Artificial neural networks trained on simulated multispectral data for real-time imaging of skin microcirculatory blood oxygen saturation.

Significance: Imaging blood oxygen saturation ( SO 2 ) in the skin can be of clinical value when studying ischemic tissue. Emerging multispectral snapshot cameras enable real-time imaging but are limited by slow analysis when using inverse Monte Carlo (MC), the gold standard for analyzing multispectral data. Using artificial neural networks (ANNs) facilitates a significantly faster analysis but requires a large amount of high-quality training data from a wide range of tissue types for a precise estimation of SO 2 . Aim: We aim to develop a framework for training ANNs that estimates SO 2 in real time from multispectral data with a precision comparable to inverse MC. Approach: ANNs are trained using synthetic data from a model that includes MC simulations of light propagation in tissue and hardware characteristics. The model includes physiologically relevant variations in optical properties, unique sensor characteristics, variations in illumination spectrum, and detector noise. This approach enables a rapid way of generating high-quality training data that covers different tissue types and skin pigmentation. Results: The ANN implementation analyzes an image in 0.11 s, which is at least 10,000 times faster than inverse MC. The hardware modeling is significantly improved by an in-house calibration of the sensor spectral response. An in-vivo example shows that inverse MC and ANN give almost identical SO 2 values with a mean absolute deviation of 1.3%-units. Conclusions: ANN can replace inverse MC and enable real-time imaging of microcirculatory SO 2 in the skin if detailed and precise modeling of both tissue and hardware is used when generating training data.

Robust analysis of microcirculatory flowmotion during post-occlusive reactive hyperemia.

BACKGROUND: Flowmotion analysis of the microcirculatory blood flow is a method to extract information about the vessel regulatory function. It has previously shown promise when applied to measurements during a post-occlusive reactive hyperemia. However, the reperfusion peak and the following monotonic decline introduces false low frequencies that should not be interpreted as rhythmic vasomotion effect. AIM: To develop and validate a robust method for flowmotion analysis of post-occlusive reactive hyperemia signals. METHOD: The occlusion-induced reperfusion response contains a typical rapid increase followed by a monotonic decline to baseline. A mathematical model is proposed to detrend this transient part of the signal to enable further flowmotion analysis. The model is validated in 96 measurements on healthy volunteers. RESULTS: Applying the proposed model corrects the flowmotion signal without adding any substantial new false flowmotion components. CONCLUSION: Future studies should use the proposed method or equivalent when analyzing flowmotion during post-occlusive reactive hyperemia to ensure valid results.

Association between cardiovascular risk profile and impaired microvascular function in a Swedish middle-aged cohort (the SCAPIS study).

AIMS: The aim was to investigate the relationship between microvascular function, cardiovascular risk profile, and subclinical atherosclerotic burden. METHODS AND RESULTS: The study enrolled 3809 individuals, 50-65 years old, participating in the population-based observational cross-sectional Swedish CArdioPulmonary bioImage Study. Microvascular function was assessed in forearm skin using an arterial occlusion and release protocol determining peak blood oxygen saturation (OxyP). Cardiovascular risk was calculated using the updated Systematic Coronary Risk Evaluation [SCORE2; 10-year risk of fatal and non-fatal cardiovascular disease (CVD) events]. The OxyP was compared with coronary artery calcification score (CACS) and to plaques in the carotid arteries. Individuals with OxyP values in the lowest quartile (Q1; impaired microvascular function) had a mean SCORE2 of 5.8% compared with 3.8% in those with the highest values of OxyP (Q4), a relative risk increase of 53%. The risk of having a SCORE2 > 10% was five times higher for those in Q1 (odds ratio: 4.96, 95% confidence interval: 2.76-8.93) vs. Q4 when adjusting for body mass index and high-sensitivity C-reactive protein. The OxyP was lower in individuals with CACS > 0 and in those with both carotid plaques and CACS > 0, compared with individuals without subclinical atherosclerotic burdens (87.5 ± 5.6% and 86.9 ± 6.0%, vs. 88.6 ± 5.8%, P < 0.01). CONCLUSION: In a population without CVD or diabetes mellitus, impaired microvascular function is associated with cardiovascular risk profiles such as higher SCORE2 risk and CACS. We suggest that OxyP may serve as a microcirculatory functional marker of subclinical atherosclerosis and CVD risk that is not detected by structural assessments.

