunctival microcirculation in diabetic retinopathy patients with MTHFR polymorphisms after Ocufolin™ Administration

PURPOSE

To investigate conjunctival microvascular responses in patients with mild diabetic retinopathy (MDR) and methylenetetrahydrofolate reductase (MTHFR) polymorphisms (D + PM) after administration of Ocufolin™, a medical food containing 900 μg l-methylfolate (levomefolate calcium or [6S]-5-methyltetrahydrofolic acid, calcium salt), methylcobalamin, and other ingredients.

METHODS

Eight D + PM patients received Ocufolin™ for six months (6 M). Bulbar conjunctival microvasculature and microcirculation metrics, including vessel diameter (D), axial blood flow velocity (Va), cross-sectional blood flow velocity (Vs), flow rate (Q), and vessel density (VD, Dbox), were measured at baseline, 4 M, and 6 M.

RESULTS

The mean age was 54 ± 7 years. No significant demographic differences were found. Conjunctival microcirculation, measured as Va, Vs, and Q was significantly increased at 4 M and 6 M, compared to baseline. Va was 0.44 ± 0.10 mm/s, 0.58 ± 0.13 mm/s, 0.59 ± 0.13 mm/s in baseline, 4 M, and 6 M, respectively (P < 0.01). Similarly, Vs was 0.31 ± 0.07 mm/s, 0.40 ± 0.09 mm/s, 0.41 ± 0.09 mm/s in baseline, 4 M, and 6 M, respectively (P < 0.05). Q was 107.8 ± 49.4 pl/s, 178.0 ± 125.8 pl/s, 163.3 ± 85.8 mm/s in baseline, 4 M, and 6 M, respectively (P < 0.05). The VD at 6 M was significantly higher than that at baseline (P = 0.017). Changes of D were positively correlated with changes of Va, Q, and VD. Effects of MTHFR and haptoglobin polymorphisms on the improvements of conjunctival microcirculation and microvasculature were found.

CONCLUSIONS

Ocufolin™ supplementation improves conjunctival microcirculation in patients with diabetic retinopathy and common folate polymorphisms.

mHealth spectroscopy of blood hemoglobin with spectral super-resolution

Although blood hemoglobin (Hgb) testing is a routine procedure in a variety of clinical situations, noninvasive, continuous, and real-time blood Hgb measurements are still challenging. Optical spectroscopy can offer noninvasive blood Hgb quantification, but requires bulky optical components that intrinsically limit the development of mobile health (mHealth) technologies. Here, we report spectral super-resolution (SSR) spectroscopy that virtually transforms the built-in camera (RGB sensor) of a smartphone into a hyperspectral imager for accurate and precise blood Hgb analyses. Statistical learning of SSR enables us to reconstruct detailed spectra from three color RGB data. Peripheral tissue imaging with a mobile application is further combined to compute exact blood Hgb content without a priori personalized calibration. Measurements over a wide range of blood Hgb values show reliable performance of SSR blood Hgb quantification. Given that SSR does not require additional hardware accessories, the mobility, simplicity, and affordability of conventional smartphones support the idea that SSR blood Hgb measurements can be used as an mHealth method.

Ocular microvascular changes in patients with sepsis: a prospective observational study

Background

The aim of the study was to detect differences in the conjunctival microcirculation between septic patients and healthy subjects and to evaluate the course of conjunctival and retinal microvasculature in survivors and non-survivors over a 24-h period of time.

Methods

This single-center prospective observational study was performed in mixed ICU in a tertiary teaching hospital. We included patients with sepsis or septic shock within the first 24 h after ICU admission. Conjunctival imaging, using an IDF video microscope, and retinal imaging, using portable digital fundus camera, as well as systemic hemodynamic measurements, were performed at three time points: at baseline, 6 h and 24 h. Baseline conjunctival microcirculatory parameters were compared with healthy controls.

Results

A total of 48 patients were included in the final assessment and analysis. Median APACHE II and SOFA scores were 16[12–21] and 10[7–12], respectively. Forty-four (92%) patients were in septic shock, 48 (100%) required mechanical ventilation. 19 (40%) patients were discharged alive from the intensive care unit. We found significant reductions in all microcirculatory parameters in the conjunctiva when comparing septic and healthy subjects. In addition, we observed a significant lower microvascular flow index (MFI) of small conjunctival vessels during all three time points in non-survivors compared with survivors. However, retinal arteriolar vessels were not different between survivors and non-survivors.

Conclusions

Conjunctival microvascular blood flow was altered in septic patients. In the 24-h observation period conjunctival small vessels had a significantly higher MFI, but no difference in retinal arteriolar diameter in survivors in comparison with non-survivors.

Trial registration NCT04214743, https://www.clinicaltrials.gov. Date of registration: 31 December 2019 – Retrospectively registered, https://clinicaltrials.gov/ct2/show/NCT04214743

Detection of Subclinical Diabetic Retinopathy by Fine Structure Analysis of Retinal Images

Background and Objective

Diabetic retinopathy (DR) is a major complication of diabetes and the leading cause of blindness among US working-age adults. Detection of subclinical DR is important for disease monitoring and prevention of damage to the retina before occurrence of vision loss. The purpose of this retrospective study is to describe an automated method for discrimination of subclinical DR using fine structure analysis of retinal images.

Methods

Discrimination between nondiabetic control (NC; N = 16) and diabetic without clinical retinopathy (NDR; N = 17) subjects was performed using ordinary least squares regression and Fisher's linear discriminant analysis. A human observer also performed the discrimination by visual inspection of the images.

Results

The discrimination rate for subclinical DR was 88% using the automated method and higher than the rate obtained by a human observer which was 45%.

Conclusions

The method provides sensitive and rapid analysis of retinal images and could be useful in detecting subclinical DR.