Transcranial ultrafast ultrasound Doppler imaging: A phantom study

Ultrafast ultrasound Doppler imaging facilitates the assessment of cerebral hemodynamics with high spatio-temporal resolution. However, the significant acoustic impedance mismatch between the skull and soft tissue results in phase aberrations, which can compromise the quality of transcranial imaging and introduce biases in velocity and direction quantification of blood flow. This paper proposed an aberration correction method that combines deep learning-based skull sound speed modelling with ray theory to realize transcranial plane-wave imaging and ultrafast Doppler imaging. The method was validated through phantom experiments using a linear array with a center frequency of 6.25 MHz, 128 elements, and a pitch of 0.3 mm. The results demonstrated an improvement in the imaging quality of intracranial targets when using the proposed method. After aberration correction, the average locating deviation decreased from 1.40 mm to 0.27 mm in the axial direction, from 0.50 mm to 0.20 mm in the lateral direction, and the average full-width-at-half-maximum (FWHM) decreased from 1.37 mm to 0.97 mm for point scatterers. For circular inclusions, the average contrast-to-noise ratio (CNR) improved from 8.1 dB to 11.0 dB, and the average eccentricity decreased from 0.36 to 0.26. Furthermore, the proposed method was applied to transcranial ultrafast Doppler flow imaging. The results showed a significant improvement in accuracy and quality for blood Doppler flow imaging. The results in the absence of the skull were considered as the reference, and the average normalized root-mean-square errors of the axial velocity component on the five selected axial profiles were reduced from 17.67% to 8.02% after the correction.

Ultrasound-based 3D bone modelling in computer assisted orthopedic surgery - a review and future challenges

Computer-assisted orthopedic surgery requires precise representations of bone surfaces. To date, computed tomography constitutes the gold standard, but comes with a number of limitations, including costs, radiation and availability. Ultrasound has potential to become an alternative to computed tomography, yet suffers from low image quality and limited field-of-view. These shortcomings may be addressed by a fully automatic segmentation and model-based completion of 3D bone surfaces from ultrasound images. This survey summarizes the state-of-the-art in this field by introducing employed algorithms, and determining challenges and trends. For segmentation, a clear trend toward machine learning-based algorithms can be observed. For 3D bone model completion however, none of the published methods involve machine learning. Furthermore, data sets and metrics are identified as weak spots in current research, preventing development and evaluation of models that generalize well.

DetSegDiff: A joint periodontal landmark detection and segmentation in intraoral ultrasound using edge-enhanced diffusion-based network

Individuals with malocclusion require an orthodontic diagnosis and treatment plan based on the severity of their condition. Assessing and monitoring changes in periodontal structures before, during, and after orthodontic procedures is crucial, and intraoral ultrasound (US) imaging has been shown a promising diagnostic tool in imaging periodontium. However, accurately delineating and analyzing periodontal structures in US videos is a challenging task for clinicians, as it is time-consuming and subject to interpretation errors. This paper introduces DetSegDiff, an edge-enhanced diffusion-based network developed to simultaneously detect the cementoenamel junction (CEJ) and segment alveolar bone structure in intraoral US videos. An edge feature encoder is designed to enhance edge and texture information for precise delineation of periodontal structures. Additionally, we employed the spatial squeeze-attention module (SSAM) to extract more representative features to perform both detection and segmentation tasks at global and local levels. This study used 169 videos from 17 orthodontic patients for training purposes and was subsequently tested on 41 videos from 4 additional patients. The proposed method achieved a mean distance difference of 0.17 ± 0.19 mm for the CEJ and an average Dice score of 90.1% for alveolar bone structure. As there is a lack of multi-task benchmark networks, thorough experiments were undertaken to assess and benchmark the proposed method against state-of-the-art (SOTA) detection and segmentation individual networks. The experimental results demonstrated that DetSegDiff outperformed SOTA approaches, confirming the feasibility of using automated diagnostic systems for orthodontists.