Impaired microvascular function was associated with higher cardiovascular risk profile SCORE2 and subclinical atherosclerotic burden defined by carotid plaque and coronary artery calcification score (CACS).Individuals with impaired microvascular function (peak oxygen saturation in the forearm skin, OxyP, after a prolonged arterial occlusion provocation) had a moderate risk level of SCORE2 compared to low risk level in those with the highest values of OxyP.The OxyP was lower in individuals with CACS > 0 and in those with both carotid plaques and CACS > 0, compared with individuals with carotid plaque only and in individuals without subclinical atherosclerotic burdens.

Microvascular dysfunction in women with a history of hypertensive disorders of pregnancy: A population-based retrospective cohort study.

OBJECTIVE: To evaluate microvascular function in women with previous hypertensive disorders of pregnancy (HDP). DESIGN: Retrospective population-based cohort study. SETTING: Linköping, Sweden. POPULATION: Women aged 50-65 years, participating in the Swedish CArdioPulmonary bioImage Study (SCAPIS) at one site (Linköping) 2016-18, who underwent microcirculatory assessment (N = 1222). METHODS: Forearm skin comprehensive microcirculatory assessment was performed with a PeriFlux PF6000 EPOS (Enhanced Perfusion and Oxygen Saturation) system measuring oxygen saturation and total speed resolved perfusion. Obstetric records were reviewed to identify women with previous HDP. Data on cardiovascular risk factors, comorbidities, medication, lifestyle, anthropometric data, and biochemical analyses were obtained from SCAPIS. The microcirculatory data were compared between women with and without previous HDP. MAIN OUTCOME MEASURES: Skin microcirculatory oxygen saturation and total speed resolved perfusion at baseline and post-ischaemic peak. RESULTS: Women with previous pre-eclampsia displayed impaired post-ischaemic peak oxygen saturation compared with women with normotensive pregnancies (88%, interquartile range [IQR] 84-89% vs 91%, IQR 87-94%, p = 0.001) 6-30 years after pregnancy. The difference remained after multivariable adjustment (ß -2.69, 95% CI -4.93 to -0.45). CONCLUSIONS: The findings reveal microvascular dysfunction at long-term follow up in women with previous pre-eclampsia and strengthen the possible role of endothelial dysfunction as a link to the increased risk of cardiovascular disease in women with HDP.

Absorption and reduced scattering coefficients in epidermis and dermis from a Swedish cohort study.

Significance: Knowledge of optical properties is important to accurately model light propagation in tissue, but in vivo reference data are sparse. Aim: The aim of our study was to present in vivo skin optical properties from a large Swedish cohort including 3809 subjects using a three-layered skin model and spatially resolved diffuse reflectance spectroscopy (Periflux PF6000 EPOS). Approach: Diffuse reflectance spectra (475 to 850 nm) at 0.4 and 1.2 mm source-detector separations were analyzed using an inverse Monte Carlo method. The model had one epidermis layer with variable thicknesses and melanin-related absorptions and two dermis layers with varying hemoglobin concentrations and equal oxygen saturations. The reduced scattering coefficient was equal across all layers. Results: Median absorption coefficients (mm-1) in the upper dermis ranged from 0.094 at 475 nm to 0.0048 at 850 nm and similarly in the lower dermis from 0.059 to 0.0035. The reduced scattering coefficient (mm-1) ranged from 3.22 to 1.20, and the sampling depth (mm) ranged from 0.23 to 0.38 (0.4 mm separation) and from 0.49 to 0.68 (1.2 mm separation). There were differences in optical properties across sex, age groups, and BMI categories. Conclusions: Reference material for skin optical properties is presented.

Workload and sex effects in comprehensive assessment of cutaneous microcirculation.

