Search Results (168)

Introduction: This manuscript addresses the limitations of traditional orthognathic surgery in achieving both functional and aesthetic correction in patients with Class II malocclusion and severe mandibular retrusion. Current techniques often struggle to simultaneously address mandibular deficiency and inadequate transverse dimension, leading to unsatisfactory outcomes. Methods: Seven male patients underwent bimaxillary osteotomy with mandibular advancement. A novel surgical plate, Implate, was used, which was designed to facilitate precise osteotomy and stabilization. Pre-surgical planning included CBCT scanning, 3D modeling, and surgical simulation. Postoperative assessments included clinical examinations, CT and OPT scans. Results: Implate successfully addressed the challenges of conventional techniques, minimizing the formation of bony steps and achieving a more harmonious facial profile. The minimally invasive procedure, with careful periosteal and muscle management, contributed to stable outcomes, and no complications were reported. At the 6-month follow-up, OPT analysis showed a mean mandibular width increase of 18.1 ± 6.2 mm and vertical ramus height gains of 6.0 ± 3.1 mm (left) and 5.8 ± 1.7 mm (right). Conclusions: According to our preliminary experience, the integration of Implate into surgical practice offers a significant improvement in treating complex Class II malocclusions. By simultaneously correcting mandibular retrusion and width while minimizing complications, Implate provides a superior solution compared to traditional methods. This innovative approach highlights the potential of combining advanced surgical techniques with personalized 3D-printed implants to achieve optimal functional and aesthetic outcomes. Further prospective studies with controls and longer follow-up are needed to validate the efficacy and reproducibility of Implate in wider clinical use. Full article

Any failure in frontonasal development can lead to malformations at the middle facial region, such as frontonasal dysplasia, midfacial clefts, and hyper/hypotelorism. Various environmental factors influence morphogenesis through epigenetic regulations, including the action of noncoding microRNAs (miRNAs). However, it remains unclear how miRNAs are involved in the frontonasal development. In our analysis of publicly available miRNA-seq and RNA-seq datasets, we found that miR-28a-5p, miR-302a-3p, miR-302b-3p, and miR-302d-3p were differentially expressed in the frontonasal process during embryonic days 10.5 to 13.5 (E10.5–E13.5) in mice. Overexpression of these miRNAs led to a suppression of cell proliferation in cultured mouse embryonic frontonasal mesenchymal (MEFM) cells as well as in O9-1 cells, a cranial neural crest cell line. Through advanced bioinformatic analyses and miRNA-gene regulation assays, we identified that miR-28a-5p regulated a total of 25 genes, miR-302a-3p regulated 23 genes, miR-302b-3p regulated 22 genes, and miR-302d-3p regulated 20 genes. Notably, the expression of miR-302a/b/d-3p—unlike miR-28a-5p—was significantly upregulated by excessive exposure to all-trans retinoic acid (atRA) that induces craniofacial malformations. Inhibition of these miRNAs restored the reduced cell proliferation caused by atRA by normalizing the expression of target genes associated with frontonasal anomalies. Therefore, our findings suggest that miR-302a/b/d-3p plays a crucial role in the development of frontonasal malformations. Full article

Deepfake detection has become a critical issue due to the rise of synthetic media and its potential for misuse. In this paper, we propose a novel approach to deepfake detection by combining video frame analysis with facial microexpression features. The dual-branch fusion model utilizes a 3D ResNet18 for spatiotemporal feature extraction and a transformer model to capture microexpression patterns, which are difficult to replicate in manipulated content. We evaluate the model on the widely used FaceForensics++ (FF++) dataset and demonstrate that our approach outperforms existing state-of-the-art methods, achieving 99.81% accuracy and a perfect ROC-AUC score of 100%. The proposed method highlights the importance of integrating diverse data sources for deepfake detection, addressing some of the current limitations of existing systems. Full article

