Daily Cosmetic Research Analysis
Three studies advance cosmetic and reconstructive practice: an AI model objectively quantifies smile attractiveness before and after orthognathic surgery using 3D facial contours; a visible–near-infrared image fusion method markedly enhances facial vessel visibility to improve filler injection safety; and a prospective cohort shows one-stage artificial dermis repair yields excellent cosmetic and functional outcomes at great toenail flap donor sites.
Summary
Three studies advance cosmetic and reconstructive practice: an AI model objectively quantifies smile attractiveness before and after orthognathic surgery using 3D facial contours; a visible–near-infrared image fusion method markedly enhances facial vessel visibility to improve filler injection safety; and a prospective cohort shows one-stage artificial dermis repair yields excellent cosmetic and functional outcomes at great toenail flap donor sites.
Research Themes
- AI-driven quantitative assessment of aesthetic outcomes
- Safety engineering for cosmetic filler injections
- Reconstructive techniques optimizing donor-site cosmesis
Selected Articles
1. Automated 3D facial smile attractiveness assessment before and after orthognathic surgery using transfer learning: A preliminary study.
Using 3D contour features and transfer learning, the authors built a web-based model that quantified smile attractiveness changes in 135 orthognathic surgery patients, showing a 25% postoperative improvement. The tool enables rapid, objective assessments for surgical planning and communication.
Impact: This is the first objective, automated 3D assessment of smile attractiveness pre/post orthognathic surgery, providing a reproducible endpoint for aesthetic outcomes.
Clinical Implications: Clinicians can incorporate AI-based quantitative attractiveness scores into shared decision-making, longitudinal outcome tracking, and multi-center benchmarking, while validating across demographics.
Key Findings
- Transfer learning CNN on 3D facial contour features quantified smile attractiveness.
- In 135 patients, postoperative scores increased from 2.62 to 3.27 (≈25% improvement).
- At least 6-month postoperative 3D images were analyzed using a web-based interface.
Methodological Strengths
- Objective 3D imaging (3dMD) with pre/post standardized acquisition.
- Use of machine learning with transfer learning to leverage limited datasets.
Limitations
- Retrospective, single-arm design without external validation or human-rater benchmarks.
- Generalizability to diverse ethnicities and imaging systems not established.
Future Directions: Prospective, multi-center validation with human aesthetic panels; calibration across devices/ethnicities; integration into surgical planning systems and patient-reported outcome measures.
The aesthetic appearance of the mouth during smiling significantly influences facial attractiveness, thereby, making smile analysis crucial in orthodontics, craniofacial surgery, and cosmetic dentistry. Accurate and quantitative evaluation of facial smile attractiveness is crucial for surgical planning and outcome assessment in orthognathic surgery (OGS). In this study, a transfer learning (TL) model using a convolutional neural network (CNN) based on three-dimensional (3D) contour line features was employed to assess facial smile attractiveness before and after OGS. A retrospective cohort study involving 135 patients was conducted between 2021 and 2024 to compare facial smile attractiveness before and after OGS. Using the 3dMD™ face system, 3D facial photos were captured in a natural head position with forward-facing eyes, relaxed facial muscles, and habitual dental occlusion, before and at least 6 months after surgery. Subsequently, 3D contour images were extracted from these photos for web-based automatic facial smile attractiveness assessment using TL with CNN model. Postoperatively, facial smile attractiveness significantly improved, with scores increasing from 2.62 to 3.27, representing a 25% enhancement as determined by the constructed machine learning model. The web-based system offered clinicians a user-friendly interface, providing rapid assessment of results and serving as an effective tool for doctor-patient communication. This study marks the first attempt to automatically evaluate facial smile attractiveness before and after surgery in an objective and quantitative manner, using a machine learning model based on the 3D contours feature map.
2. A novel image fusion approach for visual enhancement of facial vessels in surgical filler injections.
The authors introduce a physical-based fusion of visible and NIR facial images with customized NIR sharpening, producing vessel-highlighted maps that preserve natural color and texture. Quantitative and subjective evaluations showed superior vessel visibility, suggesting potential to improve filler injection safety and precision.
Impact: By enhancing real-time vessel visualization, this method targets the main preventable cause of catastrophic filler complications and could standardize pre-injection mapping.
Clinical Implications: Integration into pre-procedural mapping could reduce inadvertent intravascular injections and guide safer needle/cannula paths; clinical trials are needed to prove complication reduction.
