Face Region Research Articles

Applying 3D scanning to evaluate facial symmetry in Asian populations

BackgroundFacial symmetry enhances attractiveness, with various therapies available to improve it. However, trends in facial asymmetry remain unclear. This study evaluates differences between specific facial regions using 3D scanning to guide clinical treatment. MethodThe 3dMD face™ system (3dMD Ltd, USA) scanned 88 subjects' faces. Geomagic Wrap 2021 analyzed the left and right sides. Differences in eyebrow peaks, eyebrow tails, eye ends, and mouth corners were evaluated. ResultsMore subjects showed a drooping right side of the face in eyebrow peaks, eyebrow tails, eye ends, mouth corners, tubercula mentale, and mandibular margin positions. A higher proportion had deeper left nasolabial folds and marionette lines, while more had deeper right tear ducts and lateral chin depressions. More subjects exhibited a prominent right forehead and parotid masseter region, with a prominent left temporal and cheek region. Conclusion3D scanning effectively assesses facial asymmetry in clinical practice. Research indicates significant differences in asymmetry between facial regions. Evaluating these differences pre-treatment can guide the selection of therapeutic methods, improving facial asymmetry treatment. Level of Evidence3 (Diagnostic)

Increased Risk and Unique Clinical Course of Patient Safety Indicator-3 Pressure Injuries Among COVID-19 Hospitalized Patients.

The COVID-19 pandemic introduced unique challenges to healthcare systems, particularly in relation to patient safety and adverse events during hospitalization. There is limited understanding of COVID-19's association with some patient safety indicators (PSIs). This study aimed to investigate the impact of COVID-19 infection on the rate of PSI-3 events and its implications on quality metrics. We compared PSI-3 event rates between COVID-19-infected and uninfected patients and examined the clinical characteristics of COVID-19 patients experiencing PSI-3 events. This is a retrospective study at Mayo Clinic hospitals between January 2020 and February 2022, analyzing patients meeting PSI-3 denominator eligibility criteria. PSI-3 events were identified using AHRQ WinQI software. Patients were categorized based on COVID-19 status. Patient demographics, characteristics, and PSI-3 rates were compared. A case series analysis described clinical details of COVID-19 patients with PSI-3 events. Of 126,781 encounters meeting PSI-3 criteria, 8674 (6.8%) had acute COVID-19 infection. COVID-19-infected patients were older, more likely to be male, non-white, and had private insurance. PSI-3 rates were significantly higher in COVID-19 patients (0.21% versus 0.06%, P < 0.0001), even after risk adjustment (adjusted risk ratio, 3.24, P < 0.0001). The case series of 17 COVID-19 patients with PSI-3 events showed distinctive clinical characteristics, including higher medical device-related pressure injuries, and greater predisposition for head, face, and neck region. Acute COVID-19 infection correlates with higher PSI-3 event rates. Current quality indicators may require adaptation to address the pandemic's complexities and impact on patient safety. Further research is needed to comprehensively understand the intricate relationship between COVID-19 and patient outcomes.

Retrospective Analysis of Clinicopathological Characteristics of Surgically Treated Basal Cell Carcinomas of the Face: A Single-Centre Maxillofacial Surgery Experience.

Background: Basal cell carcinoma is the most common nonmelanoma skin cancer, followed by cutaneous squamous cell carcinoma. The objective of the current study was to retrospectively evaluate the epidemiology, characteristic variations, histological aspects, and prognosis of basal cell carcinoma of the facial region based on a single-centre experience. Methods: Data from 125 patients admitted to the Department of Oral and Maxillofacial Surgery, University Medical Center Schleswig-Holstein (UKSH), Kiel, for surgical treatment of basal cell carcinomas of the face between January 2015 and April 2021 were evaluated. Results: The mean patient age was 79.58 years, 60.5% were male and 39.5% were female. Six patients (4.8%) had tumour recurrence with no regional metastasis. Seventy-nine patients (63%) were classified as T1. The nose and the temporal region were the most common areas. The mean tumour thickness was 3.20 mm. Conclusions: Micronodular, sclerosing/morphoeic, nodular, and superficial growth patterns of basal cell carcinoma are highly correlated to recurrence, so an excision safety margin is recommended. There is a strong correlation between tumour thickness and recurrence among basal cell carcinoma cases. When completely excised, the recurrence rate for basal cell carcinoma is relatively low.