Neuro-Affective Intelligence (NAI) integrates neuroscience, psychology, and artificial intelligence to support neurodivergent children through personalized Child–Machine Interaction (CMI). This paper presents an adaptive neuro-affective system designed to enhance engagement in children with neurodevelopmental disorders through serious games. The proposed framework incorporates real-time biophysical signals—including EEG-based concentration, facial expressions, and in-game performance—to compute a personalized engagement score. We introduce a novel mechanism, Bayesian Immediate Feedback Learning (BIFL), which dynamically selects visual, auditory, or textual stimuli based on real-time neuro-affective feedback. A multimodal CNN-based classifier detects mental states, while a probabilistic ensemble merges affective state classifications derived from facial expressions. A multimodal weighted engagement function continuously updates stimulus–response expectations. The system adapts in real time by selecting the most appropriate cue to support the child’s cognitive and emotional state. Experimental validation with 40 children (ages 6–10) diagnosed with Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD) demonstrates the system’s effectiveness in sustaining attention, improving emotional regulation, and increasing overall game engagement. The proposed framework—combining neuro-affective state recognition, multimodal engagement scoring, and BIFL—significantly improved cognitive and emotional outcomes: concentration increased by 22.4%, emotional engagement by 24.8%, and game performance by 32.1%. Statistical analysis confirmed the significance of these improvements ($p<0.001$, Cohen’s $d>1.4$). These findings demonstrate the feasibility and impact of probabilistic, multimodal, and neuro-adaptive AI systems in therapeutic and educational applications. Full article

(1) Background: Esthetic regenerative medicine is increasingly in demand for facial and neck rejuvenation due to its proven efficacy, safety profile, and minimal downtime. This study aimed to evaluate the role of standardized assessment tools in optimizing the outcomes of non-invasive regenerative esthetic technologies, both during the treatment course and in follow-up. (2) Methods: A literature review of the main articles published in peer-reviewed journals was conducted to identify high-quality studies addressing the use of validated esthetic scales and questionnaires (patient-reported outcomes) for evaluating the effectiveness of non-invasive regenerative treatments for the face and neck using accessible clinical tools such as photographs and 3D facial scanning. (3) Results: Clinician-reported outcomes (CROs) can be collected using standardized and reproducible photographic documentation and facial scans. The esthetic scales and classifications target both specific facial areas (e.g., upper third, perioral, periorbital) and overall skin appearance. Furthermore, advanced software allows overlay facial scan analysis and wrinkle mapping for precise quantification of improvements. In addition to objective CROs, patient-reported outcomes (PROs) offer essential insights into perceived esthetic changes, satisfaction, and emotional well-being, completing a multidimensional evaluation of treatment efficacy. (4) Conclusions: Standardized evaluation protocols based on accessible tools such as clinical photographs, 3D facial scans, and validated PRO questionnaires are essential for guiding effective, personalized regenerative treatments. Their integration into routine practice enhances clinical decision-making and patient satisfaction. While advanced tools like dermal probes may further refine assessments, they require specific expertise and resources and may be less practical for daily clinical use. Full article

Background/Objectives: This study aimed to explore the functional implications of occlusal changes during clear aligner treatment (CAT) to (a) analyze occlusal changes throughout CAT and the extent of post-treatment occlusal recovery; (b) assess the relationship between post-treatment occlusion and masticatory performance; (c) investigate whether case complexity, facial biotype, and type of malocclusion influence occlusal adaptation and functional outcomes; and (d) evaluate the presence and progression of signs or symptoms of TMDs in patients undergoing CAT. Methods: This longitudinal cohort pilot study included 42 individuals who underwent CAT. Occlusion was evaluated at three timepoints: before treatment (T0), at treatment completion (T1), and three months after with night-only aligner use (T2). Masticatory performance was assessed using a two-colored chewing gum test analyzed through colorimetric software. TMD signs/symptoms were assessed using the Diagnostic Criteria for TMD [DC/TMD]. Statistical analysis used non-parametric tests. Results: A significant decrease in occlusal contact area was observed during active CAT [p = 0.016], which partially recovered at follow-up. Individuals with normal facial proportions (normodivergent) showed more anterior contacts at T1 compared to hyperdivergent individuals [p = 0.013]. Masticatory performance remained stable between T1 and T2 [p = 0.528]. A weak negative correlation was found between posterior contact number and performance score at T1 [r = −0.378, p < 0.05], suggesting that more contacts may be linked to better chewing. No TMD signs or symptoms were detected at any timepoint. Conclusions: Although CAT temporarily reduces occlusal contact area, it does not negatively impact chewing efficiency or trigger TMD symptoms. These findings support the functional safety of CAT when treatment is properly planned and monitored. Full article

