3D Face Scans Research Articles

An automated design pipeline for transparent facial orthoses: A clinical study

Statement of problemTransparent facial orthoses (TFOs) are commonly used for the treatment of craniomaxillofacial trauma and burns to prevent hypertrophic and keloid scarring. A TFO is typically customized to the patient’s facial contours and relies on a precise fit to ensure good rehabilitative performance. A smart method of TFO design and manufacture is needed which does not require an experienced prosthetist, allowing for rapidly produced, well-fitting TFOs. Whether the rapid application reduces the final level of patient scarring is unclear. PurposeThe purpose of this clinical study was to determine whether a scalable, automated design-through-manufacture pipeline for patient specific TFO fabrication would be successful. Material and methodsThe automated pipeline received a 3-dimensional (3D) facial scan captured from a depth sensitive mobile phone camera. The scan was cleaned, aligned, and fit to a template mesh, with a known connectivity. The resultant fitted scan was passed into an automated design pipeline, outputting a 3D printable model of a custom TFO. The TFOs were fabricated with 3D printing and were both physically and digitally evaluated to test the fidelity of a digital fit testing system. ResultsA total of 10 individuals were scanned with 5 different scanning technologies (STs). All scans were passed through an automated fitting pipeline and categorized into 2 groups. Each ST was digitally fitted to a ground truth scan. In this manner, a Euclidean distance map was built to the actual facial geometry for each scan. Heatmaps of 3D Euclidean distances were made for all participant faces. ConclusionsThe ability to automatically design and manufacture a custom fitted TFO using commercially available 3D scanning and 3D printing technology was successfully demonstrated. After considering equipment size and operational personnel requirements, vat polymerization (VP) technology was found to be the most promising route to TFO manufacture.

Development of a customized mask retainer for improving the fit performance of surgical masks.

This study introduces a customized mask retainer to improve the fit performance of surgical masks using various advanced digital techniques. The participant's 3D face scans with and without a surgical mask were taken by using a smartphone. The mask retainer was designed using the 3D face scan data based on the facial anthropometric landmarks. The fitting was inspected and adjusted using the masked face scan data. The retainer was fabricated using a 3D printer. The effectiveness of the retainer on the augmentation of the fit of the surgical mask was tested according to the Chinese Standard (GB 19083-2010). A questionnaire was used to assess the effect of wearing surgical masks with and without retainers and N95 respirators on subjective perception of discomfort. The effectiveness test of the retainer on the augmentation of the fit performance showed a better than 25-fold increase in the overall fit factor, meeting the fit requirement for KN95 respirators in China. The subjective perception of discomfort of wearing N95 was significantly greater than surgical mask with and without retainers. The fit factor results indicated that by using the retainer, the overall fit factors and that of each exercise significantly increased compared to that of the group with the surgical mask alone. And compared with N95, the surgical mask with the retainer significant improved comfort. The surgical mask with the retainer can provide an alternative of personal protective equipment for healthcare workers.

Detecting 3D syndromic faces as outliers using unsupervised normalizing flow models

Many genetic syndromes are associated with distinctive facial features. Several computer-assisted methods have been proposed that make use of facial features for syndrome diagnosis. Training supervised classifiers, the most common approach for this purpose, requires large, comprehensive, and difficult to collect databases of syndromic facial images. In this work, we use unsupervised, normalizing flow-based manifold and density estimation models trained entirely on unaffected subjects to detect syndromic 3D faces as statistical outliers. Furthermore, we demonstrate a general, user-friendly, gradient-based interpretability mechanism that enables clinicians and patients to understand model inferences. 3D facial surface scans of 2471 unaffected subjects and 1629 syndromic subjects representing 262 different genetic syndromes were used to train and evaluate the models. The flow-based models outperformed unsupervised comparison methods, with the best model achieving an ROC-AUC of 86.3% on a challenging, age and sex diverse data set. In addition to highlighting the viability of outlier-based syndrome screening tools, our methods generalize and extend previously proposed outlier scores for 3D face-based syndrome detection, resulting in improved performance for unsupervised syndrome detection.

A complete digital approach for facially generated full arch diagnostic wax up, guided surgery, and implant-supported interim prosthesis by integrating 3D facial scanning, intraoral scan and CBCT.