AmazingFT: A Transformer and GAN-Based Framework for Realistic Face Swapping

Current face-swapping methods often suffer from issues of detail blurriness and artifacts in generating high-quality images due to the inherent complexity in detail processing and feature mapping. To overcome these challenges, this paper introduces the Amazing Face Transformer (AmazingFT), an advanced face-swapping model built upon Generative Adversarial Networks (GANs) and Transformers. The model is composed of three key modules: the Face Parsing Module, which segments facial regions and generates semantic masks; the Amazing Face Feature Transformation Module (ATM), which leverages Transformers to extract and transform features from both source and target faces; and the Amazing Face Generation Module (AGM), which utilizes GANs to produce high-quality swapped face images. Experimental results demonstrate that AmazingFT outperforms existing state-of-the-art (SOTA) methods, significantly enhancing detail fidelity and occlusion handling, ultimately achieving movie-grade face-swapping results.

Serial Case of CT Scan Imaging in Fracture of Midface Region

Background: Fractures in the face region are frequently seen in motor vehicle accidents, as the face is highly exposed during such incidents. Motor vehicle accidents are common in Bali, with fracture of the face region is the 2nd most common injury found in radiologic examination. Computed tomography (CT) scans are crucial for assessing these fractures, allowing for an accurate evaluation of severity to plan the patient treatment. Case: We present serial cases CT scan images of complex midface fractures such as Le Fort, tripod, NOE and orbital wall fracture and its characteristic imaging on CT-imaging. Conclusions: CT scan may guide treatment plans aimed at minimizing disability and enhancing the patient's quality of life. Understanding the imaging characteristics of midface fractures is thus essential for effective diagnosis and management.

Defining of the nasal anthropometry on facial computed tomography in subjects with epilepsy and healthy subjects.

Epilepsy is a frequent chronic and genetic brain disease. In diagnose of genetic and craniofacial disease, the face is one of the gold standard phenotypic features. This study was carried out to determine the angle and linear measurements of face region in Turkish healthy and epilepsy subjects, and to apply a feature selection method to identify the most important attributes that affect epilepsy decision. The retrospective and observational study was conducted with 120 subjects with epilepsy aged between 18 to 60 years (56 males; 64 females) and 60 healthy subjects aged between 18 and 55 years (29 males, 31 females). Pyramidal angle performed from 3 reference points, nasal bone length, the width of piriform aperture, nasofrontal angle, nasolabial angle, distance between glabella and nasion were measured on computed tomography. Also, we used supervised machine learning to learn classification models to detect epilepsy as our dataset has class label where 1 means epilepsy, 2 means healthy. The well-known classification model learning algorithms implemented in Weka (with version 3.8.6) machine learning toolkit were applied. All parameters excluding nasal bone length were higher in epilepsy patients than in healthy subjects. Also, there was a significant difference in nasal pyramidal angle nasal bone, nasal pyramidal angle nasal tip, piriform aperture, and nasal bone lengths between epilepsy and healthy subjects. However, age related changes for healthy subjects were no seen in healthy subjects. In epilepsy subjects there was a significant difference in 6 measurements all nasal pyramidal angles, piriform aperture width, nasofrontal angle, and nasolabial angle. Gender related changes were found in only nasal pyramidal angle nasal root and nasal bone of healthy subjects, in nasal pyramidal angle nasal bone, nasal bone length, nasofrontal angle of epilepsy subjects. We can say epilepsy may affect the some facial parameters and these, although anthropometric measurements are affected by age and gender parameters. Comprehensive knowledge of this region's normal references ranges is essential for planning, proper selection of silicone implants or osteotomy determining the limitations of the surgical field and minimizing the risk of complication and performing aesthetic facial surgery or rhinoplasty in epilepsy patients.