Objectives: A randomized, double-blind, placebo-controlled intervention study aimed to evaluate whether hawthorn fruit (HF) supplementation can influence facial skin phenotypes and leukocyte telomere length (TL) and whether these effects differ by genetic polymorphisms related to TL. Participants/Methods: Among 41 male and female adults aged 25–75 years who participated in the study, 36 completed initial and follow-up examinations over 6 months. The HF supplementation group (n = 17) was instructed to take a powdered HF supplement (900 mg/day), while controls (n = 19) were to take a cornstarch placebo (900 mg/day). Facial skin phenotypes, including pigmentation, pores, hydration, wrinkles, and elasticity, were measured before and after the intervention, and changes in these phenotype scores were calculated. Sequencing of telomerase reverse transcriptase (TERT) polymorphisms, such as rs7705526 (C>A) and rs2853669 (A>G), was conducted. Results: The HF supplementation group exhibited significantly improved hydration scores compared to the control group; the mean changes (follow-up measure—baseline measure) [standard deviation] in hydration scores over 6 months were 1.71 [8.18] and −3.00 [8.42] for the supplementation group and control group, respectively (p < 0.05) (Cohen’s d = 0.57). However, changes in other phenotypes and leukocyte TL were similar between groups. The genotype-specific analysis revealed that the improvement of hydration state was most noticeable among carriers with the CC genotype of rs7705526 (p < 0.05) (Cohen’s d = 1.50) and that the HF supplementation group exhibited reduced wrinkle scores while the control group showed increased scores among carriers of the AA genotype of rs2853669 (p < 0.05) (Cohen’s d = 1.40). In correlation analysis for all participants, hydration scores were positively correlated with leukocyte TL (Spearman correlation coefficient: 0.36; p < 0.05). Conclusions: These findings suggest that HF consumption may have potential anti-skin-aging effects. Future studies may need to elucidate the biological mechanisms underlying these effects. Full article

The zygomatic major and zygomatic minor muscles play a central role in facial expression, particularly in generating the smile, one of the most essential forms of human nonverbal communication. While their function is widely recognized, the anatomical variability in these muscles remains underexplored in both clinical and surgical settings. This review provides a comprehensive, interdisciplinary analysis of the zygomaticus musculature, integrating classical anatomical insights with recent advances in imaging, developmental biology, and artificial intelligence-based analysis. By examining data from cadaveric dissection, MRI, ultrasonography, and 3D photogrammetry, we identify key morphological differences with potential clinical relevance. A novel five-type morphological classification is proposed, based on differences in the number of muscle bellies (i.e., belly number), accessory structures, insertion patterns, and population-based variation. This classification aims to offer a more functionally relevant and clinically applicable framework for use in facial surgery, aesthetic procedures, and forensic reconstruction. By moving beyond the simplistic binary categorizations that have historically defined zygomaticus morphology, this review highlights the need for a personalized approach to facial anatomy, tailored to individual morphological variation. The proposed framework may assist in refining surgical planning, improving outcomes in facial reanimation, and enhancing diagnostic accuracy in both radiological assessment and preoperative planning. By moving beyond traditional binary categorizations, this review highlights the need for a personalized approach to facial anatomy, tailored to individual morphological variations. The proposed framework may assist in refining surgical planning, improving outcomes in facial reanimation, and advancing diagnostic precision in facial imaging. A total of 75 peer-reviewed articles were selected based on a targeted search in PubMed, Scopus, and Web of Science (1995–2024). Full article

Body Mass Index (BMI) is a crucial indicator for assessing human obesity and overall health, providing valuable insights for applications such as health monitoring, patient re-identification, and personalized healthcare. Recently, several data-driven methods have been developed to estimate BMI using 2D and 3D features extracted from facial and body images or RGB-D data. However, current research faces challenges such as the incomplete consideration of anthropometric features, the neglect of multiplex networks, and low-BMI-estimation performance. To address these issues, this paper proposes three 3D anthropometric features, one 2D anthropometric feature, and a deep feature extraction method to comprehensively consider anthropometric features. Additionally, a BMI estimation method based on a multiplex network is introduced. In this method, three types of features are extracted by constructing a multichannel network, and BMI estimation is performed using Kernel Ridge Regression (KRR). The experimental results demonstrate that the proposed method significantly outperforms state-of-the-art methods. By incorporating symmetry into our analysis, we can uncover deeper patterns and relationships within complex systems, leading to a more comprehensive understanding of the phenomena under investigation. Full article

