Diffuse reflectance spectra of the palpebral conjunctiva and its utility as a noninvasive indicator of total hemoglobin

Diffuse reflectance spectroscopy and RGB-imaging: a comparative study of non-invasive haemoglobin assessment

Non-invasive assessment of haemoglobin (Hb) level in blood is a hot spot in the point-of-care biomedical diagnostics. Several optical methods are suggested as a solution, some of them being approved for clinical use. Still, there is no consensus on the accuracy of optical techniques, the quality of Hb assessment on different tissue sites, and on the ability of combined use of several optical techniques to improve the quality of Hb level prediction. In this work we examined the capabilities of two optical techniques-diffuse reflectance spectroscopy and RGB-imaging of the skin and fingernails areas-in detecting low blood Hb level. The test sample consisted of 240 adult volunteers with 70 volunteers exhibiting Hb level lower than 120 g/L. We show that using simple descriptors of the diffuse reflectance spectrum of the forearm skin and fingernails is applicable for predicting low blood Hb concentration (ROC-AUC = 0.84 ± 0.08), while RGB-imaging shows similar performance when applied to the fingernail areas (ROC-AUC = 0.83 ± 0.07), which can be considered perspective for clinical use and screening properties. We also report that while the joint use of predictions from two optical methods slightly improves the accuracy of non-invasive Hb level assessment (ROC-AUC = 0.86 ± 0.07), the effect is not as high as one might expect from combining predictions of truly independent modalities, indicating the limit of the accuracy one can expect with multimodal optical approach. We review this case and propose possible solutions towards more sensitive non-invasive optical determination of hemoglobin.

A deep learning model for novel systemic biomarkers in photographs of the external eye: a retrospective study

BACKGROUND

Photographs of the external eye were recently shown to reveal signs of diabetic retinal disease and elevated glycated haemoglobin. This study aimed to test the hypothesis that external eye photographs contain information about additional systemic medical conditions.

METHODS

We developed a deep learning system (DLS) that takes external eye photographs as input and predicts systemic parameters, such as those related to the liver (albumin, aspartate aminotransferase [AST]); kidney (estimated glomerular filtration rate [eGFR], urine albumin-to-creatinine ratio [ACR]); bone or mineral (calcium); thyroid (thyroid stimulating hormone); and blood (haemoglobin, white blood cells [WBC], platelets). This DLS was trained using 123 130 images from 38 398 patients with diabetes undergoing diabetic eye screening in 11 sites across Los Angeles county, CA, USA. Evaluation focused on nine prespecified systemic parameters and leveraged three validation sets (A, B, C) spanning 25 510 patients with and without diabetes undergoing eye screening in three independent sites in Los Angeles county, CA, and the greater Atlanta area, GA, USA. We compared performance against baseline models incorporating available clinicodemographic variables (eg, age, sex, race and ethnicity, years with diabetes).

FINDINGS

Relative to the baseline, the DLS achieved statistically significant superior performance at detecting AST >36·0 U/L, calcium <8·6 mg/dL, eGFR <60·0 mL/min/1·73 m2, haemoglobin <11·0 g/dL, platelets <150·0 × 103/μL, ACR ≥300 mg/g, and WBC <4·0 × 103/μL on validation set A (a population resembling the development datasets), with the area under the receiver operating characteristic curve (AUC) of the DLS exceeding that of the baseline by 5·3-19·9% (absolute differences in AUC). On validation sets B and C, with substantial patient population differences compared with the development datasets, the DLS outperformed the baseline for ACR ≥300·0 mg/g and haemoglobin <11·0 g/dL by 7·3-13·2%.

INTERPRETATION

We found further evidence that external eye photographs contain biomarkers spanning multiple organ systems. Such biomarkers could enable accessible and non-invasive screening of disease. Further work is needed to understand the translational implications.

FUNDING

Google.