INTRODUCTION: Workload and sex-related differences have been proposed as factors of importance when evaluating the microcirculation. Simultaneous assessments with diffuse reflectance spectroscopy (DRS) and laser Doppler flowmetry (LDF) enable a comprehensive evaluation of the microcirculation. The aim of the study was to compare the response between sexes in the microcirculatory parameters red blood cell (RBC) tissue fraction, RBC oxygen saturation, average vessel diameter, and speed-resolved perfusion during baseline, cycling, and recovery, respectively. METHODS: In 24 healthy participants (aged 20 to 30 years, 12 females), cutaneous microcirculation was assessed by LDF and DRS at baseline, during a workload generated by cycling at 75 to 80 % of maximal age-predicted heart rate, and recovery, respectively. RESULTS: Females had significantly lower RBC tissue fraction and total perfusion in forearm skin microcirculation at all phases (baseline, workload, and recovery). All microvascular parameters increased significantly during cycling, most evident in RBC oxygen saturation (34 % increase on average) and perfusion (9-fold increase in total perfusion). For perfusion, the highest speeds (>10 mm/s) increased by a factor of 31, whereas the lowest speeds (<1 mm/s) increased by a factor of 2. CONCLUSION: Compared to a resting state, all studied microcirculation measures increased during cycling. For perfusion, this was mainly due to increased speed, and only to a minor extent due to increased RBC tissue fraction. Skin microcirculatory differences between sexes were seen in RBC concentration and total perfusion.

Speed-resolved perfusion imaging using multi-exposure laser speckle contrast imaging and machine learning.

Significance: Laser speckle contrast imaging (LSCI) gives a relative measure of microcirculatory perfusion. However, due to the limited information in single-exposure LSCI, models are inaccurate for skin tissue due to complex effects from e.g. static and dynamic scatterers, multiple Doppler shifts, and the speed-distribution of blood. It has been demonstrated how to account for these effects in laser Doppler flowmetry (LDF) using inverse Monte Carlo (MC) algorithms. This allows for a speed-resolved perfusion measure in absolute units %RBC × mm/s, improving the physiological interpretation of the data. Until now, this has been limited to a single-point LDF technique but recent advances in multi-exposure LSCI (MELSCI) enable the analysis in an imaging modality. Aim: To present a method for speed-resolved perfusion imaging in absolute units %RBC × mm/s, computed from multi-exposure speckle contrast images. Approach: An artificial neural network (ANN) was trained on a large simulated dataset of multi-exposure contrast values and corresponding speed-resolved perfusion. The dataset was generated using MC simulations of photon transport in randomized skin models covering a wide range of physiologically relevant geometrical and optical tissue properties. The ANN was evaluated on in vivo data sets captured during an occlusion provocation. Results: Speed-resolved perfusion was estimated in the three speed intervals 0 to 1 mm / s , 1 to 10 mm / s , and > 10 mm / s , with relative errors 9.8%, 12%, and 19%, respectively. The perfusion had a linear response to changes in both blood tissue fraction and blood flow speed and was less affected by tissue properties compared with single-exposure LSCI. The image quality was subjectively higher compared with LSCI, revealing previously unseen macro- and microvascular structures. Conclusions: The ANN, trained on modeled data, calculates speed-resolved perfusion in absolute units from multi-exposure speckle contrast. This method facilitates the physiological interpretation of measurements using MELSCI and may increase the clinical impact of the technique.

Affected Microcirculation and Vascular Hemodynamics in Takayasu Arteritis.

Introduction: Takayasu arteritis (TAK) is a rare inflammatory disease affecting aorta and its major branches. Ultrasound (US) can detect inflammatory features in the arterial wall, but less is known regarding skin microcirculation and vascular hemodynamics. The aim was to study if assessment of these variables could add valuable information regarding vascular affection in TAK. Methods: 17 patients diagnosed with TAK and 17 age- and sex-matched healthy controls were included. Microcirculatory peak oxygen saturation (OxyP) in the skin after induced ischemia was evaluated with laser Doppler flowmetry/diffuse reflectance spectroscopy. Cerebrovascular reserve capacity (CVR) in the brain was assessed with transcranial Doppler (TCD). Pulse waves were recorded in the radial artery by the aid of applanation tonometry, for calculation of central augmentation index (AIx75). Intima-media thickness (IMT) and stenosis/occlusions were evaluated using US in carotid and central arteries. Results: Reduced OxyP (79 ± 8% vs. 87 ± 4%, p < 0.001) was seen in patients with TAK regardless of significant arterial stenosis/occlusion or not. Increased AIx75 (22.3 ± 13.6 vs. 9.2 ± 16.3, p = 0.01) was seen in TAK patients without significant stenosis/occlusions. No differences were found in CVR, regardless of proximal stenosis. However, signs of a more high-resistance flow profile were seen in arteria cerebri media. Conclusion: Regardless of arterial stenosis or not, impaired microcirculation of the skin and preserved CVR in the brain were found in subjects with TAK. Signs of increased arterial stiffness in the brain and central arteries were observed. The value of these findings for prediction of future cardiovascular events needs to be clarified in further studies.

