Regions of interest selection and thermal imaging data analysis in sports and exercise science: a narrative review

Effects of Foam Rolling Prior to Proprioceptive Neuromuscular Facilitation Stretching on Hamstring Flexibility and Thigh Skin Temperature

CONTEXT

Proprioceptive neuromuscular facilitation stretching (PNFS) is suggested to improve the range of motion and flexibility as an active warm-up. Recently, the foam rolling (FR) methods have also emerged as a passive warm-up. However, the combined effects of PNFS and FR are still unclear, and no reports have compared their effects using thermal imaging. This study investigated the acute effects of combining nonvibration FR (NVFR) and vibration FR (VFR) prior to PNFS, in comparison with PNFS alone, on hamstring flexibility and thigh skin temperature.

DESIGN

Randomized controlled trial.

METHODS

Participants (n = 60) were randomly assigned to PNFS, NVFR + PNFS, VFR + PNFS, and control group (CG). Active knee-extension (AKE), sit and reach (SR) test, and thermal imaging were evaluated before (pre-int), immediately after (post-int), and 30-minutes after (post30-int) intervention.

RESULTS

All intervention groups had a significant increase at all time periods (P < .001) except the CG in terms of AKE and sit and reach test (P > .05). Combined (NVFR + PNFS/VFR + PNFS) groups had also a significant increase in the post30-int compared with pre-int and post-int values of thigh skin temperature (P < .001). Combined groups, over time, had the best post30-int effect on increasing skin temperature. The study found a significant interaction effect between interventions and time across several measurements (P < .05). Combined groups showed more significant improvements in AKE compared to CG at post-int (P < .05). There is a similar change in AKE, SR test, and skin temperatures between combined groups and PNFS alone at both post-int and post30-int (P < .05).

CONCLUSIONS

These findings indicate that using FR, with or without vibration, before PNFS does not provide an additional benefit in improving hamstring flexibility and thigh skin temperatures compared with PNFS alone.

The influence of static and dynamic warm-up on knee temperature: infrared thermography insights before and after a change of direction exercise

Introduction

Infrared thermography is gaining attention in the field of sports medicine and performance. This study investigated the effects of static and dynamic warm-ups and a 90° change of direction (COD) exercise on the thermal response of the knee.

Methods

Thermograms were collected using the FlIR E54 Imaging Camera from 85 healthy young adults, 46 men and 39 women, aged 20-31 years. The participants were divided in two groups, static and dynamic warm-up. Four thermograms were taken: baseline (T0), warm-up (T1), COD (T2), and rest (T3). Four regions of interest (ROIs) of the knee were analyzed: anterior upper half (AUH), anterior lower half (ALH), posterior upper half (PUH), and posterior lower half (PLH). Mixed ANOVA with the Bonferroni-Holm test and independent t-test were used for pairwise comparison and to spot differences between the right and left knees at T1 and T2 and at T0 between men and women, respectively.

Results

The mixed ANOVA was significant for time points (p< 0.001) in all the ROIs and for the stretching/temperature interaction with different levels of significance. The t-test results for the right and left knees at T1 and T2 were not significant. The temperature in the static warm-up group followed a decrease at T1, a subsequent decrease at T2, and a recovery similar to the baseline at T3, in the ALH in men and women and in the PUH only in men.

Conclusion

Static stretching was more suitable for preparing the knee for the COD exercise than the dynamic one in terms of the thermal response.

Predicting Sleep Quality through Biofeedback: A Machine Learning Approach Using Heart Rate Variability and Skin Temperature

Sleep quality (SQ) is a crucial aspect of overall health. Poor sleep quality may cause cognitive impairment, mood disturbances, and an increased risk of chronic diseases. Therefore, assessing sleep quality helps identify individuals at risk and develop effective interventions. SQ has been demonstrated to affect heart rate variability (HRV) and skin temperature even during wakefulness. In this perspective, using wearables and contactless technologies to continuously monitor HR and skin temperature is highly suited for assessing objective SQ. However, studies modeling the relationship linking HRV and skin temperature metrics evaluated during wakefulness to predict SQ are lacking. This study aims to develop machine learning models based on HRV and skin temperature that estimate SQ as assessed by the Pittsburgh Sleep Quality Index (PSQI). HRV was measured with a wearable sensor, and facial skin temperature was measured by infrared thermal imaging. Classification models based on unimodal and multimodal HRV and skin temperature were developed. A Support Vector Machine applied to multimodal HRV and skin temperature delivered the best classification accuracy, 83.4%. This study can pave the way for the employment of wearable and contactless technologies to monitor SQ for ergonomic applications. The proposed method significantly advances the field by achieving a higher classification accuracy than existing state-of-the-art methods. Our multimodal approach leverages the synergistic effects of HRV and skin temperature metrics, thus providing a more comprehensive assessment of SQ. Quantitative performance indicators, such as the 83.4% classification accuracy, underscore the robustness and potential of our method in accurately predicting sleep quality using non-intrusive measurements taken during wakefulness.

