Potential of thermal imaging as a tool for prediction of cardiovascular disease

Thermal facial image analyses reveal quantitative hallmarks of aging and metabolic diseases

Although human core body temperature is known to decrease with age, the age dependency of facial temperature and its potential to indicate aging rate or aging-related diseases remains uncertain. Here, we collected thermal facial images of 2,811 Han Chinese individuals 20-90 years old, developed the ThermoFace method to automatically process and analyze images, and then generated thermal age and disease prediction models. The ThermoFace deep learning model for thermal facial age has a mean absolute deviation of about 5 years in cross-validation and 5.18 years in an independent cohort. The difference between predicted and chronological age is highly associated with metabolic parameters, sleep time, and gene expression pathways like DNA repair, lipolysis, and ATPase in the blood transcriptome, and it is modifiable by exercise. Consistently, ThermoFace disease predictors forecast metabolic diseases like fatty liver with high accuracy (AUC > 0.80), with predicted disease probability correlated with metabolic parameters.

Prediction of coronary artery disease based on facial temperature information captured by non-contact infrared thermography

BACKGROUND

Current approaches for initial coronary artery disease (CAD) assessment rely on pretest probability (PTP) based on risk factors and presentations, with limited performance. Infrared thermography (IRT), a non-contact technology that detects surface temperature, has shown potential in assessing atherosclerosis-related conditions, particularly when measured from body regions such as faces. We aim to assess the feasibility of using facial IRT temperature information with machine learning for the prediction of CAD.

METHODS

Individuals referred for invasive coronary angiography or coronary CT angiography (CCTA) were enrolled. Facial IRT images captured before confirmatory CAD examinations were used to develop and validate a deep-learning IRT image model for detecting CAD. We compared the performance of the IRT image model with the guideline-recommended PTP model on the area under the curve (AUC). In addition, interpretable IRT tabular features were extracted from IRT images to further validate the predictive value of IRT information.

RESULTS

A total of 460 eligible participants (mean (SD) age, 58.4 (10.4) years; 126 (27.4%) female) were included. The IRT image model demonstrated outstanding performance (AUC 0.804, 95% CI 0.785 to 0.823) compared with the PTP models (AUC 0.713, 95% CI 0.691 to 0.734). A consistent level of superior performance (AUC 0.796, 95% CI 0.782 to 0.811), achieved with comprehensive interpretable IRT features, further validated the predictive value of IRT information. Notably, even with only traditional temperature features, a satisfactory performance (AUC 0.786, 95% CI 0.769 to 0.803) was still upheld.

CONCLUSION

In this prospective study, we demonstrated the feasibility of using non-contact facial IRT information for CAD prediction.

Thermal Imaging of the Tongue Surface as a Predictive Method in the Diagnosis of Type 2 Diabetes Mellitus

Over the past 20 years, the high prevalence of diabetes has become a global public health problem.

BACKGROUND

The objective of this study was to develop a non-invasive screening method for diabetes which will enable the detection of the disease at an early stage.

METHODS

This study included 63 adult patients of both sexes: 30 patients with type 2 diabetes (t2DM) and 33 healthy volunteers. The temperature distribution on the tongue's dorsum and apex surface was studied in patients after a mouth-cooling procedure had been introduced. The study used an FLIR T540 thermal imaging camera. An analysis of the correlation between the ∆T values of the tongue dorsum and apex and the glycated hemoglobin (HbA1c) level was performed.

RESULTS

The median of the average dorsum temperature measured 10 min after mouth rinsing was almost 0.8 [°C] lower than for healthy individuals. Also, studies showed a positive average correlation with a Pearson coefficient of r = 0.46 between the HbA1c level and the ∆T of the tongue dorsum.

CONCLUSIONS

Tongue temperature measured using the IRT showed a correlation with standard biochemical parameters; it may also differentiate patients and constitute a specific screening method for patients with t2DM.