Intraoral Ultrasound Imaging Using a Rotational Transducer with Periodontal Feature Identification by Machine Learning

Innovative intraoral ultrasound devices with smart artificial intelligence-based identification for dento-anatomy could provide crucial information for oral health diagnosis and treatment and shed light on real-time detection of developmental dentistry. However, the grand challenge is that the current ultrasound technologies are meant for external use due to their bulkiness and low frequency. We report a compact versatile ultrasound intraoral device that consists of a rotational probe head robustly pivoted around a hand-held and portable handle for real-time imaging of intraoral anatomy using high-frequency ultrasonography (up to 25 MHz). The intraoral ultrasound device that could be adjusted for various orientations of the imaging planes by rotating the head provides real-time, high-resolution ultrasonograms of intraoral structures, including dento-periodontium of most tooth types and maxillary palate. Machine learning-based algorithms are integrated to automate the identification of important structures, including alveolar bone and cementum-enamel junction. The intraoral ultrasound device smartened with artificial intelligence could innovate oral health diagnosis and treatment plans toward precision health and patient care.

Nonionizing diagnostic imaging modalities for visualizing health and pathology of periodontal and peri-implant tissues

Radiographic examination has been an essential part of the diagnostic workflow in periodontology and implant dentistry. However, radiographic examination unavoidably involves ionizing radiation and its associated risks. Clinicians and researchers have invested considerable efforts in assessing the feasibility and capability of utilizing nonionizing imaging modalities to replace traditional radiographic imaging. Two such modalities have been extensively evaluated in clinical settings, namely, ultrasonography (USG) and magnetic resonance imaging (MRI). Another modality, optical coherence tomography (OCT), has been under investigation more recently. This review aims to provide an overview of the literature and summarize the usage of USG, MRI, and OCT in evaluating health and pathology of periodontal and peri-implant tissues. Clinical studies have shown that USG could accurately measure gingival height and crestal bone level, and classify furcation involvement. Due to physical constraints, USG may be more applicable to the buccal surfaces of the dentition even with an intra-oral probe. Clinical studies have also shown that MRI could visualize the degree of soft-tissue inflammation and osseous edema, the extent of bone loss at furcation involvement sites, and periodontal bone level. However, there was a lack of clinical studies on the evaluation of peri-implant tissues by MRI. Moreover, an MRI machine is very expensive, occupies much space, and requires more time than cone-beam computed tomography (CBCT) or intraoral radiographs to complete a scan. The feasibility of OCT to evaluate periodontal and peri-implant tissues remains to be elucidated, as there are only preclinical studies at the moment. A major shortcoming of OCT is that it may not reach the bottom of the periodontal pocket, particularly for inflammatory conditions, due to the absorption of near-infrared light by hemoglobin. Until future technological breakthroughs finally overcome the limitations of USG, MRI and OCT, the practical imaging modalities for routine diagnostics of periodontal and peri-implant tissues remain to be plain radiographs and CBCTs.

A Comparative Analysis of Artificial Intelligence and Manual Methods for Three-Dimensional Anatomical Landmark Identification in Dentofacial Treatment Planning

With the growing demand for orthognathic surgery and other facial treatments, the accurate identification of anatomical landmarks has become crucial. Recent advancements have shifted towards using three-dimensional radiologic analysis instead of traditional two-dimensional methods, as it allows for more precise treatment planning, primarily relying on direct identification by clinicians. However, manual tracing can be time-consuming, mainly when dealing with a large number of patients. This study compared the accuracy and reliability of identifying anatomical landmarks using artificial intelligence (AI) and manual identification. Thirty patients over 19 years old who underwent pre-orthodontic and orthognathic surgery treatment and had pre-orthodontic three-dimensional radiologic scans were selected. Thirteen anatomical indicators were identified using both AI and manual methods. The landmarks were identified by AI and four experienced clinicians, and multiple ANOVA was performed to analyze the results. The study results revealed minimal significant differences between AI and manual tracing, with a maximum deviation of less than 2.83 mm. This indicates that utilizing AI to identify anatomical landmarks can be a reliable method in planning orthognathic surgery. Our findings suggest that using AI for anatomical landmark identification can enhance treatment accuracy and reliability, ultimately benefiting clinicians and patients.

Advancements in oral and maxillofacial surgery medical images segmentation techniques: An overview

OBJECTIVES

This article reviews recent advances in computer-aided segmentation methods for oral and maxillofacial surgery and describes the advantages and limitations of these methods. The objective is to provide an invaluable resource for precise therapy and surgical planning in oral and maxillofacial surgery. Study selection, data and sources: This review includes full-text articles and conference proceedings reporting the application of segmentation methods in the field of oral and maxillofacial surgery. The research focuses on three aspects: tooth detection segmentation, mandibular canal segmentation and alveolar bone segmentation. The most commonly used imaging technique is CBCT, followed by conventional CT and Orthopantomography. A systematic electronic database search was performed up to July 2023 (Medline via PubMed, IEEE Xplore, ArXiv, Google Scholar were searched).