Local artifacts amplification for deepfakes augmentation

With the rapid and continuous development of AIGC, It is becoming increasingly difficult to distinguish between real and forged facial images, which calls for efficient forgery detection systems. Although many detection methods have noticed the importance of local artifacts, there has been a lack of in-depth discussion regarding the selection of locations and their effective utilization. Besides, the traditional image augmentation methods that are widely used have limited improvements for forgery detection tasks and require more specialized augmentation methods specifically designed for forgery detection tasks. In this paper, this study proposes Local Artifacts Amplification for Deepfakes Augmentation, which amplifies the local artifacts on the forged faces. Furthermore, this study incorporates prior knowledge about similar facial features into the model. This means that within the facial regions defined in this work, forged features exhibit similar patterns. By aggregating the results from all facial regions, the study can enhance the overall performance of the model. The evaluation experiments conducted in this research, achieving an AUC of 93.40% and an Acc of 87.03% in the challenging WildDeepfake dataset, demonstrate a promising improvement in accuracy compared to traditional image augmentation methods and achieve superior performance on intra-dataset evaluation. The cross-dataset evaluation also showed that the method presented in this study has strong generalization abilities.

Pediatric facial trauma management: Emergency case in a toddler

Background: Facial soft tissue trauma cases are often encountered in the emergency room. Soft tissue trauma, especially to the face, is rarely life threatening. It varies in shape, size, and depth and can also affect surrounding organs. The treatment of soft tissue trauma can be complicated and may have a significant impact on facial function and, especially, facial aesthetics. Children are easily injured due to their active nature. Soft tissue trauma to the faces of toddlers is challenging even for experienced surgeons; however, wound debridement and suture management under general anesthesia should be considered. Purpose: The aim of this article is to deliver a thorough overview of the evaluation and treatment of soft tissue injuries in children, covering initial assessments, physical examinations, the application of antimicrobial therapies, and preparation for surgical procedures. Case: An 11-month-old girl went to the emergency department of Hasan Sadikin General Hospital, Bandung, with injuries to her left cheek and upper left lip sustained when she fell, and her face hit the edge of a cement pot at home. There was no history of unconsciousness, nausea and vomiting. The injury was diagnosed as vulnus laceratum of the left face and upper lip region. Case management: Emergency management was carried out by triage, Tetagam injection, and early wound debridement and suture under general anesthesia because the patient was uncooperative. Wounds on the face and lips were primary sutured layer by layer, returning the wound edges to their normal anatomical position. Conclusion: The management of facial soft tissue injuries in toddlers requires general anesthesia for adequate and accurate wound debridement and suture, so that functional and aesthetic effects can be satisfactorily obtained.

Facial image analysis for automated suicide risk detection with deep neural networks

Accurately assessing suicide risk is a critical concern in mental health care. Traditional methods, which often rely on self-reporting and clinical interviews, are limited by their subjective nature and may overlook non-verbal cues. This study introduces an innovative approach to suicide risk assessment using facial image analysis. The Suicidal Visual Indicators Prediction (SVIP) Framework leverages EfficientNetb0 and ResNet architectures, enhanced through Bayesian optimization techniques, to detect nuanced facial expressions indicating mental state. The models’ interpretability is improved using GRADCAM, Occlusion Sensitivity, and LIME, which highlight significant facial regions for predictions. Using datasets DB1 and DB2, which consist of full and cropped facial images from social media profiles of individuals with known suicide outcomes, the method achieved 67.93% accuracy with EfficientNetb0 on DB1 and up to 76.6% accuracy with a Bayesian-optimized Support Vector Machine model using ResNet18 features on DB2. This approach provides a less intrusive, accessible alternative to video-based methods and demonstrates the substantial potential for early detection and intervention in mental health care.