Non-contact measurement of neck pulses achieved by imaging micro-motions in the neck skin

We report a method and system of micro-motion imaging (µMI) to realize non-contact measurement of neck pulses. The system employs a 16-bit camera to acquire videos of the neck skin, containing reflectance variation caused by the neck pulses. Regional amplitudes and phases of pulse-induced reflection variation are then obtained by applying a lock-in amplification algorithm to the acquired videos. Composite masks are then generated using the raw frame, amplitude and phase maps, which are then used to guide the extraction of carotid pulse (CP) and jugular vein pulse (JVP) waveforms. Experimental results sufficiently demonstrate the feasibility of our method to extract CP and JVP waves. Compared with conventional methods, the proposed strategy works in a non-contact, non-invasive and self-guidance manner without a need for manual identification to operate, which is important for patient compliance and measurement objectivity. Considering the close relationship between neck pulses and cardiovascular diseases, for example, CA stenosis, the proposed µMI system and method may be useful in the development of early screening tools for potential cardiovascular diseases.

Deep transcranial magnetic stimulation in combination with skin thermography in obesity: a window on sympathetic nervous system

AIMS

Obesity is known to be associated with an altered thermoregulation as well as a dysregulation of sympathetic nervous system (SNS). Considering the ability of deep transcranial magnetic stimulation (dTMS) to modulate the SNS, we hypothesized a potential role of dTMS in affecting thermoregulation in obesity. Aims of the study were to monitor the effect of a single session of dTMS on body temperature in subjects with obesity, and to correlate the dTMS-induced changes in body temperature with activation of the SNS (epinephrine and norepinephrine release).

METHODS

Twenty-nine subjects with obesity [5 M, 24 F; age 50 (IQR: 58, 38) yrs; BMI 36.1 (IQR: 33.9, 38.7) kg/m²] were randomized into 2 groups receiving a single session of high frequency stimulation (HF) or sham stimulation. Under neutral thermal conditions, infrared thermography was utilized to assess bilateral fingernail-beds and abdominal temperature.

RESULTS

During a single session HF, the average temperature of both fingernail-beds decreased. Right-hand temperature difference was statistically greater in HF vs Sham: median = - 1.45 (IQR: - 2.0, - 1.0)  °C for HF, p = 0.009. While temperature variation in the fingernail-bed of left hand was not statistically significant in HF compared to Sham: median = - 1.26 (IQR: - 1.6, -0.5) °C, p = 0.064. Concurrently, when estimating the effect of norepinephrine variation on temperature change of fingernail-bed of left hand, a borderline significant positive association was estimated (beta = 1.09, p = 0.067) in HF.

CONCLUSIONS

Deep TMS revealed to be effective in modulating temperature in subjects with obesity, partially reversing obesity-induced alterations in heat production and dissipation with a potential SNS-mediated mechanism.

A Preliminary Study on Infrared Thermograph of Metabolic Syndrome

OBJECTIVE

To explore the temperature distribution characteristics of the face, palms, feet and the trunk area of metabolic syndrome (MS) through infrared thermography (IRT) and provide evidence for the application of IRT in the assistant evaluation of MS population.

METHODS

We collected thermographs of 184 participants (91 males, 93 females) and further divided participants of each gender into 4 groups according to the number of abnormal metabolic indexes. Mean temperatures of 6 Region of Interests (ROIs) (face, anterior trunk, bilateral palms and dorsum of feet) were calculated. Comparisons of the mean temperatures between genders, among groups and ROIs were carried out.

RESULTS

Male participants had higher mean temperature in their face, palms (P<0.01) and dorsum of feet (P<0.05), and lower mean temperature in the anterior trunk (P<0.01). Female participants with MS had higher mean temperature in their palms and dorsum of feet (P<0.01) and lower mean temperature in the anterior trunk (P<0.01) than normal participants. Similar tendencies were shown in the mean temperature of the left palms and trunk of MS males. With the increase of the number of abnormal metabolic indexes, it seems that the mean temperature gradually increased in palms and dorsum of feet, and decreased in the anterior trunk.