An intelligent non-invasive system for automated diagnosis of anemia exploiting a novel dataset

Anemia is a condition in which the oxygen-carrying capacity of red blood cells is insufficient to meet the body's physiological needs. It affects billions of people worldwide. An early diagnosis of this disease could prevent the advancement of other disorders. Traditional methods used to detect anemia consist of venipuncture, which requires a patient to frequently undergo laboratory tests. Therefore, anemia diagnosis using noninvasive and cost-effective methods is an open challenge. The pallor of the fingertips, palms, nail beds, and eye conjunctiva can be observed to establish whether a patient suffers from anemia. This article addresses the above challenges by presenting a novel intelligent system, based on machine learning, that supports the automated diagnosis of anemia. This system is innovative from different points of view. Specifically, it has been trained on a dataset that contains eye conjunctiva photos of Indian and Italian patients. This dataset, which was created using a very strict experimental set, is now made available to the Scientific Community. Moreover, compared to previous systems in the literature, the proposed system uses a low-cost device, which makes it suitable for widespread use. The performance of the learning algorithms utilizing two different areas of the mucous membrane of the eye is discussed. In particular, the RUSBoost algorithm, when appropriately trained on palpebral conjunctiva images, shows good performance in classifying anemic and nonanemic patients. The results are very robust, even when considering different ethnicities.

Two-stage hemoglobin prediction based on prior causality

Introduction

Perioperative hemoglobin (Hb) levels can influence tissue metabolism. For clinical physicians, precise Hb concentration greatly contributes to intraoperative blood transfusion. The reduction in Hb during an operation weakens blood's oxygen-carrying capacity and poses threats to multiple systems and organs of the whole body. Patients can die from perioperative anemia. Thus, a timely and accurate non-invasive prediction for patients' Hb content is of enormous significance.

Method

In this study, targeted toward the palpebral conjunctiva images in perioperative patients, a non-invasive model for predicting Hb levels is constructed by means of deep neural semantic segmentation and a convolutional network based on a priori causal knowledge, then an automatic framework was proposed to predict the precise concentration value of Hb. Specifically, according to a priori causal knowledge, the palpebral region was positioned first, and patients' Hb concentration was subjected to regression prediction using a neural network. The model proposed in this study was experimented on using actual medical datasets.

Results

The R ² of the model proposed can reach 0.512, the explained variance score can reach 0.535, and the mean absolute error is 1.521.

Discussion

In this study, we proposed to predict the accurate hemoglobin concentration and finally constructed a model using the deep learning method to predict eyelid Hb of perioperative patients based on the a priori casual knowledge.

Progressive evaluation in spectroscopic sensors for non-invasive blood haemoglobin analysis - a review

Frequent monitoring of haemoglobin concentration is highly recommended by physicians to diagnose anaemia and polycythemia Vera. Moreover, Some other conditions also demand assessment of haemoglobin, and these conditions are blood loss, before blood donation, during pregnancy, preoperative, perioperative and postoperative conditions. Cyanmethaemoglobin/haemiglobincyanide method, portable haemoglobinometers and haematology analyzers are few standard methods to diagnose mentioned ailments. However, discomfort, delay and risk of infection are typical limitations of traditional measuring solutions. These limitations create the necessity to develop a non-invasive haemoglobin monitoring technique for a better lifestyle. Various methods and products are already developed and popular due to their non-invasiveness; however, invasive solutions are still considered as the reference standard method. Therefore, this review summarizes the attributes of existing non-invasive solutions. These attributes are finalized as brief details, accuracy, optimal benefits, and research challenges for exploring potential gaps, advancements and possibilities to consider as futuristic alternative methodologies. Non-invasive total haemoglobin assessing techniques are mainly based on optical spectroscopy (reflectance/transmittance) or digital photography or spectroscopic imaging in spot check/continuous monitoring mode. In all these techniques, we have noticed that there is a need to consider different light conditions, motion artefacts, melanocytes, other blood constituents, smoking and precise fixing of the sensor from the sensing spot for exact formulation. Moreover, based on careful and critical analysis of outcomes, none of these techniques or products is used independently or intended to replace invasive laboratory testing. Therefore there is a requirement for a more accurate technique that can eliminate the requirement of blood samples and likely end up as a reference standard method.