Active Breaks Reduce Back Overload during Prolonged Sitting: Ergonomic Analysis with Infrared Thermography

Background: Prolonged sitting is a potential risk factor for musculoskeletal disorders in office workers. This study aims to evaluate the effect of active breaks on reducing muscle overload in subjects who sit for long periods using infrared thermography (IRT). Methods: A sample of 57 office workers participated in this study and were divided into two groups: active breaks (ABs) and no active breaks (NABs). The NAB group sat continuously for 90 min without standing up, while the AB group performed stretching and mobility exercises every 30 min. IRT measurements were taken every 30 min before the active breaks. Results: The results highlight that the skin temperature of the back increased significantly in both groups after 30 min of sitting; however, in the subsequent measurements, the AB group showed a decrease in temperature, while the NAB group maintained a high temperature. Exercise and time point of measurement all reported p-values < 0.001; there were no statistically significant differences between the Δt0-1 of the NAB and AB groups, while the Δt1-2 and Δt1-3 of the NAB and AB groups showed statistically significant differences for all back regions. Conclusions: The clinical relevance of this study confirms the negative effects of prolonged sitting on the health of the back, demonstrating that active breaks can reduce back strain, emphasizing the need for workplace interventions. In addition, IRT represents a non-invasive method to assess back muscle overload and monitor the effectiveness of interventions in all categories of workers who maintain a prolonged sitting position. The main limitation of this study is the absence of a questionnaire for the assessment of back pain, which does not allow a direct correlation between temperature changes and back pain outcomes.

Acute physiological responses to a pyramidal exercise protocol and the associations with skin temperature variation in different body areas

This study aimed to examine the skin temperature (Tsk) variations in five regions of interest (ROI) to assess whether possible disparities between the ROI's Tsk could be associated with specific acute physiological responses during cycling. Seventeen participants performed a pyramidal load protocol on a cycling ergometer. We synchronously measured Tsk in five ROI with three infrared cameras. We assessed internal load, sweat rate, and core temperature. Reported perceived exertion and calves' Tsk showed the highest correlation (r = -0.588; p < 0.01). Mixed regression models revealed that the heart rate and reported perceived exertion were inversely related to calves' Tsk. The exercise duration was directly associated with the nose tip and calf Tsk but inversely related to the forehead and forearm Tsk. The sweat rate was directly related to forehead and forearm Tsk. The association of Tsk with thermoregulatory or exercise load parameters depends on the ROI. The parallel observation of the face and calf Tsk could indicate simultaneously the observation of acute thermoregulatory needs and individual internal load. The separate Tsk analyses of individual ROI appear more suitable to examine specific physiological response than a mean Tsk of several ROI during cycling.

An exploratory, intra- and interindividual comparison of the deep neural network automatically measured calf surface radiation temperature during cardiopulmonary running and cycling exercise testing: A preliminary study

Non-invasive and contactless infrared thermography (IRT) measurements have been claimed to indicate acute neural, cardiovascular, and thermoregulatory adaptations during exercise. Due to challenging comparability, reproducibility, and objectivity, investigations considering different exercise types and intensities, and automatic ROI analysis are currently needed. Thus, we aimed to examine surface radiation temperature (T_sr) variations during different exercise types and intensities in the same individuals, ROI, and environmental conditions. Ten healthy, active males performed a cardiopulmonary exercise test on a treadmill in the first week and on a cycling ergometer the following week. Respiration, heart rate, lactate, rated perceived exertion, the mean, minimum, and maximum T_sr of the right calf (CT_sr (°C)), and the surface radiation temperature pattern (CP_sr) were explored. We executed two-way rmANOVA and Spearman's rho correlation analyses. Across all IRT parameters, mean CT_sr showed the highest association to cardiopulmonary parameters (E.g., oxygen consumption: r_s = -0.612 (running); -0.663 (cycling); p < .001). A global significant difference of CT_sr was identified between all relevant exercise test increments for both exercise-types (p < .001; η²_p = .842) and between both exercise-types (p = .045; η²_p = .205). Differences in CT_sr between running and cycling significantly appeared after a 3-min recovery period, whereas lactate, heart rate, and oxygen consumption were not different. High correlations between the CT_sr values extracted manually and the CT_sr values processed automatically by a deep neural network were identified. The applied objective time series analysis enables crucial insights into intra- and interindividual differences between both tests. CT_sr variations indicate different physiological demands between incremental running and cycling exercise testing. Further studies applying automatic ROI analyses are needed to enable the extensive analysis of inter- and intraindividual factors influencing the CT_sr variation during exercise to allow determine the criterion and predictive validity of IRT parameters in exercise physiology.