In vivo dose-response analysis to acetylcholine: pharmacodynamic assessment by polarized reflectance spectroscopy.

Transdermal iontophoresis offers an in vivo alternative to the strain-gauge model for measurement of vascular function but is limited due to lack of technical solutions for outcome assessment. The aims of this study were to, after measurement by polarized reflectance spectroscopy (PRS), use pharmacodynamic dose-response analysis on responses to different concentrations of acetylcholine (ACh); and to examine the effect of three consecutively administered iontophoretic current pulses. The vascular responses in 15 healthy volunteers to iontophorised ACh (5 concentrations, range 0.0001% to 1%, three consecutive pulses of 0.02 mA for 10 min each) were recorded using PRS. Data were fitted to a four-parameter logistic dose response model and compared. Vascular responses were quantifiable by PRS. Similar pharmacodynamic dose response curves could be generated irrespectively of the ACh concentration. Linearly increasing maximum vasodilatory responses were registered with increasing concentration of ACh. A limited linear dose effect of the concentration of ACh was seen between pulses. Polarized reflectance spectroscopy is well suited for measuring vascular responses to iontophoretically administrated ACh. The results of this study support further development of iontophoresis as a method to study vascular function and pharmacological responses in vivo.

Multispectral snapshot imaging of skin microcirculatory hemoglobin oxygen saturation using artificial neural networks trained on in vivo data.

SIGNIFICANCE: Developing algorithms for estimating blood oxygenation from snapshot multispectral imaging (MSI) data is challenging due to the complexity of sensor characteristics and photon transport modeling in tissue. We circumvent this using a method where artificial neural networks (ANNs) are trained on in vivo MSI data with target values from a point-measuring reference method. AIM: To develop and evaluate a methodology where a snapshot filter mosaic camera is utilized for imaging skin hemoglobin oxygen saturation (SO2), using ANNs. APPROACH: MSI data were acquired during occlusion provocations. ANNs were trained to estimate SO2 with MSI data as input, targeting data from a validated probe-based reference system. Performance of ANNs with different properties and training data sets was compared. RESULTS: The method enables spatially resolved estimation of skin tissue SO2. Results are comparable to those acquired using a Monte-Carlo-based approach when relevant training data are used. CONCLUSIONS: Training an ANN on in vivo MSI data covering a wide range of target values acquired during an occlusion protocol enable real-time estimation of SO2 maps. Data from the probe-based reference system can be used as target despite differences in sampling depth and measurement position.

Comprehensive imaging of microcirculatory changes in the foot during endovascular intervention - A technical feasibility study.

Chronic limb-threatening ischemia (CLTI) has a major impact on patients' lives and is associated with a heavy health care burden with high morbidity and mortality. Treatment by endovascular intervention is mostly based on macrocirculatory information from angiography and does not consider the microcirculation. Despite successful endovascular intervention according to angiographic criteria, a proportion of patients fail to heal ischemic lesions. This might be due to impaired microvascular perfusion and variations in the supply to different angiosomes. Non-invasive optical techniques for microcirculatory perfusion and oxygen saturation imaging have the potential to provide the interventionist with additional information in real-time, supporting clinical decisions during the intervention. This study presents a novel multimodal imaging system, based on multi-exposure laser speckle contrast imaging and multi-spectral imaging, for continuous use during endovascular intervention. The results during intervention display spatiotemporal changes in the microcirculation compatible with expected physiological reactions during balloon dilation, with initially induced ischemia followed by a restored perfusion, and local administration of a vasodilator inducing hyperemia. We also present perioperative and postoperative follow-up measurements with a pulsatile microcirculation perfusion. Finally, cases of spatial heterogeneity in the oxygen saturation and perfusion are discussed. In conclusion, this technical feasibility study shows the potential of the methodology to characterize changes in microcirculation before, during, and after endovascular intervention.

Post-ischemic skin peak oxygen saturation is associated with cardiovascular risk factors: a Swedish cohort study.

