Heart rate is a crucial indicator of human health with significant physiological importance. Traditional contact methods for measuring heart rate, such as electrocardiograph or wristbands, may not always meet the need for convenient health monitoring. Remote photoplethysmography (rPPG) provides a non-contact method for measuring heart rate and other physiological indicators by analyzing blood volume pulse signals. This approach is non-invasive, does not require direct contact, and allows for long-term healthcare monitoring. Deep learning has emerged as a powerful tool for processing complex image and video data, and has been increasingly employed to extract heart rate signals remotely. This article reviewed the latest research advancements in rPPG-based heart rate measurement using deep learning, summarized available public datasets, and explored future research directions and potential advancements in non-contact heart rate measurement.
Humans ; Deep Learning ; Heart Rate/physiology* ; Photoplethysmography/methods* ; Video Recording ; Face ; Monitoring, Physiologic/methods* ; Signal Processing, Computer-Assisted

Multi-task learning (MTL) has demonstrated significant advantages in the field of physiological signal measurement. This approach enhances the model's generalization ability by sharing parameters and features between similar tasks, even in data-scarce environments. However, traditional multi-task physiological signal measurement methods face challenges such as feature conflicts between tasks, task imbalance, and excessive model complexity, which limit their application in complex environments. To address these issues, this paper proposes an enhanced multi-scale spatiotemporal network (EMSTN) based on Eulerian video magnification (EVM), super-resolution reconstruction and convolutional multilayer perceptron. First, EVM is introduced in the input stage of the network to amplify subtle color and motion changes in the video, significantly improving the model's ability to capture pulse and respiratory signals. Additionally, a super-resolution reconstruction module is integrated into the network to enhance the image resolution, thereby improving detail capture and increasing the accuracy of facial action unit (AU) tasks. Then, convolutional multilayer perceptron is employed to replace traditional 2D convolutions, improving feature extraction efficiency and flexibility, which significantly boosts the performance of heart rate and respiratory rate measurements. Finally, comprehensive experiments on the Binghamton-Pittsburgh 4D Spontaneous Facial Expression Database (BP4D+) fully validate the effectiveness and superiority of the proposed method in multi-task physiological signal measurement.
Humans ; Neural Networks, Computer ; Signal Processing, Computer-Assisted ; Face/physiology* ; Video Recording ; Facial Expression ; Heart Rate ; Algorithms

OBJECTIVE: To investigate the changes and symmetry of facial soft tissue during posed smile, to analyze the feature of posed smile in different gender, and verify the reproducibility of posed smile. METHODS: Three-dimensional (3D) facial images of 41 adults (16 males and 25 females with an average age of 26.76±2.70 years) which were taken by FaceScan three-dimensional sensor, including one rest position and two posed smile images. Then these images were imported into 3D soft tissue analysis software for model repositioning. 3D morphable model method (3DMM) was carried out to automatic landmarks setting. After that, the measurement of the eyes, cheeks, nose and perioral area were carried out for 3D soft tissue analysis. Finally, the changes and symmetry of the soft tissues between the two expression states and the gender differences during the posed smiles were compared. Meanwhile, the reproducibility of posed smile was statistically tested. RESULTS: Compared with the rest position, except for nasolabial angle (1.45°±7.65°), the measurements of 3D soft tissue in other region were changed in posed smile (P < 0.001). It should be noted that the eye region was also significantly changed (P < 0.001). Furthermore, the prominent feature of posed smile was that the alar base length became longer, the upper and lower vermilions were narrow and thin, and the mentolabial furrows became shallow. Meanwhile the chin extended anteriorly while the mouth retracted; During posed smile, the labial fissure asymmetry [2.78 (1.73, 3.49) mm], mid-infraorbital asymmetry [2.36 (1.22, 3.27) mm] and outercanthal asymmetry [2.31(1.29, 2.80) mm] were most apparent. Compared with the rest position, the asymmetry was not significantly increased except for cheilion and alar curvature points during the posed smile (P>0.05). In the posed smile, the changes of the right palpebral fissure height and the thickness of lower vermilion (|Li-Stoi| _z) of males were greater than those of females (P < 0.05), and asymmetry of exocanthion and cheekbone increased more than that of females (P < 0.05). There was no obvious difference between the two posed smiles. CONCLUSION In this study, during the posed smile the soft tissues of the eyes, cheeks, nose, lips and chin changed in different degrees, and the asymmetry of cheilion and alar curvature point was greater than that of the rest position; In addition, the reproducibility of posed smile was excellent, which can be a reference for clinical aesthetics and functional research of smile.
Humans ; Smiling/physiology* ; Female ; Male ; Adult ; Imaging, Three-Dimensional/methods* ; Face/anatomy & histology* ; Young Adult ; Facial Expression