Can Data-Driven Supervised Machine Learning Approaches Applied to Infrared Thermal Imaging Data Estimate Muscular Activity and Fatigue?

Surface electromyography (sEMG) is the acquisition, from the skin, of the electrical signal produced by muscle activation. Usually, sEMG is measured through electrodes with electrolytic gel, which often causes skin irritation. Capacitive contactless electrodes have been developed to overcome this limitation. However, contactless EMG devices are still sensitive to motion artifacts and often not comfortable for long monitoring. In this study, a non-invasive contactless method to estimate parameters indicative of muscular activity and fatigue, as they are assessed by EMG, through infrared thermal imaging (IRI) and cross-validated machine learning (ML) approaches is described. Particularly, 10 healthy participants underwent five series of bodyweight squats until exhaustion interspersed by 1 min of rest. During exercising, the vastus medialis activity and its temperature were measured through sEMG and IRI, respectively. The EMG average rectified value (ARV) and the median frequency of the power spectral density (MDF) of each series were estimated through several ML approaches applied to IRI features, obtaining good estimation performances (r = 0.886, p < 0.001 for ARV, and r = 0.661, p < 0.001 for MDF). Although EMG and IRI measure physiological processes of a different nature and are not interchangeable, these results suggest a potential link between skin temperature and muscle activity and fatigue, fostering the employment of contactless methods to deliver metrics of muscular activity in a non-invasive and comfortable manner in sports and clinical applications.

Theory and applications of InfraRed and thermal image analysis in ergonomics research

Designing products and services to fit human needs, wants and lifestyle require meaningful data. With Industry 4.0 and the internet of things, we have many ways to capture data using sensors and other means. InfraRed (IR) cameras are quite ubiquitous, especially for screening illness and wellness. They can provide a wealth of data on different objects and even people. However, their use has been limited due to processing complexities. With reducing cost and increasing accuracy of IR cameras, access to thermal data is becoming quite widespread, especially in medicine and people-related applications. These cameras have software to help process the data, with a focus on qualitative analyses and rather primitive quantitative analyses. In ergonomics, data from multiple users are essential to make reasonable predictions for a given population. In this study, using 4 simple experiments, several quantitative analysis techniques such as simple statistics, multivariate statistics, geometric modeling, and Fourier series modeling are applied to IR images and videos to extract essential user and population data. Results show that IR data can be useful to provide user and population data that are important for design. More research in modeling IR data and application software is needed for the increased application of IR information in ergonomics applications.

Preliminary study of thermal density distribution and entropy analysis during cycling exercise stress test using infrared thermography

Considerable differences related to the results of temperature changes acquired during exercise exist, and in many cases, these lead to poor correlation with physiological variables. In this preliminary study we investigated the temperature changes and the temperature distribution (entropy) of the torso during a graded cycling exercise stress test using thermal imaging and studied the correlation between the increase in pulmonary ventilation (VE) and the changes in the surface temperature of the anterior torso during exercise. Thermal images of the anterior torso were captured every 30 s during the exercise, while the resistance was gradually increased every minute until exhaustion. The thermal images were processed to obtain a mean temperature in the regions of interest (ROI) (chest, forehead, and abdomen). We also developed an algorithm to calculate the distribution of temperature and texture (entropy) within each ROI. No changes were found in absolute temperatures. However, the entropy of the chest surface area increased significantly throughout the exercise test, compared with baseline temperature at rest. This increase in entropy was significantly correlated with exercise duration and intensity (p < 0.001). Furthermore, a high correlation between the increase in VE and chest entropy during exercise was detected (r = 0.9515). No correlations were found between the increase in entropy and the abdomen or the forehead compared with the VE. The non-invasive IR thermal imaging during graded exercise, combined with advanced image processing, successfully correlates surface thermography with exercise duration and pulmonary ventilation.

Towards Exercise Radiomics: Deep Neural Network-Based Automatic Analysis of Thermal Images Captured During Exercise

Infrared thermography is increasingly applied in sports science due to promising observations regarding changes in skin's surface radiation temperature ( T_sr) before, during, and after exercise. The common manual thermogram analysis limits an objective and reproducible measurement of T_sr. Previous analysis approaches depend highly on expert knowledge and have not been applied during movement. We aimed to develop a deep neural network (DNN) capable of automatically and objectively segmenting body parts, recognizing blood vessel-associated T_sr distributions, and continuously measuring T_sr during exercise. We conducted 38 cardiopulmonary exercise tests on a treadmill. We developed two DNNs: body part network and vessel network, to perform semantic segmentation of 1 107 855 captured thermal images. Both DNNs were trained with 263 training and 75 validation images. Additionally, we compare the results of a common manual thermogram analysis with these of the DNNs. Performance analysis identified a mean IoU of 0.8 for body part network and 0.6 for vessel network. There is a high agreement between manual and automatic analysis (r = 0.999; p 0.001; T-test: p = 0.116), with a mean difference of 0.01 ^C (0.08). Non-parametric Bland Altman's analysis showed that the 95% agreement ranges between -0.086 ^C and 0.228 ^C. The developed DNNs enable automatic, objective, and continuous measurement of T_sr and recognition of blood vessel-associated T_sr distributions in resting and moving legs. Hence, the DNNs surpass previous algorithms by eliminating manual region of interest selection and form the currently needed foundation to extensively investigate T_sr distributions related to non-invasive diagnostics of (patho-)physiological traits in means of exercise radiomics.