The objective of this study was to explore the associations between skin microcirculatory function and established cardiovascular risk factors in a large Swedish cohort. As part of the Swedish CArdioPulmonary bioImage Study (SCAPIS), microcirculatory data were acquired at Linköping University hospital, Linköping, Sweden during 2016-2017. The subjects, aged 50-64 years, were randomly selected from the national population register. Microcirculatory reactivity was assessed using a 5-min arterial occlusion-release protocol. Comprehensive skin microcirculatory data were continuously acquired by using a fiberoptic probe placed on the lower right arm. After exclusion of missing data (208), 1557 subjects were remaining. Among the parameters, skin microcirculatory peak oxygen saturation after occlusion release, had the strongest relationship to the cardiovascular risk factors. The linear associations between peak oxygen saturation and cardiovascular risk factors were analyzed adjusted for age and sex. We found a negative association with peak oxygen saturation (standardized regression coefficient) for blood pressure (systolic -0.05 (95% CI: -0.10;-0.003) and diastolic -0.05 (-0.10; -0.003)), BMI -0.18 (-0.23; -0.13), waist circumference (males -0.20 (-0.32; -0.16), females -0.18 (-0.25; -0.11)), prevalent diabetes -0.31 (-0.49; -0.12), hypertension -0.30 (-0.42; -0.18), dyslipidemia -0.24 (-0.40; -0.09), fasting glucose level -0.06 (-0.12; -0.01), HbA1c -0.07 (-0.12; -0.02), triglyceride level -0.09 (-0.14; -0.04), hsCRP -0.12 (-0.17; -0.07), and current smoker versus never smoked -0.50 (-0.67; -0.34). A positive association with peak oxygen saturation was found for cholesterol level 0.05 (0.005; 0.11) and HDL 0.11 (0.06; 0.17). This is the first study showing that post-ischemic skin microvascular peak oxygen saturation is associated with virtually all established cardiovascular risk factors in a population-based middle-aged cohort.

Vasomotion analysis of speed resolved perfusion, oxygen saturation, red blood cell tissue fraction, and vessel diameter: Novel microvascular perspectives.

BACKGROUND: Vasomotion is the spontaneous oscillation in vascular tone in the microcirculation and is believed to be a physiological mechanism facilitating the transport of blood gases and nutrients to and from tissues. So far, Laser Doppler flowmetry has constituted the gold standard for in vivo vasomotion analysis. MATERIALS AND METHODS: We applied vasomotion analysis to speed-resolved perfusion, oxygen saturation, red blood cell tissue (RBC) tissue fraction, and average vessel diameter from five healthy individuals at rest measured by the newly developed Periflux 6000 EPOS system over 10 minutes. Magnitude scalogram and the time-averaged wavelet spectra were divided into frequency intervals reflecting endothelial, neurogenic, myogenic, respiratory, and cardiac function. RESULTS: Recurrent high-intensity periods of the myogenic, neurogenic, and endothelial frequency intervals were found. The neurogenic activity was considerably more pronounced for the oxygen saturation, RBC tissue fraction, and vessel diameter signals, than for the perfusion signals. In a correlation analysis we found that changes in perfusion in the myogenic, neurogenic, and endothelial frequency intervals precede changes in the other signals. Furthermore, changes in average vessel diameter were in general negatively correlated to the other signals in the same frequency intervals, indicating the importance of capillary recruitment. CONCLUSION: We conclude that vasomotion can be observed in signals reflecting speed resolved perfusion, oxygen saturation, RBC tissue fraction, and vessel diameter. The new parameters enable new aspects of the microcirculation to be observed.

Spectral characterization of liquid hemoglobin phantoms with varying oxygenation states.

SIGNIFICANCE: For optical methods to accurately assess hemoglobin oxygen saturation in vivo, an independently verifiable tissue-like standard is required for validation. For this purpose, we propose three hemoglobin preparations and evaluate methods to characterize them. AIM: To spectrally characterize three different hemoglobin preparations using multiple spectroscopic methods and to compare their absorption spectra to commonly used reference spectra. APPROACH: Absorption spectra of three hemoglobin preparations in solution were characterized using spectroscopic collimated transmission: whole blood, lysed blood, and ferrous-stabilized hemoglobin. Tissue-mimicking phantoms composed of Intralipid, and the hemoglobin solutions were characterized using spatial frequency-domain spectroscopy (SFDS) and enhanced perfusion and oxygen saturation (EPOS) techniques while using yeast to deplete oxygen. RESULTS: All hemoglobin preparations exhibited similar absorption spectra when accounting for methemoglobin and scattering in their oxyhemoglobin and deoxyhemoglobin forms, respectively. However, systematic differences were observed in the fitting depending on the reference spectra used. For the tissue-mimicking phantoms, SFDS measurements at the surface of the phantom were affected by oxygen diffusion at the interface with air, associated with higher values than for the EPOS system. CONCLUSIONS: We show the validity of different blood phantoms and what considerations need to be addressed in each case to utilize them equivalently.