Autism Spectrum Disorder (ASD) poses significant challenges in diagnosis due to its diverse symptomatology and the complexity of early detection. Atypical gait and gesture patterns, prominent behavioural markers of ASD, hold immense potential for facilitating early intervention and optimising treatment outcomes. These patterns can be efficiently and non-intrusively captured using modern computational techniques, making them valuable for ASD recognition. Various types of research have been conducted to detect ASD through deep learning, including facial feature analysis, eye gaze analysis, and movement and gesture analysis. In this study, we optimise a dual-stream architecture that combines image classification and skeleton recognition models to analyse video data for body motion analysis. The first stream processes Skepxels—spatial representations derived from skeleton data—using ConvNeXt-Base, a robust image recognition model that efficiently captures aggregated spatial embeddings. The second stream encodes angular features, embedding relative joint angles into the skeleton sequence and extracting spatiotemporal dynamics using Multi-Scale Graph 3D Convolutional Network(MSG3D), a combination of Graph Convolutional Networks (GCNs) and Temporal Convolutional Networks (TCNs). We replace the ViT model from the original architecture with ConvNeXt-Base to evaluate the efficacy of CNN-based models in capturing gesture-related features for ASD detection. Additionally, we experimented with a Stack Transformer in the second stream instead of MSG3D but found it to result in lower performance accuracy, thus highlighting the importance of GCN-based models for motion analysis. The integration of these two streams ensures comprehensive feature extraction, capturing both global and detailed motion patterns. A pairwise Euclidean distance loss is employed during training to enhance the consistency and robustness of feature representations. The results from our experiments demonstrate that the two-stream approach, combining ConvNeXt-Base and MSG3D, offers a promising method for effective autism detection. This approach not only enhances accuracy but also contributes valuable insights into optimising deep learning models for gesture-based recognition. By integrating image classification and skeleton recognition, we can better capture both global and detailed motion patterns, which are crucial for improving early ASD diagnosis and intervention strategies. Full article

Investigating how facial movements can be used to characterize and quantify speech is important, in particular, to aid those suffering from motor control speech disorders. Here, we sought to investigate how facial action units (AUs), previously used to classify human expressions and emotion, could be used to quantify and understand unimpaired human speech. Fourteen (14) adult participants (30.1 ± 7.9 years old), fluent in English, with no speech impairments, were examined. Within each data collection session, 6 video trials per participant per phoneme were acquired (i.e., 102 trials total/phoneme). The participants were asked to vocalize the vowels /æ/, /ɛ/, /ɪ/, /ɒ/, and /ʊ/; the consonants /b/, /n/, /m/, /p/, /h/, /w/, and /d/; and the diphthongs /eI/, /ʌɪ/, /i/, /a:/, and /u:/. Through the use of Python Py-Feat, our analysis displayed the AU contributions for each phoneme. The important implication of our methodological findings is that AUs could be used to quantify speech in populations with no speech disability; this has the potential to be broadened toward providing feedback and characterization of speech changes and improvements in impaired populations. This would be of interest to persons with speech disorders, speech language pathologists, engineers, and physicians. Full article

Background: Macrocephaly can be a component manifestation of several monogenic conditions, in association with intellectual disability/developmental delay (ID/DD) behaviour abnormalities, including autism spectrum disorders (ASD), and variable additional features. On the other hand, idiopathic ASD can present with developmental delay and macrocephaly. Methods: We carried out a retrospective analysis of a cohort of 78 patients who were tested from February 2017 to December 2024 by high-throughput sequencing of a panel of 27 genes (ABCC9, AKT1, AKT2, AKT3, BRWD3, DIS3L2, DNMT3A, EZH2, GPC3, GPC4, HERC1, MED12, MTOR, NFIA, NFIX, NSD1, PDGFRB, PIK3CA, PIK3R1, PIK3R2, PPP2R1A, PPP2R5D, PTEN, RAB39B, RNF135, SETD2, and TBC1D7) because of neurodevelopmental impairment, including ID/DD, ASD/behaviour abnormalities associated with macrocephaly, mimicking to a large extent idiopathic ASD. Results: Pathogenic variants leading to the diagnosis of monogenic conditions were detected in 22 patients (28%), including NSD1 (2), PTEN (16), and PPP2R5D (4). Distinctive of the PTEN-associated phenotype were true macrocephaly (100%), ASD or behaviour abnormalities (92%), mild/borderline ID (79%), and no facial dysmorphisms. Typical of the PPP2R5D-associated phenotype were relative macrocephaly (75%), a few unspecific peculiar facial characteristics (50%), and a more variable presentation of the neurodevelopmental phenotype. Conclusions: Pathogenic variants in PTEN and PPP2R5D are the most recurrent gene mutations in a patient-oriented procedure for the genetic diagnosis of apparently idiopathic ASD and behaviour abnormalities associated with macrocephaly. The clinical applicability of the presented diagnostic strategy is discussed. Full article