RESULTS

These segmentation methods can be mainly divided into two categories: traditional image processing and machine learning (including deep learning). Performance testing on a dataset of images labeled by medical professionals shows that it performs similarly to dentists' annotations, confirming its effectiveness. However, no studies have evaluated its practical application value.

CONCLUSION

Segmentation methods (particularly deep learning methods) have demonstrated unprecedented performance, while inherent challenges remain, including the scarcity and inconsistency of datasets, visible artifacts in images, unbalanced data distribution, and the "black box" nature.

CLINICAL SIGNIFICANCE

Accurate image segmentation is critical for precise treatment and surgical planning in oral and maxillofacial surgery. This review aims to facilitate more accurate and effective surgical treatment planning among dental researchers.

The feasibility of ultrasonography for the measurement of periodontal and peri-implant phenotype: A systematic review and meta-analysis

BACKGROUND

Screening ultrasonography was proposed for monitoring periodontal soft tissues in the early 1960s, owing to its nonionizing, real-time, and cost-effective properties. Studies have provided convincing preliminary evidence for the use of ultrasound (US) in implant dentistry.

PURPOSE

To assess the feasibility of ultrasonography (US) for measuring the buccal thickness of periodontal and peri-implant tissues. The secondary objective was to evaluate the reliability of US measurements compared to classic techniques, such as CBCT and directly measurements.

MATERIALS AND METHODS

An electronic literature search was conducted by three independent reviewers through February 2023. The inclusion criteria were articles investigating at least five patients/cadavers with US measurements in periodontal or peri-implant buccal tissues. Compliance with methodological reporting standards and risk of bias was assessed using EULAR and QUADAS-C tools, respectively. Random-effects meta-analysis was conducted, using Bland-Altman analysis. Certainty of the evidence was assessed using GRADE.

RESULTS

The final selection included 12 studies examining 458 patients and 13 cadavers, with a total of 226 implants, 1958 teeth and 60 edentulous sites. The body of evidence was assessed as partially compliant with methodological reporting standards for US studies and had an unclear to high risk of bias. Meta-analysis of five comparative studies showed no evidence of clinically significant bias between US and direct measurements (very low certainty), and between US and CBCT (very low certainty) for soft-tissue thickness. Likewise, for bone thickness, there is no evidence of clinically significant bias between US and CBCT (low certainty).

CONCLUSIONS

Compared to the CBCT and direct measurements, ultrasonography might be a reliable approach for monitoring on periodontal and peri-implant phenotype. However, there is uncertainty about estimates of the actual effect, so further standardized and larger sample size of clinical research is needed.

Developing an Artificial Intelligence Solution to Autosegment the Edentulous Mandibular Bone for Implant Planning

OBJECTIVE

 Dental implants are considered the optimum solution to replace missing teeth and restore the mouth's function and aesthetics. Surgical planning of the implant position is critical to avoid damage to vital anatomical structures; however, the manual measurement of the edentulous (toothless) bone on cone beam computed tomography (CBCT) images is time-consuming and is subject to human error. An automated process has the potential to reduce human errors and save time and costs. This study developed an artificial intelligence (AI) solution to identify and delineate edentulous alveolar bone on CBCT images before implant placement.

MATERIALS AND METHODS

 After obtaining the ethical approval, CBCT images were extracted from the database of the University Dental Hospital Sharjah based on predefined selection criteria. Manual segmentation of the edentulous span was done by three operators using ITK-SNAP software. A supervised machine learning approach was undertaken to develop a segmentation model on a "U-Net" convolutional neural network (CNN) in the Medical Open Network for Artificial Intelligence (MONAI) framework. Out of the 43 labeled cases, 33 were utilized to train the model, and 10 were used for testing the model's performance.

STATISTICAL ANALYSIS

 The degree of 3D spatial overlap between the segmentation made by human investigators and the model's segmentation was measured by the dice similarity coefficient (DSC).

RESULTS

 The sample consisted mainly of lower molars and premolars. DSC yielded an average value of 0.89 for training and 0.78 for testing. Unilateral edentulous areas, comprising 75% of the sample, resulted in a better DSC (0.91) than bilateral cases (0.73).