Impaired Microcirculation and Vascular Hemodynamics in Relation to Macrocirculation in Patients With Systemic Lupus Erythematosus.

Introduction: Systemic lupus erythematosus (SLE) is associated with premature cardiovascular disease (CVD) and mortality, unexplained by traditional risk factors. Impairment of microcirculation and vascular hemodynamics may represent early signs of vascular affection. We hypothesized that studies of microcirculation and pulse waves may provide additional information, compared to ultrasound (US) alone, for the detection of early vascular disease in SLE. Methods: Sixty well-characterized SLE-patients (52 women, eight men; mean age 43.21 ± 1.3 years) characterized by lupus nephritis (LN; n = 20), antiphospholipid syndrome (APS; n = 20) or skin and joint involvement (n = 20) and 60 healthy controls were included. Microcirculatory peak oxygen saturation (OxyP) was evaluated using a novel combined laser Doppler flowmetry/diffuse reflectance spectroscopy method. Pulse waves were recorded in the radial artery by the aid of applanation tonometry in order to calculate central augmentation index (AIx75). Intima-media thickness (IMT) and plaque occurrence were evaluated using high frequency US, in carotid and central arteries. Results: Lower OxyP (84 ± 8 vs. 87 ± 5 %, p = 0.01) and higher AIx75 (17.3 ± 13.9 vs. 10.0 ± 14.2 %, p = 0.005) were seen in the SLE cohort. OxyP was inversely correlated with IMT in internal carotid artery (ICA), (R = -0.32, p = 0.01). AIx75 correlated with IMT in common carotid artery (CCA), (R = 0.36, p = 0.005), common femoral artery (CFA), (R = 0.43, p = 0.001), and ICA (R = 0.27, p = 0.04). AIx75 correlated negatively with OxyP (R = -0.29, p = 0.02). SLE-patients with plaque had lower OxyP values (80 ± 8 vs. 85 ± 7 %, p < 0.001) and higher AIx75 (23.0 ± 11.6 vs. 15.5 ± 14.2 %, p < 0.001) compared to those without plaque. Conclusion: Impaired microcirculation and vessel hemodynamics were observed in SLE. These methods correlated with IMT and plaque occurrence. The importance of early macro- and micro-circulatory vascular affection for increased risk of CVD in SLE will be followed-up in future studies.

Estimation of skin microcirculatory hemoglobin oxygen saturation and red blood cell tissue fraction using a multispectral snapshot imaging system: a validation study.

SIGNIFICANCE: Hemoglobin oxygen saturation and red blood cell (RBC) tissue fraction are important parameters when assessing microvascular status. Functional information can be attained using temporally resolved measurements performed during stimulus-response protocols. Pointwise assessments can currently be conducted with probe-based systems. However, snapshot multispectral imaging (MSI) can be used for spatial-temporal measurements. AIM: To validate if hemoglobin oxygen saturation and RBC tissue fraction can be quantified using a snapshot MSI system and an inverse Monte Carlo algorithm. APPROACH: Skin tissue measurements from the MSI system were compared to those from a validated probe-based system during arterial and venous occlusion provocation on 24 subjects in the wavelength interval 450 to 650 nm, to evaluate a wide range of hemoglobin oxygen saturation and RBC tissue fraction levels. RESULTS: Arterial occlusion results show a mean linear regression R2 = 0.958 for hemoglobin oxygen saturation. Comparing relative RBC tissue fraction during venous occlusion results in R2 = 0.925. The MSI system shows larger dynamic changes than the reference system, which might be explained by a deeper sampling including more capacitance vessels. CONCLUSIONS: The snapshot MSI system estimates hemoglobin oxygen saturation and RBC tissue fraction in skin microcirculation showing a high correlation (R2 > 0.9 in most subjects) with those measured by the reference method.

Machine learning for direct oxygen saturation and hemoglobin concentration assessment using diffuse reflectance spectroscopy.

