Three dimensional (3D) imaging techniques in orthodontics-An update

Comparison of deep learning models for facial attractiveness assessment on 3D photos

OBJECTIVES

Convolutional neural networks (CNNs) have demonstrated remarkable success in orthodontics. This study aimed to evaluate the accuracy and precision of several prominent CNN models for evaluating the facial attractiveness in Chinese orthodontic patients aged 6-18 years.

MATERIALS AND METHODS

A total of 1272 three-dimensional (3D) pretreatment photographs of patients were gathered. A panel of seven Chinese orthodontists assessed facial attractiveness using a visual analog scale. After conversion to two-dimensional RGB images, the data were fed into CNN models, including ResNet18, ResNet50, ResNet101, VGG-16, VGG-19, Inception-v3, MobileNet-v2, and DenseNet121. The performance of these CNNs was evaluated using root mean square error (RMSE), mean absolute error (MAE), Kendall's tau (τ), and Spearman's rank correlation coefficient (ρ).

RESULTS

DenseNet121 demonstrated the best, and MobileNet-v2 performed the worst in terms of prediction accuracy. ResNet18 required the shortest training time yet was still able to accurately predict facial attractiveness. In addition, VGG-19 was the largest and consumed the most time during training. DenseNet121 successfully achieved a balance between the model performance and the training cost and outperformed the other CNNs in terms of ranking correlation, validation loss, and validation MAE. Meanwhile, ResNet101 failed to achieve a performance improvement after an initial stage as the number of epochs increased.

CONCLUSIONS

DenseNet121 exhibited the best performance in terms of prediction accuracy and ranking correlation. Furthermore, the trade-offs was also analyzed between model accuracy and training efficiency, offering insights into model selection under different computational constraints.

CLINICAL SIGNIFICANCE

The successful application of deep learning models helps evaluate facial attractiveness accurately and precisely.

Smartphone-generated 3D facial images: reliable for routine assessment of the oronasal region of patients with cleft or mere convenience? A validation study

OBJECTIVES

To evaluate the validity and reliability of smartphone-generated three-dimensional (3D) facial images for routine evaluation of the oronasal region of patients with cleft by comparing their accuracy to that of direct anthropometry (DA) and 3dMD.

MATERIALS AND METHODS

Eighteen soft-tissue facial landmarks were manually labelled on each of the 17 (9 males and 8 females; mean age 23.3 ± 5.4 years) cleft lip and palate (CLP) patients' faces. Two surface imaging systems, 3dMDface and Bellus3D FaceApp, were used to perform two imaging operations on each labelled face. Subsequently, 32 inter-landmark facial measurements were directly measured on the labelled faces and digitally measured on the 3D facial images. Statistical comparisons were made between smartphone-generated 3D facial images (SGI), DA, and 3dMD measurements.

RESULTS

The SGI measurements were slightly higher than those from DA and 3dMD, but the mean differences between inter-landmark measurements were not statistically significant across all three methods. In terms of clinical acceptability, 16% and 59% of measures showed differences of ≤ 3 mm or ≤ 5º, with good agreement between DA and SGI and 3dMD and SGI, respectively. A small systematic bias of ± 0.2 mm was observed generally among the three methods. Additionally, the mean absolute difference between the DA and SGI methods was the highest for linear measurements (1.31 ± 0.34 mm) and angular measurements (4.11 ± 0.76º).

CONCLUSIONS

SGI displayed fair trueness compared to DA and 3dMD. It exhibited high accuracy in the orolabial area and specific central and flat areas within the oronasal region. Notwithstanding this, it has limited clinical applicability for assessing the entire oronasal region of patients with CLP. From a clinical application perspective, SGI should accurately encompass the entire oronasal region for optimal clinical use.

CLINICAL RELEVANCE

SGI can be considered for macroscopic oronasal analysis or for patient education where accuracy within 3 mm and 5º may not be critical.

Frontiers in Three-Dimensional Surface Imaging Systems for 3D Face Acquisition in Craniofacial Research and Practice: An Updated Literature Review

Digitalizing all aspects of dental care is a contemporary approach to ensuring the best possible clinical outcomes. Ongoing advancements in 3D face acquisition have been driven by continuous research on craniofacial structures and treatment effects. An array of 3D surface-imaging systems are currently available for generating photorealistic 3D facial images. However, choosing a purpose-specific system is challenging for clinicians due to variations in accuracy, reliability, resolution, and portability. Therefore, this review aims to provide clinicians and researchers with an overview of currently used or potential 3D surface imaging technologies and systems for 3D face acquisition in craniofacial research and daily practice. Through a comprehensive literature search, 71 articles meeting the inclusion criteria were included in the qualitative analysis, investigating the hardware, software, and operational aspects of these systems. The review offers updated information on 3D surface imaging technologies and systems to guide clinicians in selecting an optimal 3D face acquisition system. While some of these systems have already been implemented in clinical settings, others hold promise. Furthermore, driven by technological advances, novel devices will become cost-effective and portable, and will also enable accurate quantitative assessments, rapid treatment simulations, and improved outcomes.