NIR-based sensing system for non-Invasive detection of Hemoglobin for point-of-care applications

BACKGROUND

Hemoglobin is essential biomolecule for the transportation of oxygen therefore; its assessment is also obligatory very frequently in innumerable clinical practices. Traditional invasive techniques have concomitant shortcomings e.g. time delay, onset of infections and discomfort, which necessitates a non-invasive hemoglobin estimating solution to get rid of these constraints in health informatics. Currently various techniques are underway in allied domain and scanty products are also feasible in the market but due to low satisfaction rate, invasive solutions are still assumed as gold standard. Recently introduced technologies are effectively evolved as optical spectroscopy and digital photographic concepts on different sensing spots e.g. fingertip, palpebral conjunctiva, bulbar conjunctiva and fingernail. Productive sensors utilize more than eight wavelengths to compute hemoglobin concentration and four wavelengths to display only Hb-index (trending of hemoglobin) either in disposable adhesive or reusable clip type sensor's configuration.

OBJECTIVE

This study aims an optimistic optical spectroscopic technique to measure hemoglobin concentration and conditional usability of non-invasive blood parameters' diagnostics at point-of-care.

METHODS

Two distinguishable light emitting sources (810nm & 1300nm) are utilized at isosbestic points with single photodetector (800-1700nm). With this purpose, reusable finger probe assembly is facilitated in transmittance mode based on newly offered sliding mechanism to block ambient light.

RESULTS

Investigation with proposed design presents correlation coefficients between reference hemoglobin and every individual feature, multivariate linear regression model for highly correlated independent features. Moreover, principal component analytical model with multivariate linear regression offers mean bias of 0.036 & -0.316 g/dL, precision of 0.878 & 0.838 and limits of agreement from -1.685 to 1.758 g/dL & -1.790 to 1.474 g/dL for 18 & 21 principle components respectively.

CONCLUSION

The encouraging readouts emphasize favorable precision therefore proposed sensing system is amenable to assess hemoglobin in settings with limited resources and strengthening future routes for point of care applications.

Prediction of anemia and estimation of hemoglobin concentration using a smartphone camera

Anemia, defined as a low hemoglobin concentration, has a large impact on the health of the world’s population. We describe the use of a ubiquitous device, the smartphone, to predict hemoglobin concentration and screen for anemia. This was a prospective convenience sample study conducted in Emergency Department (ED) patients of an academic teaching hospital. In an algorithm derivation phase, images of both conjunctiva were obtained from 142 patients in Phase 1 using a smartphone. A region of interest targeting the palpebral conjunctiva was selected from each image. Image-based parameters were extracted and used in stepwise regression analyses to develop a prediction model of estimated hemoglobin (HBc). In Phase 2, a validation model was constructed using data from 202 new ED patients. The final model based on all 344 patients was tested for accuracy in anemia and transfusion thresholds. Hemoglobin concentration ranged from 4.7 to 19.6 g/dL (mean 12.5). In Phase 1, there was a significant association between HBc and laboratory-predicted hemoglobin (HBl) slope = 1.07 (CI = 0.98–1.15), p<0.001. Accuracy, sensitivity, and specificity of HBc for predicting anemia was 82.9 [79.3, 86.4], 90.7 [87.0, 94.4], and 73.3 [67.1, 79.5], respectively. In Phase 2, accuracy, sensitivity and specificity decreased to 72.6 [71.4, 73.8], 72.8 [71, 74.6], and 72.5 [70.8, 74.1]. Accuracy for low (<7 g/dL) and high (<9 g/dL) transfusion thresholds was 94.4 [93.7, 95] and 86 [85, 86.9] respectively. Error trended with increasing HBl values (slope 0.27 [0.19, 0.36] and intercept -3.14 [-4.21, -2.07] (p<0.001) such that HBc tended to underestimate hemoglobin in higher ranges and overestimate in lower ranges. Higher quality images had a smaller bias trend than lower quality images. When separated by skin tone results were unaffected. A smartphone can be used in screening for anemia and transfusion thresholds. Improvements in image quality and computational corrections can further enhance estimates of hemoglobin.