CONCLUSION

 Segmentation of the edentulous spans on CBCT images was successfully conducted by machine learning with good accuracy compared to manual segmentation. Unlike traditional AI object detection models that identify objects present in the image, this model identifies missing objects. Finally, challenges in data collection and labeling are discussed, together with an outlook at the prospective stages of a larger project for a complete AI solution for automated implant planning.

Measuring the alveolar bone level in adolescents: A comparison between ultrasound and cone beam computed tomography

BACKGROUND

Cone beam computed tomography (CBCT) is an imaging modality, which is used routinely in orthodontic diagnosis and treatment planning but delivers much higher radiation than conventional dental radiographs. Ultrasound is a noninvasive imaging method that creates an image without ionizing radiation.

AIM

To investigate the reliability of ultrasound and the agreement between ultrasound and CBCT in measuring the alveolar bone level (ABL) on the buccal/labial side of the incisors in adolescent orthodontic patients.

DESIGN

One hundred and eighteen incisors from 30 orthodontic adolescent patients were scanned by CBCT with 0.3-mm voxel size and ultrasound at 20 MHz frequency. The ABL, distance from the cementoenamel junction (CEJ) to the alveolar bone crest (ABC), was measured twice to evaluate the agreement between ultrasound and CBCT. In addition, the intra- and inter-rater reliabilities in measuring the ABL by four raters were compared.

RESULTS

The mean difference (MD) in the ABL between ultrasound and CBCT was -0.07 mm with 95% limit of agreement (LoA) from -0.47 to 0.32 mm for all teeth. For each jaw, the MDs between the ultrasound and CBCT were -0.18 mm (for mandible with 95% LoA from -0.53 to 0.18 mm) and 0.03 mm (for maxilla with 95% LoA from -0.28 to 0.35 mm). In comparison, ultrasound had higher intra-rater (ICC = 0.83-0.90) and inter-rater reliabilities (ICC = 0.97) in ABL measurement than CBCT (ICC = 0.56-0.78 for intra-rater and ICC = 0.69 for inter-rater reliabilities).

CONCLUSION

CBCT parameters used in orthodontic diagnosis and treatment planning in adolescents may not be a reliable tool to assess the ABL for the mandibular incisors. On the contrary, ultrasound imaging, an ionizing radiation-free, inexpensive, and portable diagnostic tool, has potential to be a reliable diagnostic tool in assessing the ABL in adolescent patients.

Early Predicting Tribocorrosion Rate of Dental Implant Titanium Materials Using Random Forest Machine Learning Models

Early detection and prediction of bio-tribocorrosion can avert unexpected damage that may lead to secondary revision surgery and associated risks of implantable devices. Therefore, this study sought to develop a state-of-the-art prediction technique leveraging machine learning(ML) models to classify and predict the possibility of mechanical degradation in dental implant materials. Key features considered in the study involving pure titanium and titanium-zirconium (zirconium = 5, 10, and 15 in wt%) alloys include corrosion potential, acoustic emission(AE) absolute energy, hardness, and weight-loss estimates. ML prototype models deployed confirms its suitability in tribocorrosion prediction with an accuracy above 90%. Proposed system can evolve as a continuous structural-health monitoring as well as a reliable predictive modeling technique for dental implant monitoring.

Knee Bone Models From Ultrasound

The number of total knee arthroplasties performed worldwide is on the rise. Patient-specific planning and implants may improve surgical outcomes but require 3-D models of the bones involved. Ultrasound (US) may become a cheap and nonharmful imaging modality if the shortcomings of segmentation techniques in terms of automation, accuracy, and robustness are overcome; furthermore, any kind of US-based bone reconstruction must involve some kind of model completion to handle occluded areas, for example, the frontal femur. A fully automatic and robust processing pipeline is proposed, generating full bone models from 3-D freehand US scanning. A convolutional neural network (CNN) is combined with a statistical shape model (SSM) to segment and extrapolate the bone surface. We evaluate the method in vivo on ten subjects, comparing the US-based model to a magnetic resonance imaging (MRI) reference. The partial freehand 3-D record of the femur and tibia bones deviate by 0.7-0.8 mm from the MRI reference. After completion, the full bone model shows an average submillimetric error in the case of the femur and 1.24 mm in the case of the tibia. Processing of the images is performed in real time, and the final model fitting step is computed in less than a minute. It took an average of 22 min for a full record per subject.