The most common aftereffect of severe burns in patients is hypertrophic scarring. Hypertrophic scars typically form following severe burns; it refers to excessive collagen production in the dermal layer during the healing process, resulting in an abnormal raised scar. Currently, practical treatments for suppressing hypertrophic scars include laser therapy, pressure therapy, and the application of silicone sheets for moisture retention. The most extensively used treatment involves compression therapy using specially designed garments for the affected areas. However, this method has limitations when applied to curved surfaces like the face. To address this issue, three-dimensional (3D) scanning and 3D printing techniques have been actively developed for face masks and have shown promising clinical results. Unfortunately, current facial masks under development lack a sensor system to measure pressure, making it difficult to ensure consistent and appropriate pressures during clinical trials. In this study, we have developed a burn pressure mask capable of real-time pressure monitoring. The facial mask developed in this study utilizes an FSR-type sensor to measure the pressure applied to the skin. We have also embedded electrical wires within the mask to enhance its comfort and wearability. For this study, two patients wore the facial mask with real-time pressure measurement capabilities for 4 weeks in 12 h per day on average. We evaluated whether the mask maintained the appropriate pressure range (15–25 mmHg) throughout the clinical trial and whether it effectively inhibited scar formation. Through the analysis of recorded pressure signal data, we confirmed that the patients consistently maintained the appropriate pressure while wearing the mask during the clinical trial. Additionally, we observed significant differences in skin moisture levels, transepidermal water loss, and scar thickness before and after the experiment. These findings suggest that the facial mask, featuring real-time monitoring capabilities, effectively prevents the formation of hypertrophic scars. Full article

Evaluating designed objects in real-world use cases enables usability optimization. For functional objects such as face masks, the mask must fit the user initially and continue to fit during movements such as talking. This paper describes methodology development for dynamic fit analysis of face masks using 3D head scans. Participants were scanned while wearing Basic, Cup, and Petal model masks before and after reading a passage aloud and completed surveys across eight fit dimensions. Face and mask measurements were virtually extracted from the head scans for quantitative fit analysis, and mask overlays were inspected for qualitative fit analysis. Four of eleven facial measurements changed significantly from closed to open-mouth posture while the nasal dorsum was identified as a stable landmark and served as a reference to define a mask shift metric. The mask shift was compared to the survey results for the model masks, with the Cup design fitting best and the Petal design rated as most comfortable. Poor fit modes identified from mask overlays were fabric buckling, compressed nose and ears, and gapping between the mask and facial features. This methodology can be implemented during the analysis stage of the iterative design process and complements static fit analyses. Full article

Background/Objectives: Crisponi/cold-induced sweating syndrome 1 (CISS1/CISS, MIM#272430) is a genetic disorder due to biallelic variants in CRFL1 (MIM*604237). The related phenotype is mainly characterized by abnormal thermoregulation and sweating, facial muscle contractions in response to tactile and crying-inducing stimuli at an early age, skeletal anomalies (camptodactyly of the hands, scoliosis), and craniofacial dysmorphisms, comprising full cheeks, micrognathia, high and narrow palate, low-set ears, and a depressed nasal bridge. The condition is associated with high lethality during the neonatal period and can benefit from timely symptomatic therapy. Methods: We collected frontal images of all patients with CISS1/CISS published to date, which were analyzed with Face2Gene (F2G), a machine-learning technology for the facial diagnosis of syndromic phenotypes. In total, 75 portraits were subdivided into three cohorts, based on age (Cohort 1 and 2) and the presence of the typical facial trismus (Cohort 3). These portraits were uploaded to F2G to test their suitability for facial analysis and to verify the capacity of the AI tool to correctly recognize the syndrome based on the facial features only. The photos which passed this phase (62 images) were fed to three different AI algorithms—DeepGestalt, Facial D-Score, and GestaltMatcher. Results: The DeepGestalt algorithm results, including the correct diagnosis using a frontal portrait, suggested a similar facial phenotype in the first two cohorts. Cohort 3 seemed to be highly differentiable. The results were expressed in terms of the area under the curve (AUC) of the receiver operating characteristic (ROC) curve and p Value. The Facial D-Score values indicated the presence of a consistent degree of dysmorphic signs in the three cohorts, which was also confirmed by the GestaltMatcher algorithm. Interestingly, the latter allowed us to identify overlapping genetic disorders. Conclusions: This is the first AI-powered image analysis in defining the craniofacial contour of CISS1/CISS and in determining the feasibility of training the tool used in its clinical recognition. The obtained results showed that the use of F2G can reveal valid support in the diagnostic process of CISS1/CISS, especially in more severe phenotypes, manifesting with facial contractions and potentially lethal consequences. Full article