Spectral diffuse reflectance and autofluorescence imaging can perform early prediction of blood vessel occlusion in skin flaps

Flap transfer has become a common technique in reconstructive surgery. However, a significant number of compromised skin flaps are not successfully salvaged because the current clinical method for flap assessment relies heavily on the clinician's experience. Vascular occlusion is the major reason for flap failure, thus the accurate and objective early prediction of blood vessel occlusion is vitally important. Our parallel point measurement study has demonstrated the great potential of joint diffuse reflectance and autofluorescence spectroscopy in the early detection and differentiation of venous and arterial occlusion in skin flaps. Unfortunately, the technique of point measurements is not suitable to examine a large skin flap when a high spatial resolution is required. In this study, we attempted to overcome this problem by performing spectral diffuse reflectance and autofluorescence imaging on a rat skin flap model. Both imaging data and reconstructed spectra were used to statistically differentiate control flaps, arterially occluded flaps and venously occluded flaps. Our preliminary results suggest that the technique of joint diffuse reflectance and autofluorescence spectroscopic imaging can achieve high classification accuracy thus could be used to detect and differentiate flaps with venous and arterial occlusion accurately at an early time point in a large skin flap. Typical reconstructed spectra of (a) diffuse reflectance and (b) autofluorescence after normalization.

Biomedical device innovation methodology: applications in biophotonics

The process of medical device innovation involves an iterative method that focuses on designing innovative, device-oriented solutions that address unmet clinical needs. This process has been applied to the field of biophotonics with many notable successes. Device innovation begins with identifying an unmet clinical need and evaluating this need through a variety of lenses, including currently existing solutions for the need, stakeholders who are interested in the need, and the market that will support an innovative solution. Only once the clinical need is understood in detail can the invention process begin. The ideation phase often involves multiple levels of brainstorming and prototyping with the aim of addressing technical and clinical questions early and in a cost-efficient manner. Once potential solutions are found, they are tested against a number of known translational factors, including intellectual property, regulatory, and reimbursement landscapes. Only when the solution matches the clinical need, the next phase of building a "to market" strategy should begin. Most aspects of the innovation process can be conducted relatively quickly and without significant capital expense. This white paper focuses on key points of the medical device innovation method and how the field of biophotonics has been applied within this framework to generate clinical and commercial success.

Development and validation of a noncontact spectroscopic device for hemoglobin estimation at point-of-care

Anemia severely and adversely affects human health and socioeconomic development. Measuring hemoglobin with the minimal involvement of human and financial resources has always been challenging. We describe a translational spectroscopic technique for noncontact hemoglobin measurement at low-resource point-of-care settings in human subjects, independent of their skin color, age, and sex, by measuring the optical spectrum of the blood flowing in the vascular bed of the bulbar conjunctiva. We developed software on the LabVIEW platform for automatic data acquisition and interpretation by nonexperts. The device is calibrated by comparing the differential absorbance of light of wavelength 576 and 600 nm with the clinical hemoglobin level of the subject. Our proposed method is consistent with the results obtained using the current gold standard, the automated hematology analyzer. The proposed noncontact optical device for hemoglobin estimation is highly efficient, inexpensive, feasible, and extremely useful in low-resource point-of-care settings. The device output correlates with the different degrees of anemia with absolute and trending accuracy similar to those of widely used invasive methods. Moreover, the device can instantaneously transmit the generated report to a medical expert through e-mail, text messaging, or mobile apps.

Toward laboratory blood test-comparable photometric assessments for anemia in veterinary hematology

Anemia associated with intestinal parasites and malnutrition is the leading cause of morbidity and mortality in small ruminants worldwide. Qualitative scoring of conjunctival redness has been developed so that farmers can gauge anemia in sheep and goats to identify animals that require treatment. For clinically relevant anemia diagnosis, complete blood count-comparable quantitative methods often rely on complicated and expensive optical instruments, requiring detailed spectral information of hemoglobin. We report experimental and numerical results for simple, yet reliable, noninvasive hemoglobin detection that can be correlated with laboratory-based blood hemoglobin testing for anemia diagnosis. In our pilot animal study using calves, we exploit the third eyelid (i.e., palpebral conjunctiva) as an effective sensing site. To further test spectrometer-free (or spectrometerless) hemoglobin assessments, we implement full spectral reconstruction from RGB data and partial least square regression. The unique combination of RGB-based spectral reconstruction and partial least square regression could potentially offer uncomplicated instrumentation and avoid the use of a spectrometer, which is vital for realizing a compact and inexpensive hematology device for quantitative anemia detection in the farm field.