Generalized face forgery detection with self-supervised face geometry information analysis network

The emergence of high-quality deepfake facial videos has raised concerns about the security of facial images. Existing face forgery detectors mainly tend to locate a specific forgery region of the human face for detection, which achieves satisfactory performance with known forgery patterns presented in the training set. However, with the continuous advancements in face forgery technology, this approach becomes less reliable with new forgery patterns that emerge. Towards this end, we proposed a novel Self-supervised Face Geometry Information Analysis Network (SF-GAN) method for generalized face forgery detection. SF-GAN effectively leverages the relationships among informative regions based on information theory. Drawing from information theory, regions with high uncertainty tend to contain more valuable information. Our methodology integrates a self-supervised learning mechanism, enabling the precise identification of multiple informative regions. Furthermore, we leverage facial geometry by establishing both explicit and latent geometric relationships through the use of Graph Convolutional Networks (GCNs). Within our framework, facial landmarks and informative regions are depicted as nodes in the GCNs. By analyzing the geometric relationships between the graph of facial landmarks and the graph of informative regions, we are able to identify valid anomalous regions, thereby minimizing uncertainty. Our proposed model gains a comprehensive understanding of common information in face forgery images. Extensive experiments on eight large-scale benchmark datasets: FaceForensics++ (FF++), WildDeepfake (WDF), Celeb-DF v2 (CDF), DeepFake Detection Challenge (DFDC), DFDC preview (DFDC-P), Deepfake Detection (DFD), DeeperForensics-1.0 (DF-1.0) and ForgeryNIR, show that the proposed method is comparable to state-of-the-arts and exhibits better generalizability. Specifically, our SF-GAN, when trained on high-quality FF++ data, achieves an impressive AUC of 76.43% on the CDF dataset.

Dose-Dependent Effects of Botulinum Toxin Type A on Prevention of Postoperative Scars in Various Regions in the Body: A Prospective, Double-Blind Randomized Controlled Trial.

Botulinum toxin type A (BTXA) can improve wound healing and reduce scar formation; however, the exact dose required to prevent postoperative scarring across various anatomical sites remains unclear. This study aimed to investigate the effectiveness and optimal concentrations of BTXA for preventing postoperative scarring across various common surgical sites throughout the body. In this prospective randomized controlled trial, 46 patients with benign skin tumors received injections of 1, 2.5, or 5U/0.1mL of BTXA or 0.9% saline immediately following surgical tumor excision on both sides of the incisions. Follow-ups were conducted at 7days, 15days, and 1, 3, and 6months postoperatively. Patient-reported adverse events and standardized digital photographs were collected. Scar formation was assessed using the modified Stony Brook Scar Evaluation Scale (mSBSES). All 46 patients completed the trial without severe complications. The mSBSES scores were higher in the experimental groups at all follow-ups. The 5U/0.1mL BTXA dose group demonstrated optimal scar prevention at all high-risk sites for scar hyperplasia. No significant difference was observed between the 2.5U/0.1mL and 5U/0.1mL doses for intermediate-risk sites, while 1U/0.1mL dose was sufficient for low-risk sites. Overall, 86.5% of patients were satisfied with their treatments, with 16.3% being very satisfied. Early postoperative BTXA injection can reduce or prevent hypertrophic scarring, with optimal doses ranging from 1 to 5U/0.1mL depending on the surgical site, supporting broader clinical application of BTXA. The effectiveness of different concentrations of botulinum toxin type A (BTXA) in preventing postoperative scarring was compared, expanding the scope of previous research, which focused only on the head, face, and neck regions, to include the trunk and extremity areas. Different optimal injection strategies were determined based on different surgical sites and their risks of developing hypertrophic scars. The study demonstrates that BTXA not only reduces scar formation but also enhances patient satisfaction and reduces postoperative itching and pain, contributing to overall better postoperative outcomes. By establishing the efficacy and optimal dosing of BTXA for various surgical sites, this research supports the potential for broader clinical application of BTXA in aesthetic and reconstructive surgeries. This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Microstructural and mechanical characterizations of weld metal of S960QL ultra high strength steel joints obtained with different multi-pass laying techniques using GMAW