Continuous innovation in digital dental technology offers new prospects for creating a complete virtual environment. The technique described adds a facial approach to the conventional digital workflow by incorporating 3D face scans to cone beam computed tomography and intraoral scans. Using this workflow, clinicians can obtain a complete virtual patient for facially generated diagnostic wax up and plan and implement a predictable implant placement and interim prosthesis. This technique provides a full digital workflow for restoratively-driven computer-aided implant planning, guided surgery, and 3D printing of an interim complete-arch fixed implant-supported prosthesis.

Anthropometric Comparison of 3-Dimensional Facial Scan Taken With a Low-Cost Facial Scanner With Cone-Beam Computed Tomography Scan.

The aim of this study was to evaluate the accuracy of 3-dimensional (3D) facial scans taken with a low-cost facial scanner compared with cone-beam computed tomography (CBCT). Twenty-five patients had their CBCT scan and 3D facial scan taken on the same day. Facial scans were taken with a low-cost facial scanner (Bellus3D, ARC-1 scanner) in an upright position. The facial scans were imported into Invivo5 software and were integrated with the corresponding CBCT scans. Then, 16 soft tissue landmarks were identified on the CBCT scans and the 3D-integrated facial scans. The 6 vertical, 7 horizontal, 10 oblique linear, and 11 angular anthropometric measurements were obtained and compared between the CBCT scans and 3D-integrated facial scans using paired t test and Bland-Altman plots. The differences between CBCT scans and 3D-integrated facial scans showed no statistical significance except for 2 vertical measurements. Bland-Altman plots showed that all anthropometric measurements were within the limit of agreement. The differences between CBCT scans and 3D-integrated facial scans were <1.5mm or 1.5 degrees except for 2 vertical measurements. Three-dimensional facial scans taken with facial scanner showed a clinical acceptance when compared with CBCT scans.

Evaluation of soft tissue prediction accuracy for orthognathic surgery with skeletal class III malocclusion using maxillofacial regional aesthetic units.

This study aimed to evaluate the soft tissue prediction accuracy of patients undergoing orthognathic surgery to correct skeletal class III malocclusion using maxillofacial regional aesthetic units. Pre- and postoperative cone-beam computed tomography (CBCT) and 3D facial scans were taken for 58 patients who had undergone orthognathic surgery. The preoperative 3D facial scan was integrated with the preoperative CBCT using ProPlan CMF software. The software simulated the surgery and generated postoperative soft tissue prediction. The simulated 3D facial scan was then compared with the actual 3D facial scan obtained at least 6months after the surgery by the maxillofacial regional aesthetic units and the facial soft tissue landmark points. The anatomical regions of the upper lip, lower lip, chin, right external buccal and left external buccal prediction were above 2.0mm. As for the soft tissue landmarks, at chl, chr, ls, stm and li, the position of predicted scan was higher than that of the actual postoperative scan. The accuracy of 3D soft tissue predictions using ProPlan CMF software in Skeletal III patients was clinically satisfactory according to maxillofacial regional aesthetic units combined with facial soft tissue landmark points. However, the accuracy of prediction still needed improvement in some areas. The accuracy of soft tissue prediction can be analyzed more clearly through maxillofacial regional aesthetic units so that clinicians have a deeper understanding of the use of the software to predict soft tissue change after orthognathic surgery.

Meta-learning-based adversarial training for deep 3D face recognition on point clouds

Recently, deep face recognition using 2D face images has made great advances mainly due to the readily available large-scale face data. However, deep face recognition using 3D face scans, especially on point clouds, has been far from fully explored. In this paper, we propose a novel meta-learning-based adversarial training (MLAT) algorithm for deep 3D face recognition (3DFR) on point clouds. It consists of two alternate modules: adversarial sample generating for 3D face data augmentation and meta-learning-based deep network training. In the first module, adversarial samples of given 3D face scans are dynamically generated based on current deep 3DFR model. In the second module, a meta-learning framework is designed to avoid the performance decrease caused by the generated adversarial samples. Overall, MLAT algorithm combines the adversarial sample generating and meta-learning-based network training in a uniform framework, in which adversarial samples and network parameters are optimized alternately. Thus, it can continuously generate diverse and suitable adversarial samples, and then the meta-learning framework can further improve the accuracy of 3DFR model. Comprehensive experimental results show that the proposed approach consistently achieves competitive rank-one recognition accuracies on the BU-3DFE (100%), Bosphorus (99.78%), BU-4DFE (98.02%) and FRGC v2 (98.01%) database, and thereby substantiate its superiority.