Central and Peripheral Thermal Signatures of Brain-Derived Fatigue during Unilateral Resistance Exercise: A Preliminary Study

Simple Summary

Fatigue is considered a brain-derived emotion that could impact performance during the execution of physical exercises. Infrared thermography is a valuable technique able to measure the psychophysiological state associated with emotions in a contactless manner. The aim of the study is to test the capability of infrared thermography to evaluate the central and peripheral physiological effect of fatigue through facial skin and muscle temperature modulations collected during the execution of a unilateral resistance exercise of the lower limb. Both time- and frequency-domain analyses were performed on the temperature time course of the face and limbs. Particularly, significant correlations between features extracted from the thermal signals and the perceived exertion were found. These findings confirmed the ability of thermal imaging to detect both peripheral and central effects of fatigue in response to physical exercises. These results could foster the employment of infrared thermography to monitor the psychophysiological state of the athletes during training. The possibility to calibrate the training load in accordance with the psychophysiological conditions could improve the performance of the athletes during the training process and competitions.

Abstract

Infrared thermography (IRT) allows to evaluate the psychophysiological state associated with emotions from facial temperature modulations. As fatigue is a brain-derived emotion, it is possible to hypothesize that facial temperature could provide information regarding the fatigue related to exercise. The aim of this study was to investigate the capability of IRT to assess the central and peripheral physiological effect of fatigue by measuring facial skin and muscle temperature modulations in response to a unilateral knee extension exercise until exhaustion. Rate of perceived exertion (RPE) was recorded at the end of the exercise. Both time- (∆T_ROI: pre–post exercise temperature variation) and frequency-domain (∆PSD: pre–post exercise power spectral density variation of specific frequency bands) analyses were performed to extract features from regions of interest (ROIs) positioned on the exercised and nonexercised leg, nose tip, and corrugator. The ANOVA-RM revealed a significant difference between ∆T_ROI (F_(1.41,9.81) = 15.14; p = 0.0018), and between ∆PSD of myogenic (F_(1.34,9.39) = 15.20; p = 0.0021) and neurogenic bands (F_(1.75,12.26) = 9.96; p = 0.0034) of different ROIs. Moreover, significant correlations between thermal features and RPE were found. These findings suggest that IRT could assess both peripheral and central responses to physical exercise. Its applicability in monitoring the psychophysiological responses to exercise should be further explored

The use of infrared thermography for the dynamic measurement of skin temperature of moving athletes during competition; methodological issues

Objective. To investigate the use of infrared thermography (IRT) for skin temperature measurement of moving athletes during competition and its sensitivity to factors that are traditionally standardised.Approach. Thermograms were collected for 18 female athletes during the 20 km racewalk at the 2019 World Athletics Championships, with a medium-wave, cooled indium antimonide medium wave infrared band (MWIR) and a long-wave, uncooled microbolometer longwave infrared band (LWIR) infrared camera.Main results. The MWIR provided greater clarity images of motion due to a shorter exposure and response time and produced a higher percentage of acceptable images. Analysing acceptable images only, the LWIR and WMIR produced good levels of agreement, with a bias of -0.1 ± 0.6 °C in mean skin temperature for the LWIR. As the surface area of an ROI was reduced, the measured temperature became less representative of the whole ROI. Compared to measuring the whole area ROI, a single central pixel produced a bias of 0.3 ± 0.3 °C (MWIR) and 0.1 ± 0.4 °C (LWIR) whilst using the maximum and minimum temperature pixels resulted in deviations of 1.3 ± 0.4 °C and -1.1 ± 0.3 °C (MWIR) and 1.2 ± 0.3 °C and -1.3 ± 0.4 °C (LWIR). The sensitivity to air and reflected temperatures was lower for the LWIR camera, due to the higher emissivity of skin in its wavelength.Significance. IRT provides an appropriate tool for the measurement of skin temperature during real-world competition and critically during athlete motion. The cheaper LWIR camera provides a feasible alternative to the MWIR in low rate of motion scenarios, with comparable precision and sensitivity to analysis. However, the LWIR is limited when higher speeds prevent the accurate measurement and ability to capture motion.