Abstract 15 mm thick ultra-high strength steel plates with 960MPa yield strength were welded using different multi-pass laying techniques (i.e., stringer and weaving beads) with torch manipulation. Weld metals obtained were compared using different mechanical (i.e., micro tensile tests and Vickers hardness maps) and microstructural (i.e., optical microscope, scanning electron microscope, X-ray diffraction, electron backscatter diffraction) characterization techniques. Coarser grains and acicular ferrite were observed in weld metal obtained with weaving pass procedure. There were hardness differences in face and root passes of both weld metals. Yet, hardness values were 19% and 11% higher for face and root regions of the joint obtained by stringer pass procedure, respectively. Fractographs of micro tensile test specimens revealed dimples depicting ductile network structure for both joints.

Management of complicated crown fracture in maxillary incisor using fragment reattachment - 5-year follow-up

Complicated crown-root fractures of maxillary incisors are a relatively common occurrence in cases of trauma to the facial region. Patients with such fractures are in acute pain and usually require emergency care on their first clinical visit. Pain management and restoration of function, esthetics, and phonetics should be the prime objective in handling such patients. The reattachment of fractured tooth fragments is a relatively simple procedure that provides natural esthetics and conservation of tooth structure. This case report describes such a reattachment procedure in a complicated crown-root fracture and its success at 5 years of follow-up.

Spatiotemporal Eye Movement Dynamics Reveal Altered Face Prioritization in Early Visual Processing Among Children With Autism

BackgroundReduced social attention—looking at faces—is one of the most common manifestations of social difficulty in autism that is central to social development. Although reduced social attention is well characterized in autism, qualitative differences in how social attention unfolds across time remains unknown. MethodsWe used a computational modeling (i.e., hidden Markov modeling) approach to assess and compare the spatiotemporal dynamics of social attention in a large, well-characterized sample of children with autism (n = 280) and neurotypical children (n = 120) (ages 6–11) who completed 3 social eye-tracking assays at 3 longitudinal time points (baseline, 6 weeks, 24 weeks). ResultsOur analysis supported the existence of 2 common eye movement patterns that emerged across 3 eye-tracking assays. A focused pattern was characterized by small face regions of interest, which had high a probability of capturing fixations early in visual processing. In contrast, an exploratory pattern was characterized by larger face regions of interest, with a lower initial probability of fixation and more nonsocial regions of interest. In the context of social perception, children with autism showed significantly more exploratory eye movement patterns than neurotypical children across all social perception assays and all 3 longitudinal time points. Eye movement patterns were associated with clinical features of autism, including adaptive function, face recognition, and autism symptom severity. ConclusionsDecreased likelihood of precisely looking at faces early in social visual processing may be an important feature of autism that is associated with autism-related symptomology and may reflect less visual sensitivity to face information.

Real-Time Human Profiling: Unveiling Age, Gender and Emotions Using Deep Learning