Accuracy of Three-Dimensional Soft-Tissue Prediction Considering the Facial Aesthetic Units Using a Virtual Planning System in Orthognathic Surgery.

Virtual surgical planning (VSP) is commonly used in orthognathic surgery. A precise soft-tissue predictability would be a helpful tool, for determining the correct displacement distances of the maxilla and mandible. This study aims to evaluate the soft-tissue predictability of the VSP software IPS CaseDesigner® (KLS Martin Group, Tuttlingen, Germany). Twenty patients were treated with bimaxillary surgery and were included in the study. The soft-tissue simulation, done by the VSP was exported as STL files in the engineering software Geomagic Control XTM (3D systems, RockHill, SC, USA). Four months after surgery, a 3D face scan of every patient was performed and compared to the preoperative simulation. The quality of the soft-tissue simulation was validated with the help of a distance map. This distance map was calculated using the inter-surface distance algorithm between the preoperative simulation of the soft-tissue and the actual scan of the postoperative soft-tissue surface. The prediction of the cranial parts of the face (upper cheek, nose, upper lip) was more precise than the prediction of the lower areas (lower cheek, lower lip, chin). The percentage of correctly predicted soft-tissue for the face in total reached values from 69.4% to 96.0%. The VSP system IPS CaseDesigner® (KLS Martin Group; Tuttlingen, Germany) predicts the patient’s post-surgical soft-tissue accurately. Still, this simulation has to be seen as an approximation, especially for the lower part of the face, and continuous improvement of the underlying algorithm is needed for further development.

Measuring 3D facial displacement of increasing smile expressions

Following paralysis, facial reanimation surgery can restore movement by nerve and/or muscle transfer within the face. The subtleties of lip and cheek movements during smiling are important aspects in assessing reanimation. This study quantifies average 3D movement vectors of the face during smiling based on the diverse Binghamton University 3D facial expression database to yield normative measures of lip and cheek movement. The analysis was conducted on 100 subjects with 3D facial scans in a neutral and 4 increasing smile intensities, as well as associated labeled 3D landmark points. Each subject set of 3D scans was rigidly registered to measure average displacement vectors (distance, azimuth, and elevation) between the neutral and happy expressions. The average lip commissure displacement was found to be 9.2, 11.4, 13.5, and 16.0 mm for increasing smile levels 1-4, respectively. Similarly, the average commissure azimuth angle across all 4 smile levels is ∼44 ± 21 degrees, and the average elevation angle across all 4 smile levels is ∼37 ± 15 degrees. The maximum cheek displacement from the neutral expression was 4.5, 5.7, 6.8, and 7.9 mm for the smile levels 1-4, respectively. The average cheek movement azimuth angle is outward (increasing 1-13 degrees), and the elevation angle is upward (increasing 51-59 degrees) from the face. These data quantifying 3D lip and cheek smile displacements improve the understanding of facial movement and may be applicable to future assessment/planning of facial reanimation surgeries.

Personalised 3D printed respirators for healthcare workers during the COVID-19 pandemic.

Widespread issues in respirator availability and fit have been rendered acutely apparent by the COVID-19 pandemic. This study sought to determine whether personalized 3D printed respirators provide adequate filtration and function for healthcare workers through a Randomized Controlled Trial (RCT). Fifty healthcare workers recruited within NHS Lothian, Scotland, underwent 3D facial scanning or 3D photographic reconstruction to produce 3D printed personalized respirators. The primary outcome measure was quantitative fit-testing to FFP3 standard. Secondary measures included respirator comfort, wearing experience, and function instrument (R-COMFI) for tolerability, Modified Rhyme Test (MRT) for intelligibility, and viral decontamination on respirator material. Of the 50 participants, 44 passed the fit test with the customized respirator, not significantly different from the 38 with the control (p = 0.21). The customized respirator had significantly improved comfort over the control respirator in both simulated clinical conditions (p < 0.0001) and during longer wear (p < 0.0001). For speech intelligibility, both respirators performed equally. Standard NHS decontamination agents were able to eradicate 99.9% of viral infectivity from the 3D printed plastics tested. Personalized 3D printed respirators performed to the same level as control disposable FFP3 respirators, with clear communication and with increased comfort, wearing experience, and function. The materials used were easily decontaminated of viral infectivity and would be applicable for sustainable and reusable respirators.

Integration accuracy of craniofacial cone-beam computed tomography images with three-dimensional facial scans according to different registration areas.