CONCLUSION

The thermograph of MS exhibits certain characteristics. This may help reveal the correlations between Infrared thermography and metabolic disorders.

Driver drowsiness detection using facial thermal imaging in a driving simulator

Driver drowsiness causes fatal driving accidents. Thermal imaging is a suitable drowsiness detection method as it is non-invasive and robust against changes in the ambient light. In this paper, driver drowsiness is detected by measuring the forehead temperature at the region covering the supratrochlear artery and also the cheek temperature. About 30 subjects drove on a highway in a driving simulator in two sessions. A thermal camera was used to monitor the facial temperature pattern. The subjects' drowsiness levels were estimated by three human observers. The forehead and the cheek regions were located and tracked in each frame. The forehead and the cheek skin temperatures were obtained at three levels of drowsiness. The Support Vector Machine, the K-Nearest Neighbor, and the regression tree classifiers were used. From wakefulness to extreme drowsiness, the forehead skin temperature and the absolute cheek-forehead skin temperature gradient decreased by 0.46°C and 0.81°C, respectively. But the cheek skin temperature increased by 0.35°C in two sessions. The gradient difference is on average 50% higher than the forehead or the cheek temperature change alone. The results indicate that drowsiness can be detected with an accuracy of 82%, sensitivity of 85%, specificity of 90%, and precision of 84%. Driver drowsiness can be detected by monitoring changes in the forehead and the cheek temperature signal. Also, the temperature gradient can be used as a more robust and sensitive indicator of drowsiness.

Relation between oro-facial thermographic findings and myofunctional characteristics in patients with obstructive sleep apnoea

AIM

To evaluate the thermographic characteristics of oro-facial structures and submental triangle of participants with obstructive sleep apnoea (OSA), as well as to investigate its correlation with the anatomy, posture and functions of the oro-facial structures.

METHOD

Eighteen patients diagnosed with OSA by polysomnography (OSA group; 57.4 ± 15.8 years) and 13 healthy participants screened for OSA (control group; 57.8 ± 18.1 years) were included. All participants answered to questionnaires for OSA and excessive daytime sleepiness, and were submitted to infrared image thermography analysis of facial regions of interest (ROIs), oro-facial myofunctional evaluation (OMES-E protocol) and masticatory performance. Statistical analysis included one-way ANOVA and Pearson/Spearman correlation test.

RESULTS

Obstructive sleep apnoea group showed lower thermographic measures in many ROIs in the frontal and lateral views of the face, including the submental triangle region, and lower scores of aspect/posture and performance of oro-facial structures, as well lower total score of OMES-E evaluation (P < .05). Scores of aspect/posture and mobility were correlated with the temperature of some ROIs in the frontal and lateral views.

CONCLUSION

Lower facial skin and submental triangle region temperatures, measured by infrared thermography, and a worse oro-facial myofunctional condition were identified in the group of individuals with OSA. The higher temperatures of the ROIs were correlated with the better status of aspect/posture and performance of the oro-facial myofunctional structures.

A computer aided diagnostic method for the evaluation of type II diabetes mellitus in facial thermograms