OBJECTIVES: To search age-correlated facial features and construct an age estimation model based on the three-dimensional （3D） facial images of Xinjiang Uygur males, and to structure individual face images of old age and young age. METHODS: Pretreatment was performed to collect 105 3D facial images of Xingjiang Uygur males aged between 17-57 years by Artec Studio software. The facial images were transferred to high-density 3D dot matrix data by FaceAnalysis software, and each image could be represented with 32 251 vertexes. Central correction of the facial images was done and all the data were aligned to a standard coordinate frame by generalized Procrustes analysis （GPA）. The age estimation model was established by partial least square regression （PLSR）. Furthermore, the changes of age-correlated facial features were presented on the heat map of average face, and the reconstruction of facial images at different ages was performed based on this model. RESULTS: With age, the average faces showed a series of changes including the nasolabial sulcus deepening, cheek sinking, cheekbone protruding and eye corner drooping. The Pearson correlation coefficient （r） between estimated age and chronological age was 0.71. The mean absolute deviation （MAD） of age estimation was 6.37 years. The results of age estimation in >30-40 years group showed a best accuracy （MAD=4.27 years）, and the deviations increased with age after 40 years. The composite facial images represented a significant result with age on facial morphological features and aging. CONCLUSIONS The results of this study reveal the age-correlated facial features and aging markers in Uygur population, which help to construct a reliable age estimation model.
Adolescent ; Adult ; Aging/physiology* ; Face/anatomy & histology* ; Head/anatomy & histology* ; Humans ; Imaging, Three-Dimensional/methods* ; Male ; Middle Aged ; Software ; Young Adult

BACKGROUNDThe pain caused by orthodontic treatment has been considered as tough problems in orthodontic practice. Danggui-shaoyao-san (DSS) is a traditional Chinese medicine (TCM) prescription which has long been used for pain treatment and possesses antioxidative, cognitive enhancing and antidepressant effects. We raise the hypothesis that DSS exerts analgesic effect for orthodontic pain via inhibiting the activations of neuron and microglia.

METHODSDSS was given twice a day from day 5 prior to experimental tooth movement (ETM). Directed face grooming and vacuous chewing movements (VCM) were evaluated. Immunofluorescent histochemistry and Western blot analysis were used to quantify the Iba-1 (microglia activation) and Fos (neuronal activation) expression levels in the trigeminal spinal nucleus caudalis (Vc).

RESULTSETM significantly increased directed face grooming and VCM which reached the peak at post-operative day (POD) 1 and gradually decreased to the baseline at POD 7. However, a drastic peak increase of Fos expression in Vc was observed at 4 hours and gradually decreased to baseline at POD 7; while the increased Iba-1 level reached the peak at POD 1 and gradually decreased to baseline at POD 7. Furthermore, pre-treatment with DSS significantly attenuated the ETM induced directed face grooming and VCM as well as the Fos and Iba-1 levels at POD 1.

CONCLUSIONTreatment with DSS had significant analgesic effects on ETM-induced pain, which was accompanied with inhibition of both neuronal and microglial activation.

Animals ; Drugs, Chinese Herbal ; therapeutic use ; Face ; physiology ; Male ; Mastication ; physiology ; Medicine, Chinese Traditional ; methods ; Microglia ; drug effects ; physiology ; Neurons ; drug effects ; physiology ; Pain ; drug therapy ; Pain Management ; methods ; Postoperative Period ; Rats ; Rats, Sprague-Dawley ; Tooth Movement Techniques ; adverse effects

OBJECTIVETo observe the specificity relationship between acupuncture at "Hegu" (LI 4) and the facial muscular movement in rhesus monkeys under the physiological state by using neuromuscular electrical measurement technique.

METHODSEighteen rhesus monkeys were randomized into a Hegu group, a Houxi group and a Waiguan group, 6 monkeys in each one. Under the physiological state, EMG was detected on the frontal muscle, zygomatic muscle and orbicular muscle before and after acupuncture at different acupoints. The impacts of acupuncture on the facial EMG were studied and compared among different acupoints.

RESULTSWith acupuncture at "Hegu" (LI 4), the latency was reduced (P < 0.01) and the peak value and area were increased (P < 0.05, P < 0.01) in the frontal EMG; the area and the peak value were increased (P < 0.01, P < 0.05) and latency was reduced (P < 0.05) in the zygomatic EMG; the frequency was increased (P < 0.01) and the latency was reduced (P < 0.05) in the orbicular EMG. Before and after acupuncture at "Hegu" (LI 4), the change rates of EMG frequency, peak value, area and latency on the frontal, zygomatic and orbicular muscles were higher than those at "Houxi" (SI 3) and "Waiguan" (TE 5) (P < 0.05, P < 0.01) separately.

CONCLUSIONThe relative specificity presents between Hegu (LI 4) and facial muscular movement.

Acupuncture Points ; Acupuncture Therapy ; Animals ; Electromyography ; Face ; physiology ; Female ; Humans ; Macaca mulatta ; Male ; Models, Animal

OBJECTIVETo discuss the midface aging mechanism through anatomic study of malar fat pad.

METHODS10 fresh adult cadaveric heads (20 sides) fixed by vascular perfusion of formalin were used for anatomic study with microsurgery technique under microscope. The midfacial ligament and connective tissue between skin and subcutaneous fat were observed carefully in different parts of midface. The location, shape and extent of malar fat pad was also recorded and photographed.