Can smartphones be used for routine dental clinical application? A validation study for using smartphone-generated 3D facial images

OBJECTIVES

To compare the accuracy of smartphone-generated three-dimensional (3D) facial images to that of direct anthropometry (DA) and 3dMD with the aim of assessing the validity and reliability of smartphone-generated 3D facial images for routine clinical applications.

MATERIALS AND METHODS

Twenty-five anthropometric soft-tissue facial landmarks were labelled manually on 22 orthognathic surgery patients (11 males and 11 females; mean age 26.2 ± 5.3 years). For each labelled face, two imaging operations were performed using two different surface imaging systems: 3dMDface and Bellus3D FaceApp. Next, 42 inter-landmark facial measurements amongst the identified facial landmarks were measured directly on each labelled face and also digitally on 3D facial images. The measurements obtained from smartphone-generated 3D facial images (SGI) were statistically compared with those from DA and 3dMD.

RESULTS

SGI had slightly higher measurement values than DA and 3dMD, but there was no statistically significant difference between the mean values of inter-landmark measures across the three methods. Clinically acceptable differences (≤3 mm or ≤5°) were observed for 67 % and 74 % of measurements with good agreement between DA and SGI, and 3dMD and SGI, respectively. An overall small systematic bias of ± 0.2 mm was observed between the three methods. Furthermore, the mean absolute difference between DA and SGI methods was highest for linear (1.41 ± 0.33 mm) as well as angular measurements (3.07 ± 0.73°).

CONCLUSIONS

SGI demonstrated fair trueness compared to DA and 3dMD. The central region and flat areas of the face in SGI are more accurate. Despite this, SGI have limited clinical application, and the panfacial accuracy of the SGI would be more desirable from a clinical application standpoint.

CLINICAL SIGNIFICANCE

The usage of SGI in clinical practice for region-specific macro-proportional facial assessment involving central and flat regions of the face or for patient education purposes, which does not require accuracy within 3 mm and 5° can be considered.

Application of three-dimensional reconstruction technology in dentistry: a narrative review

BACKGROUND

Three-dimensional(3D) reconstruction technology is a method of transforming real goals into mathematical models consistent with computer logic expressions and has been widely used in dentistry, but the lack of review and summary leads to confusion and misinterpretation of information. The purpose of this review is to provide the first comprehensive link and scientific analysis of 3D reconstruction technology and dentistry to bridge the information bias between these two disciplines.

METHODS

The IEEE Xplore and PubMed databases were used for rigorous searches based on specific inclusion and exclusion criteria, supplemented by Google Academic as a complementary tool to retrieve all literature up to February 2023. We conducted a narrative review focusing on the empirical findings of the application of 3D reconstruction technology to dentistry.

RESULTS

We classify the technologies applied to dentistry according to their principles and summarize the different characteristics of each category, as well as the different application scenarios determined by these characteristics of each technique. In addition, we indicate their development prospects and worthy research directions in the field of dentistry, from individual techniques to the overall discipline of 3D reconstruction technology, respectively.

CONCLUSIONS

Researchers and clinicians should make different decisions on the choice of 3D reconstruction technology based on different objectives. The main trend in the future development of 3D reconstruction technology is the joint application of technology.

Accuracy and Reliability of 3D Imaging for Facial Movement Evaluation: Validation of the VECTRA H1

Three-dimensional imaging can be used to obtain objective assessments of facial morphology that is useful in a variety of clinical settings. The VECTRA H1 is unique in that it is relatively inexpensive, handheld, and does not require standardized environmental conditions for image capture. Although it provides accurate measurements when imaging relaxed facial expressions, the clinical evaluation of many disorders involves the assessment of facial morphology when performing facial movements. The aim of this study was to assess the accuracy and reliability of the VECTRA H1, specifically when imaging facial movement.

Methods

The accuracy, intrarater, and interrater reliability of the VECTRA H1 were assessed when imaging four facial expressions: eyebrow lift, smile, snarl, and lip pucker. Fourteen healthy adult subjects had the distances between 13 fiducial facial landmarks measured at rest and the terminal point of each of the four movements by digital caliper and by the VECTRA H1. Intraclass correlation and Bland-Altman limits of agreement were used to determine agreement between measures. The agreement between measurements obtained by five different reviewers was evaluated by intraclass correlation to determine interrater reliability.

Results

Median correlation between digital caliper and VECTRA H1 measurements ranged from 0.907 (snarl) to 0.921 (smile). Median correlation was very good for both intrarater (0.960-0.975) and interrater reliability (0.997-0.999). The mean absolute error between modalities, and both within and between raters was less than 2 mm for all movements tested.

Conclusion

The VECTRA H1 met acceptable standards for the assessment of facial morphology when imaging facial movements.