Almost 50% of individuals around the globe are unaware of diabetes and its complications. So, an early screening of diabetes is very important at this current situation. To overcome the difficulties such as pain and discomfort to the subjects obtained from the biochemical diagnostic procedures; an infrared thermography is the diagnostic technique which measures the skin surface temperature noninvasively. Thus, the aim of our proposed study was to evaluate the type II diabetes in facial thermograms and to develop a computer aided diagnosis (CAD) system to classify the normal and diabetes. The facial thermograms (n = 160) including male (n = 79) and female (n = 81) were captured using FLIR A 305sc infrared thermal camera. The Haralick textural features were extracted from the facial thermograms based on gray level co-occurrence matrix algorithm. The T_ROI, T_MAX, and T_TOT are the statistical temperature parameters exhibited a significant negative correlation with HbA1c (r = - 0.421, - 0.411, - 0.242, p < 0.01 (T_ROI); r = - 0.259, p < 0.01(T_MAX) and - 0.173, p < 0.05 (T_TOT)). An optimal regression equation has been constructed by using the significant facial variables and standard HbA1c values. The model has achieved sensitivity, specificity, and accuracy rate as 91.42%, 88.57%, and 90% respectively. The anthropometrical variables, extracted textural features and temperature parameters were fed into the classifiers and their performances were compared. The Support Vector Machine outperformed the Linear Discriminant Analysis (84.37%) and k-Nearest Neighbor (81.25%) classifiers with the maximum accuracy rate of 89.37%. The developed CAD system has achieved 89.37% of accuracy rate for the classification of diabetes. Thus, the facial thermography could be used as the basic non-invasive prognostic tool for the evaluation of type II diabetes mellitus.

Infrared (IR) thermography as a potential screening modality for carotid artery stenosis

In the present study, an infrared (IR) thermal camera was used to map the temperature of the target skin surface, and the resulting thermal image was evaluated for the presence of carotid artery stenosis (CAS). In the presence of stenosis in the carotid artery, abnormal temperature maps are expected to occur on the external skin surface, which could be captured and quantified using IR thermography. A Duplex Ultrasound (DUS) examination was used to establish the ground truth. In each patient, the background-subtracted thermal image, referred to as full thermal image, was used to extract novel parametric cold thermal feature images. From these images, statistical features, viz., correlation, energy, homogeneity, contrast, entropy, mean, standard deviation (SD), skewness, and kurtosis, were calculated and the two groups of patients (control and diseased: a total of 80 carotid artery samples) were classified. Both cut-off value- and support vector machine (SVM)-based binary classification models were tested. While the cut-off value classification model resulted in a moderate performance (70% accurate), SVM was found to have classified the patients with high accuracy (92% or higher). This preliminary study suggests the potential of IR thermography as a possible screening tool for CAS patients.

An Overview of Biofield Devices

Advances in biophysics, biology, functional genomics, neuroscience, psychology, psychoneuroimmunology, and other fields suggest the existence of a subtle system of "biofield" interactions that organize biological processes from the subatomic, atomic, molecular, cellular, and organismic to the interpersonal and cosmic levels. Biofield interactions may bring about regulation of biochemical, cellular, and neurological processes through means related to electromagnetism, quantum fields, and perhaps other means of modulating biological activity and information flow. The biofield paradigm, in contrast to a reductionist, chemistry-centered viewpoint, emphasizes the informational content of biological processes; biofield interactions are thought to operate in part via low-energy or "subtle" processes such as weak, nonthermal electromagnetic fields (EMFs) or processes potentially related to consciousness and nonlocality. Biofield interactions may also operate through or be reflected in more well-understood informational processes found in electroencephalographic (EEG) and electrocardiographic (ECG) data. Recent advances have led to the development of a wide variety of therapeutic and diagnostic biofield devices, defined as physical instruments best understood from the viewpoint of a biofield paradigm. Here, we provide a broad overview of biofield devices, with emphasis on those devices for which solid, peer-reviewed evidence exists. A subset of these devices, such as those based upon EEG- and ECG-based heart rate variability, function via mechanisms that are well understood and are widely employed in clinical settings. Other device modalities, such a gas discharge visualization and biophoton emission, appear to operate through incompletely understood mechanisms and have unclear clinical significance. Device modes of operation include EMF-light, EMF-heat, EMF-nonthermal, electrical current, vibration and sound, physical and mechanical, intentionality and nonlocality, gas and plasma, and other (mode of operation not well-understood). Methodological issues in device development and interfaces for future interdisciplinary research are discussed. Devices play prominent cultural and scientific roles in our society, and it is likely that device technologies will be one of the most influential access points for the furthering of biofield research and the dissemination of biofield concepts. This developing field of study presents new areas of research that have many important implications for both basic science and clinical medicine.