To evaluate the integration accuracy of cone-beam computed tomography (CBCT) images with three-dimensional (3D) facial scans according to different registration areas. Twenty-five patients (14 males and 11 females), with a mean age of 19.0 ± 11.3 years, were included in this study. Each patient underwent CBCT and facial scans on the same day in an upright position. The facial scans were integrated with the corresponding soft-tissue images of CBCT scans. Three methods were used to integrate the two imaging modalities based on the facial regions scanned: R1, only the forehead and nasal bridge area were included; R2, the right and left malar area were included; and R3, the forehead, nasal bridge, and malar areas were included. The integration accuracy between the facial scans and CBCT images was evaluated by color-mapping methods and average surface distances, calculated by measuring the 3D distances between the surface points on the two superimposed images. The average surface differences between facial scans and CBCT images were less than 1.0 mm in all three methods. The R3 method showed fewer differences between the facial scans and CBCT images than the other methods did. Facial scans obtained using a low-cost facial scanner showed clinically acceptable performance. The integration accuracy of facial and CBCT scans can be increased by including the forehead, nasal bridge, and malar areas as registration areas.

A Deep Invertible 3-D Facial Shape Model for Interpretable Genetic Syndrome Diagnosis.

One of the primary difficulties in treating patients with genetic syndromes is diagnosing their condition. Many syndromes are associated with characteristic facial features that can be imaged and utilized by computer-assisted diagnosis systems. In this work, we develop a novel 3D facial surface modeling approach with the objective of maximizing diagnostic model interpretability within a flexible deep learning framework. Therefore, an invertible normalizing flow architecture is introduced to enable both inferential and generative tasks in a unified and efficient manner. The proposed model can be used (1) to infer syndrome diagnosis and other demographic variables given a 3D facial surface scan and (2) to explain model inferences to non-technical users via multiple interpretability mechanisms. The model was trained and evaluated on more than 4700 facial surface scans from subjects with 47 different syndromes. For the challenging task of predicting syndrome diagnosis given a new 3D facial surface scan, age, and sex of a subject, the model achieves a competitive overall top-1 accuracy of 71%, and a mean sensitivity of 43% across all syndrome classes. We believe that invertible models such as the one presented in this work can achieve competitive inferential performance while greatly increasing model interpretability in the domain of medical diagnosis.

Experimental and numerical evaluation of simulated dental arch expansion during orthodontic therapy

Abstract In this publication, methods are presented to improve predictions of perioral soft-tissue changes following the expansion of the dental arches during orthodontic therapy. Acrylic veneers with different thicknesses were reversibly attached to the buccal surfaces of the upper and lower incisors to simulate their protrusion. The resulting morphological changes of the perioral soft-tissue surface were determined by 3D face scans. Experimentally-determined 3D soft-tissue changes are compared to numerical predictions using detailed finite-element (FE) models of the face of two individuals differing in the body mass index (BMI). The results suggest that common estimates of material constants used by the detailed and individualized FE models might be sufficient to explain absolute soft-tissue displacements although differences occurred between experimental and modeling results regarding the directions of displacements. The aim of this investigation is to create predictions of post-treatment appearance that are helpful for therapy planning.

The effect of maternal smoking and alcohol consumption on lip morphology.

To determine whether maternal smoking and/or alcohol consumption has an influence on lip morphology. Maternal smoking is a known risk factor for orofacial clefts; however, its influence on normal lip variation is unknown. Recent research regarding normal lip morphology has been contradictory. Retrospective cohort study. A total of 4747 children from the Avon Longitudinal Study of Parents and Children (ALSPAC) who each had 3D facial scans carried out at 15 years of age were included in the study. Each of the participants was automatically categorised regarding predetermined lip morphological traits. Questionnaires completed by their mothers identified smoking and alcohol habits during pregnancy. Logistic regression analyses were applied to determine the effect of maternal smoking and alcohol consumption on lip morphology. Maternal smoking has significant effects on upper and lower lip contours, Cupid's bow, lower lip-chin shape and lower lip tone (all P < 0.05). There was also an indication of a potential epigenetic effect of smoking pre-pregnancy on upper lip contour (P = 0.0573). Alcohol consumption is significantly associated with philtrum shape, particularly when >6 units of alcohol are consumed per week (P = 0.0149, 32 weeks). Overall results suggest a deeply grooved philtrum is more likely if alcohol is consumed. Investigating the combined effect of smoking and alcohol consumption, lower lip contour (P = 0.00923) and lower lip-chin shape (P = 0.0171) are statistically significant, with lower lip contour more likely to be narrow in the midline, and lower lip-chin shape more likely to be an angular concavity. Maternal smoking influences a number of lip traits, including a possible epigenetic effect on upper lip contour. Maternal alcohol consumption, particularly at a high level, influences philtrum shape. Maternal smoking and alcohol consumption have a combined effect on lower lip contour and lower lip-chin shape.