RESULTSThe malar fat pad has a triangle shape. The bottom is a curve along the orbicularis retaining ligament at the lower eyelid. The fat pad is extended internally to the nasolabial fold and labiomandibular fold, externally from the major zygomatic muscle end point at the malar surface to the angulus oris and submandibular edge. (2) The malar fat pad is composed of meshed fibrous tissue, with big fat particles in it. It becomes tight when being stretched in horizontal direction along nasolabial fold and loosen when being stretched in vertical direction. (3) There is tight connection between skin and fat pad, which is divided into four areas as I, II, III, IV. The areas I, II, III are strip-shaped parelled to the nasolabial fold. The area IV is a irregular quadrilateral. (4) There are six fixation ligaments between malar fat pad and deep tissue: orbicularis retaining ligament upper layer of lower eyelid, orbicularis retaining ligament substratum of lower eyelid, zygomaticus ligament, zygomatic cutaneous ligament, zygomatic cutaneous ligament substratum, platysma There are four closely connected areas cutaneous forward ligament, cheek maxilla ligament.

CONCLUSIONSbetween the facial skin and malar fat pad which makes malar fat pad and skin keep relatively consistent. The malar fat pad moving down mainly resulted from slack of ligaments support which is one of the reasons for aging face.

Adipose Tissue ; anatomy & histology ; physiology ; Cadaver ; Cheek ; Eyelids ; anatomy & histology ; physiology ; Face ; anatomy & histology ; physiology ; Facial Muscles ; anatomy & histology ; physiology ; Head ; Humans ; Ligaments ; anatomy & histology ; physiology ; Lip ; anatomy & histology ; physiology ; Skin ; anatomy & histology ; Skin Aging ; pathology ; physiology

Event-related potential (ERP) studies report that early components P120, N170 and VPP are associated with face processing. Several lines of evidence suggest that VPP is the positive counterpart of N170, and they are generated by the same brain sources. However, whether P120 has a negative counterpart and the relations among these early components (i.e. P120, N170, VPP) remain unclear. In this study, the scalp electroencephalogram was recorded when the subjects passively viewed different stimuli, and ERP was calculated. The synchronization of electroencephalography signals between fronto-central and bilateral occipitotemporal sites was evaluated, and independent component analysis was employed to seek the face-sensitive independent components and their corresponding sources. We found that P120 had the negative counterpart, i.e., VN120; moreover, VN120-VPP and P120-N170 complexes were generated by the same sources located in fusiform gyrus, which reflected the same sequential neural activities of face processing.
Adolescent ; Brain ; physiology ; Electroencephalography ; Evoked Potentials ; physiology ; Face ; Female ; Humans ; Male ; Pattern Recognition, Visual ; physiology ; Perception ; physiology ; Sensation ; physiology ; Young Adult

PURPOSE: The purposes of this study were to explain the phenomena of hot flashes in climacteric women by using Mexameter, Skin Thermometer, Corneometer, and Laser Doppler Perfusion Imager (LDPI) objectively and to identify the interrelation between the subjective and objective measurements of hot flashes by comparing the two as reported in retrospective questionnaires. METHODS: The participants were one hundred women (45-60 yr) who were not currently on hormone therapy, and had reached hot flash scores of 10 or higher. Hot flashes were measured in a temperature and humidity controlled room for 7 hr from 10 am to 5 pm. Hot flashes were measured subjectively and recorded via the Hot Flash Diary Report. When participants felt the hot flashes, they were measured objectively by Mexameter, Skin Thermometer, Corneometer, and LDPI. RESULTS: The frequency of hot flashes in participants ranged from 1 to 7 times. When hot flashes occurred in participants, the erythema, skin temperature, skin hydration, and blood perfusion showed statistically significant changes in all measurements. But, the subjective and objective measurements of hot flashes showed only weak correlations. CONCLUSION: Results indicate a need for future research with subjective and objective measuring instruments chosen depending variations identified for the study.
Climacteric ; Erythema/etiology ; Face/blood supply/physiology ; Female ; Hot Flashes/*complications/epidemiology ; Humans ; Middle Aged ; Postmenopause ; Skin Temperature/physiology

The method of event-related potentials (ERP) was used to study the gender difference in face recognition. The stimuli in the experiment were 10 upright and 10 inverted face photos. The subjects, half female and half male, were asked to judge whether the face was upright or inverted. The results showed that the N170 wave forms were observed in the occipito-temporal regions and they were found exhibiting brain's right hemispheric dominance. The stimuli of different gender photos were noticed to have no significant impact on the N170 wave forms, but there were significant differentce in the amplitude and latency period of N170 between different gender participants. Moreover, there was marked difference in the latency period of the male participants watching the same gender face and different gender face. Similar results were not found in the ERP's latency period of female participants.
Adult ; Brain ; physiology ; Electroencephalography ; Evoked Potentials ; Face ; Facial Expression ; Female ; Form Perception ; physiology ; Humans ; Male ; Pattern Recognition, Visual ; physiology ; Recognition (Psychology) ; Sex Factors ; Young Adult