SIGNIFICANCE: Diffuse reflectance spectroscopy (DRS) is frequently used to assess oxygen saturation and hemoglobin concentration in living tissue. Methods solving the inverse problem may include time-consuming nonlinear optimization or artificial neural networks (ANN) determining the absorption coefficient one wavelength at a time. AIM: To present an ANN-based method that directly outputs the oxygen saturation and the hemoglobin concentration using the shape of the measured spectra as input. APPROACH: A probe-based DRS setup with dual source-detector separations in the visible wavelength range was used. ANNs were trained on spectra generated from a three-layer tissue model with oxygen saturation and hemoglobin concentration as target. RESULTS: Modeled evaluation data with realistic measurement noise showed an absolute root-mean-square (RMS) deviation of 5.1% units for oxygen saturation estimation. The relative RMS deviation for hemoglobin concentration was 13%. This accuracy is at least twice as good as our previous nonlinear optimization method. On blood-intralipid phantoms, the RMS deviation from the oxygen saturation derived from partial oxygen pressure measurements was 5.3% and 1.6% in two separate measurement series. Results during brachial occlusion showed expected patterns. CONCLUSIONS: The presented method, directly assessing oxygen saturation and hemoglobin concentration, is fast, accurate, and robust to noise.

Real-time video-rate perfusion imaging using multi-exposure laser speckle contrast imaging and machine learning.

SIGNIFICANCE: Multi-exposure laser speckle contrast imaging (MELSCI) estimates microcirculatory blood perfusion more accurately than single-exposure LSCI. However, the technique has been hampered by technical limitations due to massive data throughput requirements and nonlinear inverse search algorithms, limiting it to an offline technique where data must be postprocessed. AIM: To present an MELSCI system capable of continuous acquisition and processing of MELSCI data, enabling real-time video-rate perfusion imaging with high accuracy. APPROACH: The MELSCI algorithm was implemented in programmable hardware (field programmable gate array) closely interfaced to a high-speed CMOS sensor for real-time calculation. Perfusion images were estimated in real-time from the MELSCI data using an artificial neural network trained on simulated data. The MELSCI perfusion was compared to two existing single-exposure metrics both quantitatively in a controlled phantom experiment and qualitatively in vivo. RESULTS: The MELSCI perfusion shows higher signal dynamics compared to both single-exposure metrics, both spatially and temporally where heartbeat-related variations are resolved in much greater detail. The MELSCI perfusion is less susceptible to measurement noise and is more linear with respect to laser Doppler perfusion in the phantom experiment (R2 = 0.992). CONCLUSIONS: The presented MELSCI system allows for real-time acquisition and calculation of high-quality perfusion at 15.6 frames per second.

Handheld multispectral imager for quantitative skin assessment in low-resource settings.

SIGNIFICANCE: Spatial frequency domain imaging (SFDI) is a quantitative imaging method to measure absorption and scattering of tissue, from which several chromophore concentrations (e.g., oxy-/deoxy-/meth-hemoglobin, melanin, and carotenoids) can be calculated. Employing a method to extract additional spectral bands from RGB components (that we named cross-channels), we designed a handheld SFDI device to account for these pigments, using low-cost, consumer-grade components for its implementation and characterization. AIM: With only three broad spectral bands (red, green, blue, or RGB), consumer-grade devices are often too limited. We present a methodology to increase the number of spectral bands in SFDI devices that use RGB components without hardware modification. APPROACH: We developed a compact low-cost RGB spectral imager using a color CMOS camera and LED-based mini projector. The components' spectral properties were characterized and additional cross-channel bands were calculated. An alternative characterization procedure was also developed that makes use of low-cost equipment, and its results were compared. The device performance was evaluated by measurements on tissue-simulating optical phantoms and in-vivo tissue. The measurements were compared with another quantitative spectroscopy method: spatial frequency domain spectroscopy (SFDS). RESULTS: Out of six possible cross-channel bands, two were evaluated to be suitable for our application and were fully characterized (520 ± 20 nm; 556 ± 18 nm). The other four cross-channels presented a too low signal-to-noise ratio for this implementation. In estimating the optical properties of optical phantoms, the SFDI data have a strong linear correlation with the SFDS data (R2 = 0.987, RMSE = 0.006 for µa, R2 = 0.994, RMSE = 0.078 for µs'). CONCLUSIONS: We extracted two additional spectral bands from a commercial RGB system at no cost. There was good agreement between our device and the research-grade SFDS system. The alternative characterization procedure we have presented allowed us to measure the spectral features of the system with an accuracy comparable to standard laboratory equipment.