3D Printed Customized Facemask for Maxillary Protraction in the Early Treatment of a Class III Malocclusion: Proof-of-Concept Clinical Case.

In order to improve fit and comfort, a maxillary protraction facemask customized to the patient’s anatomy was produced by means of 3D face scanning, digital design and additive manufacturing. An 8-year-old patient in need of early treatment for the Class III malocclusion received a rapid palatal expander and a Petit-type facemask, whose components were digitally designed on a 3D scan of the patient’s face. For face scanning, the iPad Pro 2018 tablet (Apple, Cupertino, CA, USA) with the Bellus3D DentalPro application (Bellus3D, Campbell, CA, USA) was used. Facemask components were modelled with 3D Blender software. The rests were 3D printed in BioMed Clear biocompatible resin (Formlabs, Somerville, MA, USA), and the bar in stainless steel. For greater comfort, the internal surface of the rests was lined with a polymer gel pad (Silipos, Niagara Falls, NY, USA). The manufacturing procedure of the customized facemask is patented. The patient wore the facemask at night for a period of 9 months. The patient’s experience was evaluated with a questionnaire at 1 week, 3, 6, and 10 months of treatment. The customized facemask was well accepted by the patient and obtained the expected treatment outcome. Furthermore, 3D face scanning, 3D modelling and 3D printing allow for the manufacturing of customized facemasks with improved fit and comfort, favoring patient compliance and treatment success.

Digital workflow for fabrication of bespoke facemask in burn rehabilitation with smartphone 3D scanner and desktop 3D printing: clinical case study

We present a digital workflow for the production of custom facial orthosis used for burn scar management using smartphone three-dimensional (3D) scanner and desktop 3D printing. 3D facial scan of a 48-year-old lady with facial burn scars was obtained. 3D modeling with open-source programs were used to create facemask then 3D printed using rigid polylactic acid (PLA) filament and semi-rigid thermoplastic polyurethane (TPU). Conventional facemask was used as a control. Each mask was worn for 7 days. Primary outcomes were level of comfort, and adherence to treatment. The conventional facemask was the most convenient followed by the TPU-facemask (mean comfort score of 9/10 and 8.7/10, respectively). Patient’s compliance was high for both TPU and conventional masks, each was worn for at least 21 hours/day for 7 days. On the contrary, PLA-facemask was not well tolerated. The proposed digital workflow is simple, patient-friendly and can be adopted for resource-intensive healthcare.

A comparison of virtually mounted dental casts from traditional facebow records, average values, and 3D facial scans

Statement of problemAlthough average values and facebow records have been incorporated into prosthetic dentistry with much success, little is known about how using 3D facial scans for mounting compare with traditional mounting methods. PurposeThe purpose of this pilot clinical study was to determine differences in measurements among casts mounted virtually by using the average values of the Bonwill triangle and the Balkwill angle, casts mounted by using facebow records, and casts mounted from 3D facial scans. Material and methodsIntraoral digital scans were obtained from each participant (n=10) and 3D printed in resin. For the facebow preservation group (FPG), a facebow record was used to mount the resin casts on a semiadjustable articulator. A desktop scanner was used to digitize this mounting while preserving the facebow record. The average mounting group (AMG) consisted of intraoral digital scans that were mounted virtually by using the concepts of the Bonwill triangle and the Balkwill angle. For the facial scan group (FSG), the participants’ digitized casts were superimposed on the facial scans by using a target system. The Bergstrom point and the glabella were used to mount these casts and their associated facial scans in the digital environment. This study used the FPG as the group to compare with the other mounting techniques because of its wide acceptance in restorative dentistry. These virtual mountings were completed in a computer-aided design software program, and the distance from right and left condylar elements to the incisal embrasure between mandibular central incisors, distance from left mandibular first molar to left condylar element and from right mandibular first molar to right condylar element, and anterior and posterior recordings at 0 mm, 3 mm, and 5 mm of vertical dimension increase were recorded. A Kruskal-Wallis 1-way analysis of variance was performed (α=.05). The Mann-Whitney U test was performed to evaluate differences in measured values among groups, and multiple comparisons were adjusted by using Bonferroni correction. ResultsAll anterior and posterior measurements to the condylar elements of the virtual articulator were found to be significantly different (P<.05). Both anterior and posterior condylar measurements between the FPG and the AMG were found to be significantly different (P<.05), while comparisons between the FPG and the FSG were found not to be significantly different (P>.05). All changes in vertical dimension were found not to be significantly different with respect to both anterior and posterior measurements (P>.05). ConclusionsWhen used to virtually mount dental casts, 3D facial scanners performed similarly to traditional facebow records.