This paper introduces the development of a real-time system, which deploys an integrated use of Flask, deep learning, Convolutional Neural Networks (CNNs) and cascade classifier approach to detect age, gender, and emotion from facial images. While its numerous applications—ranging from marketing and medical services to security surveillance—immediately catches the eye, the facial recognition technology is fast becoming the hot topic. Our suggested system aims at absolutely determining the age, gender or emotional state of a person instantaneously in real life. Flask, Python micro web framework, is at the basis of the software, providing the desired functionalities for the exchange of information between the processing engine and the front end. Convolutional Neural Networks (CNNs) which are a part of deep learning for tasks involving feature extraction and classification are the main tool used by most learning algorithms. CNNs are widely used in face recognition systems mainly due to the fact that they perform very well at such tasks as image processing. On the one hand, the model uses cascade classifiers for superior face detection, thereby finding and separating face regions in input images or video streams. Unlike some of the approaches that require heavy computation, these classifiers are computationally light solutions that can run in real-time even on resource- limited devices. The system capacity to identify age, gender, and emotion accurately in real-time is exemplified through: performance evaluation. We have used various means to stress the system and ensure that it is precise and offers timely results over the given period. By means of varied testing stages, we have discovered that the system usually brings high levels of precision and validity for the numerous data sets and trial situations. In this regard, be it differentiating between individuals’ age or readily identifying the exact gender or recognizing nuanced emotional clues, the system performs at the optimum level.

Unveiling the human-like similarities of automatic facial expression recognition: An empirical exploration through explainable ai

AbstractFacial expression recognition is vital for human behavior analysis, and deep learning has enabled models that can outperform humans. However, it is unclear how closely they mimic human processing. This study aims to explore the similarity between deep neural networks and human perception by comparing twelve different networks, including both general object classifiers and FER-specific models. We employ an innovative global explainable AI method to generate heatmaps, revealing crucial facial regions for the twelve networks trained on six facial expressions. We assess these results both quantitatively and qualitatively, comparing them to ground truth masks based on Friesen and Ekman’s description and among them. We use Intersection over Union (IoU) and normalized correlation coefficients for comparisons. We generate 72 heatmaps to highlight critical regions for each expression and architecture. Qualitatively, models with pre-trained weights show more similarity in heatmaps compared to those without pre-training. Specifically, eye and nose areas influence certain facial expressions, while the mouth is consistently important across all models and expressions. Quantitatively, we find low average IoU values (avg. 0.2702) across all expressions and architectures. The best-performing architecture averages 0.3269, while the worst-performing one averages 0.2066. Dendrograms, built with the normalized correlation coefficient, reveal two main clusters for most expressions: models with pre-training and models without pre-training. Findings suggest limited alignment between human and AI facial expression recognition, with network architectures influencing the similarity, as similar architectures prioritize similar facial regions.

Investigating Single Nucleotide Polymorphisms in the Etiology of Cleft Lip and Cleft Palate in the Polish Population.

Cleft lip and/or palate (CL/P) are the most common congenital anomalies in the craniofacial region, leading to morphological and functional disruptions in the facial region. Their etiology involves genetic and environmental factors, with genetics playing a crucial role. This study aimed to investigate the association of four single nucleotide polymorphisms (SNPs)-rs987525, rs590223, rs522616, and rs4714384-with CL/P in the Polish population. We analyzed DNA samples from 209 individuals with CL/P and 418 healthy controls. The impact of SNPs on the presence of CL/P was assessed using multivariate logistic regression. Significant associations were found with rs987525. Specifically, the AC genotype was linked to an increased CL/P risk (odds ratio [OR] = 1.95, 95% confidence interval [CI]: 1.34-2.83, p < 0.001), while the CC genotype was associated with a decreased risk (OR = 0.46, 95% CI: 0.32-0.67, p < 0.001). Rs4714384 was also significant, with the CT genotype correlated with a reduced risk of CL/P (OR = 0.66, 95% CI: 0.46-0.94, p = 0.011). SNPs rs590223 and rs522616 did not show statistically significant associations. These results underscore the role of rs987525 and rs4714384 in influencing CL/P risk and suggest the utility of genetic screening in understanding CL/P etiology.