Key Findings
- Simultaneous visible and NIR images are fused after customized sharpening of the NIR channel.
- Quantitative and subjective assessments show clearer vessel depiction with preserved facial color/texture.
- Approach supports accurate vessel localization/marking to enhance filler injection safety.
Methodological Strengths
- Physical-based image fusion with device-synchronized acquisition of visible and NIR spectra.
- Dual evaluation (quantitative metrics and human subjective assessment).
Limitations
- No clinical outcome data on complication rates or procedural efficiency.
- Performance across diverse skin tones, lighting conditions, and devices not detailed.
Future Directions: Prospective clinical studies measuring intravascular event rates; robustness testing across skin types; integration with ultrasound and AR overlays.
In the absence of visual perception of the subcutaneous blood vessels, the performance of facial filling procedures may result in serious complications, such as blindness, cerebral infarction, and potentially fatal outcomes. In order to improve the visibility of facial vessels to ensure the filler injection procedure safe, this paper reports an efficient physical-based image fusion approach that combines simultaneously captured visible and near-infrared (NIR) images to produce vessel-highlighted effects. The enhancement of vessels visibility involves applying a customized sharpening filter to the invisible NIR image prior to merging it with the color facial image. The quantitative and subjective assessments of the fusion images indicate that the suggested approach is capable of efficiently reproducing a clear representation of blood vessels and realistically preserving their color and structural texture. Therefore, this new approach may be utilized to improve the efficiency and accuracy in locating or marking facial blood vessels and enhance the injection safety and precision of surgical filler injections.
3. One-stage prosthetic dermal repair of skin defects in the donor area of the great toe nails flap.
In a prospective cohort of 56 great toenail flap reconstructions, one-stage Pelnac artificial dermis repair of the donor site yielded low pain, minimal complications (1 infection), high aesthetic satisfaction (87/100), and preserved joint motion and sensation over a mean 13.4 months.
Impact: Demonstrates a practical, single-stage strategy that reduces donor-site morbidity while achieving favorable cosmetic and functional outcomes, informing reconstructive planning.
Clinical Implications: Consider one-stage artificial dermis closure of great toenail flap donor sites to minimize morbidity and improve cosmesis, potentially avoiding staged grafting and expediting rehabilitation.
Key Findings
- Prospective follow-up of 56 cases with mean 13.4 months (range 3–30).
- Pain VAS 0.23±0.6, Vancouver scar scale 2.82±1.06; only 1 postoperative infection.
- High aesthetic satisfaction (87.10±5.48/100) and 78.6% normal/near-normal sensory recovery.
- Preserved donor-site joint motion: MTP 66.51±7.38°, DIP 43.21±4.62°.
Methodological Strengths
- Prospective design with systematic outcome assessment.
- Use of validated scales (VAS for pain, Vancouver scar scale) and objective ROM measures.
Limitations
- Single-arm study without control or randomization; potential selection bias.
- Single-center experience limits generalizability.
Future Directions: Comparative trials versus traditional staged grafting; cost-effectiveness and time-to-rehabilitation analyses; long-term durability of cosmetic outcomes.
PURPOSE: This study aimed to evaluate the safety and efficacy of Pelnac artificial skin one-stage surgical direct repair of significant toenail flap donor area defects. METHODS: From March 2020 to May 2023, a total of 56 patients with traumatic finger injuries underwent reconstruction using a great toenail flap combined with iliac bone grafting, along with one-stage artificial skin repair of the great toenail flap. These patients were followed prospectively, and their clinical outcomes were systematically evaluated. RESULTS: The average follow-up was 13.4 months (3 to 30 months). The visual analog scale for pain was 0.23±0.6, and the Vancouver scar scale (VAS) was 2.82±1.06. Among 56 patients, only one case developed postoperative infections. The aesthetic satisfaction of the donor area of the patient's foot was 87.10±5.48 points (out of 100 points). Regarding the sensory recovery, the response "normal or near normal" was obtained in 44 patients (78.6 %). The maximum active mobility of the first metatarsophalangeal joint and the distal interphalangeal joint in the donor area was 66.51±7.38°and 43.21±4.62°, respectively. CONCLUSIONS: Given its low donor-site morbidity and favorable cosmetic and functional outcomes, one-stage reconstruction of donor site defects using artificial dermis represents an effective and clinically viable treatment option.