Effects of Artificial Extraoral Markers on Accuracy of Three-Dimensional Dentofacial Image Integration: Smartphone Face Scan versus Stereophotogrammetry.

Recently, three-dimensional (3D) facial scanning has been gaining popularity in personalized dentistry. Integration of the digital dental model into the 3D facial image allows for a treatment plan to be made in accordance with the patients’ individual needs. The aim of this study was to evaluate the effects of extraoral markers on the accuracy of digital dentofacial integrations. Facial models were generated using smartphone and stereophotogrammetry. Dental models were generated with and without extraoral markers and were registered to the facial models by matching the teeth or markers (n = 10 in each condition; total = 40). Accuracy of the image integration was measured in terms of general 3D position, occlusal plane, and dental midline deviations. The Mann–Whitney U test and two-way analysis of variance were used to compare results among face-scanning systems and matching methods (α = 0.05). As result, the accuracy of dentofacial registration was significantly affected by the use of artificial markers and different face-scanning systems (p < 0.001). The deviations were smallest in stereophotogrammetry with the marker-based matching and highest in smartphone face scans with the tooth-based matching. In comparison between the two face-scanning systems, the stereophotogrammetry generally produced smaller discrepancies than smartphones.

Downsampled depth encoding for enhanced 3D range geometry compression.

The use of three-dimensional (3D) range geometry is expanding across a variety of disciplines ranging from medicine to the visual arts. A large amount of information is available in 3D range geometry, causing some applications to be limited in their ability to effectively store or transmit captured data. To help alleviate this constraint, a variety of 3D range data compression techniques have been proposed. One method, multiwavelength depth (MWD) encoding, smoothly encodes 3D range geometry into the three color channels of a 2D RGB image. To the best of our knowledge, we present a novel compression enhancement to further reduce file sizes that employs image downsampling, MWD encoding, and lossless (e.g., PNG) or lossy (e.g., JPEG) compression. Image upsampling is used to return downsampled encodings to their original resolution from which the 3D information is then decoded. The proposed method is robust to various scales of downsampling and levels of lossy compression. For example, when this method was applied with 50% downsampling and JPEG 85 to an encoding of a 3D face scan, a compression ratio of 68.85:1 versus the raw data was achieved with a global RMS reconstruction accuracy of 98.77%. Experimental results demonstrate that the proposed method can provide substantial file size savings at minimal reduction in overall reconstruction accuracy.

Reliability of cone beam CT for morphometry of nasolabial soft tissue in patients with skeletal class III malocclusion: A qualitative and quantitative analysis.

To assess reliability of cone-beam CT (CBCT) for nasolabial soft tissue measurements in patients with skeletal class III malocclusion based on 3-dimensional (3D) facial scanner results. CBCT and 3D facial scan images of 20 orthognathic patients are used in this study. Eleven soft tissue landmarks and 15 linear and angular measurements are identified and performed. For qualitative evaluation, Shapiro-Wilk test and Bland-Altman plots are applied to analyze the equivalence of the measurements derived from these two kinds of images. To quantify specific deviation of CBCT measurements from facial scanner, the latter is set as a benchmark, and mean absolute difference (MAD) and relative error magnitude (REM) for each variable are also calculated. Statistically significant differences are observed in regions of nasal base and lower lip vermilion between two methods. MAD value for all length measurements are less than 2 mm and for angular variables < 8°. The average MAD and REM for length measurements are 0.94 mm and 5.64%, and for angular measurements are 2.27° and 3.78%, respectively. The soft tissue results measured by CBCT show relatively good reliability and can be used for 3D measurement of soft tissue in the nasolabial region clinically.