Experimental and Numerical Research on a Sand Cushion Geotechnical Seismic Isolation System in Strong Earthquakes and Cold Regions

Masonry buildings in high-intensity seismic and cold regions of China face the dual challenges of frost heaving and seismic hazards. To explore the potential of a sand cushion instead of the frozen soil layer to deal with these problems, a cost-effective sand cushion-based Geotechnical Seismic Isolation System (GSI-SC) was developed in this study, where a sand cushion is introduced between the structural foundation and natural soil, while the space around the foundation is backfilled with sand. Shaking table tests on a one-story masonry structure equipped and non-equipped with the GSI-SC system were undertaken to investigate its effectiveness in seismic isolation, where the input wave adopted the north–south component of the EL Centro wave recorded in 1940, and the peak input acceleration (PIA) was set as 0.1 g, 0.2 g, and 0.4 g. It is found that the GSI-SC system significantly reduced the seismic response of the structure, effectively achieving seismic isolation. For a PIA of 0.4 g, the GSI-SC system reduced the acceleration of the roof panel and the inter-story displacement of the structure by 33% and 39%, respectively. Numerical simulations were performed to evaluate the seismic response of buildings equipped and non-equipped with the GSI-SC system. The simulation results matched well with the experimental results, verifying the effectiveness of the newly developed seismic isolation system. The GSI-SC system can provide the potential to reduce frost heave and earthquake disasters for buildings in high-intensity seismic and cold regions.

Utility of facial thermography in the recognition of acute pain in hospitalized cats (Felis catus)

Different clinical conditions have been associated with the presence of pain in animals, so understanding the pathophysiological changes associated with their response is essential in in-hospital clinical monitoring. The objective of this study was to describe the usefulness of facial thermography in the recognition of acute pain in hospitalized cats (Felis catus), for which 71 cats were studied with an average weight of 4.3±1.4 Kg and an age average of 4.4±3.5 years. Facial temperature values were obtained in different region of interest (ROI) and compared according to the values of the Grimace pain scale in cats according to the following subclassification: Group 1, control animals (n=10); Group 2, animals classified with score 0-3 (n=21); Group 3, animals classified with score 4-6 (n=30) and Group 4, animals classified with score 7-10 (n=10). The global average temperature of the facial (F), auricular (A), periocular (PO), nasal (N) and rectal (R) regions was 33.7±1.9; 31.4±3.6; 32.1±0.9; 28.9±4.5 and 38.3±0.8 oC respectively. A difference (p&lt;0.05) was observed between the temperature of A and PO as well as between PO and N, but not between A and N. The present study allowed us to show an increase (p=0.0484) in the temperature mean PO ROI in G4 animals compared to G1 and a correlation with R temperature and peak temperature in the PO region in all groups. It is concluded that the increase in temperature of the periocular region and the nasal plane observed through infrared thermal imaging of the facial surface of hospitalized cats suggests the presence of clinically relevant acute pain. Facial thermography is a safe and non-invasive diagnostic method that complements other methods of identifying pain in cats.

Combating deepfakes: a comprehensive multilayer deepfake video detection framework

AbstractDeepfakes represent a class of synthetic media crafted with the aid of advanced deep learning techniques that exhibit an unparalleled degree of authenticity. The rapid advancement in Artificial Intelligence (AI) has contributed to an increase in the prevalence of deepfakes on the internet, consequently amplifying the spread of misinformation among the public. Consequently, the detection of deepfakes has become a pressing concern. In this context, we put forth a comprehensive framework for deepfake video detection, which is built upon three distinct layers. The first layer, termed as the RGB features extraction layer, is designed to identify potential signs of forgery within the spatial domain of analogous video frames. The second layer, known as the GAN features extraction layer, focuses on the extraction of forgery fingerprints in the high-frequency region. This layer is specifically engineered to detect the fingerprints left by the Generative Adversarial Network (GAN) process in fake videos and the traces of the imaging process in genuine videos. The third and final layer, referred to as the facial region intra-frame inconsistency feature extraction layer, is dedicated to uncovering the anomalies associated with the manipulation process. This is achieved by extracting features from both the inner and outer regions of the manipulated portion of a frame. The extensive experimental evaluations have underscored the superior performance of proposed approach in comparison to existing state-of-the-art methods.