Combined reflectance spectroscopy and stochastic modeling approach for noninvasive hemoglobin determination via palpebral conjunctiva

A combination of stochastic photon propagation model in a multilayered human eyelid tissue and reflectance spectroscopy was used to study palpebral conjunctiva spectral reflectance for hemoglobin (Hgb) determination. The developed model is the first biologically relevant model of eyelid tissue, which was shown to provide very good approximation to the measured spectra. Tissue optical parameters were defined using previous histological and microscopy studies of a human eyelid. After calibration of the model parameters the responses of reflectance spectra to Hgb level and blood oxygenation variations were calculated. The stimulated reflectance spectra in adults with normal and low Hgb levels agreed well with experimental data for Hgb concentrations from 8.1 to 16.7 g/dL. The extracted Hgb levels were compared with in vitro Hgb measurements. The root mean square error of cross-validation was 1.64 g/dL. The method was shown to provide 86% sensitivity estimates for clinically diagnosed anemia cases. A combination of the model with spectroscopy measurements provides a new tool for noninvasive study of human conjunctiva to aid in diagnosing blood disorders such as anemia.

Early detection in head and neck cancer - current state and future perspectives

Survival and quality of life in head and neck cancer are directly linked to the size of the primary tumor at first detection. In order to achieve substantial gain at these issues, both, primary prevention and secondary prevention, which is early detection of malignant lesions at a small size, have to be improved. So far, there is not only a lack in the necessary infrastructure not only in Germany, but rather worldwide, but additionally the techniques developed so far for early detection have a significance and specificity too low as to warrant safe implementation for screening programs. However, the advancements recently achieved in endoscopy and in quantitative analysis of hypocellular specimens open new perspectives for secondary prevention. Chromoendoscopy and narrow band imaging (NBI) pinpoint suspicious lesions more easily, confocal endomicroscopy and optical coherence tomography obtain optical sections through those lesions, and hyperspectral imaging classifies lesions according to characteristic spectral signatures. These techniques therefore obtain optical biopsies. Once a "bloody" biopsy has been taken, the plethora of parameters that can be quantified objectively has been increased and could be the basis for an objective and quantitative classification of epithelial lesions (multiparametric cytometry, quantitative histology). Finally, cytomics and proteomics approaches, and lab-on-the-chip technology might help to identify patients at high-risk. Sensitivity and specificity of these approaches have to be validated, yet, and some techniques have to be adapted for the specific conditions for early detection of head and neck cancer. On this background it has to be stated that it is still a long way to go until a population based screening for head and neck cancer is available. The recent results of screening for cancer of the prostate and breast highlight the difficulties implemented in such a task.

Noninvasive monitoring of tissue hemoglobin using UV-VIS diffuse reflectance spectroscopy: a pilot study

We conducted a pilot study on 10 patients undergoing general surgery to test the feasibility of diffuse reflectance spectroscopy in the visible wavelength range as a noninvasive monitoring tool for blood loss during surgery. Ratios of raw diffuse reflectance at wavelength pairs were tested as a first-pass for estimating hemoglobin concentration. Ratios can be calculated easily and rapidly with limited post-processing, and so this can be considered a near real-time monitoring device. We found the best hemoglobin correlations were when ratios at isosbestic points of oxy- and deoxyhemoglobin were used, specifically 529/500 nm. Baseline subtraction improved correlations, specifically at 520/509 nm. These results demonstrate proof-of-concept for the ability of this noninvasive device to monitor hemoglobin concentration changes due to surgical blood loss. The 529/500 nm ratio also appears to account for variations in probe pressure, as determined from measurements on two volunteers.

Photonics-based in vivo total hemoglobin monitoring and clinical relevance

Anemia is a serious disorder which, as a result of antiquated invasive blood testing, is undiagnosed in millions of people in the U.S. As a result of the clinical need, many technological solutions have been proposed to measure total blood hemoglobin, and thus diagnose anemia, noninvasively. Because hemoglobin is the strongest chromophore in tissue, spectroscopic methods have been the most prevalently investigated. Difficulties in extracting a quantitative estimation of hemoglobin based on tissue absorption include variability in the absorption spectra of hemoglobin derivatives, interference from other tissue chromophores, and interpatient physiological variations affecting the effective optical path length of light propagating in tissue. In spite of these challenges, studies with a high degree of correlation between in vitro and in vivo measured total hemoglobin have been disclosed using variants of transmission and diffuse reflection spectroscopy in assorted physiological locations. A review of these technologies and the relevant advantages/disadvantages are presented here.

Point-of-care noninvasive hemoglobin determination using fiber optic reflectance spectroscopy

STUDY OBJECTIVE

Rapidly identifying anemia through qualitative observation of the palpebral conjunctiva for pallor is standard medical practice. We report on the ability of using a fiber optic array probe to collect diffusely reflected light from the palpebral conjunctiva and measure hemoglobin concentration noninvasively. Patients (N=102) admitted to the emergency department and receiving a complete blood count (CBC) were enrolled as a convenience set. The tarsal plate was exposed by averting the lower eyelid and illuminated with a white LED while diffusely reflected light was collected using a fiber optic probe and commercial grating spectrometer. Spectra were analyzed using partial least squares regression to extract hemoglobin concentration information and compare to the CBC result. The probe and algorithm demonstrated correlation coefficient of r = 0.82 and standard error of 1.05 g/dL compared to invasive CBC test. Experimental error is due to variability in distance and position of the probe relative to the conjunctiva. This technique has shown the ability to measure total hemoglobin noninvasively and in real-time at the point-of-care using diffuse reflectance spectroscopy of the tarsal plate, leading to potential inclusion of this class of device as a triage centric tool to identify anemia appearing with internal hemorrhage or other acute conditions.

[Cytomics and predictive medicine for oncology]

One hundred and fifty years after Virchow introduced his fundamental concept of cellular pathology, we now have tools that allow us to unravel the mechanisms of single living cells on a previously unprecedented level of detail. By exploring the molecular cellular phenotype, multiparametric cytometry not only detects specific cellular functions in general but also offers insights into the interaction of single subunits of proteins (e.g., growth factor receptors). Several quantitative and objective techniques allow analysis of single-cell preparations as well as tissue sections to obtain data on different cellular parameters. This opens the way to quantitative and objective histology, which in the future may be possible even without blood or the need to make an incision. To use this huge amount of data for treatment decisions in an individual patient, novel bioinformatic concepts are needed in order to predict the individual course of a disease. The concept of cytomics centers on the cell as the integral unit of all life and explores diseases starting from the cell and going to subcellular units (top-down analysis).

Noninvasive Optical, Electrical, and Acoustic Methods of Total Hemoglobin Determination

Background: Anemia is an underdiagnosed, significant public health concern afflicting &gt;2 billion people worldwide. The detrimental effects of tissue oxygen deficiency on the cardiovascular system and concurrent appearance of anemia with numerous high-risk disorders highlight the importance of clinical screening. Currently there is no universally accepted, clinically applicable, noninvasive hemoglobin/hematocrit screening tool. The need for such a device has prompted an investigation into a breadth of techniques.

Methods: A synopsis of the literature and current directions of research in noninvasive total hemoglobin measurement was collected. Contributions highlighted in this review are limited to those studies conducted with a clinical aspect, and most include in vivo patient studies.

Results: The review of potential techniques presented here includes optoacoustic spectroscopy, spectrophotometric imaging, diffuse reflectance spectroscopy, transcutaneous illumination, electrical admittance plethysmography, and photoplethysmography. The technological performance, relative benefits of each approach, potential instrumentation design considerations, and future directions are discussed in each subcategory.

Conclusions: Many techniques reviewed here have shown excellent accuracy, sensitivity, and specificity in measuring hemoglobin/hematocrit, thus in the near future a new clinically viable tool for noninvasive hemoglobin/hematocrit monitoring will likely be widely used for patient care. Limiting factors in clinical adoption will likely involve technology integration into the current standard of care in each field routinely dealing with anemia.