Overview of Ultrasound in Dentistry for Advancing Research Methodology and Patient Care Quality with Emphasis on Periodontal/Peri-implant Applications

BACKGROUND

Ultrasound is a non-invasive, cross-sectional imaging technique emerging in dentistry. It is an adjunct tool for diagnosing pathologies in the oral cavity that overcomes some limitations of current methodologies, including direct clinical examination, 2D radiographs, and cone beam computerized tomography. Increasing demand for soft tissue imaging has led to continuous improvements on transducer miniaturization and spatial resolution. The aims of this study are (1) to create a comprehensive overview of the current literature of ultrasonic imaging relating to dentistry, and (2) to provide a view onto investigations with immediate, intermediate, and long-term impact in periodontology and implantology.

METHODS

A rapid literature review was performed using two broad searches conducted in the PubMed database, yielding 576 and 757 citations, respectively. A rating was established within a citation software (EndNote) using a 5-star classification. The broad search with 757 citations allowed for high sensitivity whereas the subsequent rating added specificity.

RESULTS

A critical review of the clinical applications of ultrasound in dentistry was provided with a focus on applications in periodontology and implantology. The role of ultrasound as a developing dental diagnostic tool was reviewed. Specific uses such as soft and hard tissue imaging, longitudinal monitoring, as well as anatomic and physiological evaluation were discussed.

CONCLUSIONS

Future efforts should be directed towards the transition of ultrasonography from a research tool to a clinical tool. Moreover, a dedicated effort is needed to introduce ultrasonic imaging to dental education and the dental community to ultimately improve the quality of patient care.

Estimating Crestal Thickness of Alveolar Bones on Intra-oral Ultrasonograms

OBJECTIVE

Alveolar crestal bone thickness and level provide important diagnostic and prognostic information for orthodontic treatment, periodontal disease management and dental implants. Ionizing radiation-free ultrasound has emerged as a promising clinical tool in imaging oral tissues. However, the ultrasound image is distorted when the wave speed of the tissue of interest is different from the mapping speed of the scanner and, therefore, the subsequent dimension measurements are not accurate. This study was aimed at deriving a correction factor that can be applied to the measurements to correct for discrepancy caused by speed variation.

METHODS

The factor is a function of the speed ratio and the acute angle that the segment of interest makes with the beam axis perpendicular to the transducer. The phantom and cadaver experiments were designed to validate the method.

DISCUSSION

The comparisons agree well with absolute errors not more than 4.9%. Dimension measurements on ultrasonographs can be properly corrected by applying the correction factor without recourse to the raw signals.

CONCLUSION

The correction factor has reduced the measurement discrepancy on the acquired ultrasonographs for the tissue whose speed is different from the scanner's mapping speed.

Machine Learning in Dentistry: A Scoping Review

Machine learning (ML) is being increasingly employed in dental research and application. We aimed to systematically compile studies using ML in dentistry and assess their methodological quality, including the risk of bias and reporting standards. We evaluated studies employing ML in dentistry published from 1 January 2015 to 31 May 2021 on MEDLINE, IEEE Xplore, and arXiv. We assessed publication trends and the distribution of ML tasks (classification, object detection, semantic segmentation, instance segmentation, and generation) in different clinical fields. We appraised the risk of bias and adherence to reporting standards, using the QUADAS-2 and TRIPOD checklists, respectively. Out of 183 identified studies, 168 were included, focusing on various ML tasks and employing a broad range of ML models, input data, data sources, strategies to generate reference tests, and performance metrics. Classification tasks were most common. Forty-two different metrics were used to evaluate model performances, with accuracy, sensitivity, precision, and intersection-over-union being the most common. We observed considerable risk of bias and moderate adherence to reporting standards which hampers replication of results. A minimum (core) set of outcome and outcome metrics is necessary to facilitate comparisons across studies.

A miniaturized ultrasound transducer for monitoring full-mouth oral health: a preliminary study

OBJECTIVE

To customize a miniaturized ultrasound transducer to access full-mouth B-mode, color Doppler, and spectral Doppler imaging for monitoring oral health.

METHODS

A customized periodontal ultrasound transducer SS-19-128 (19 MHz, 128 channels) 1.8-cm wide and 1-cm thick was developed and connected to a data acquisition (DAQ) system. B-mode, color Doppler, and spectral Doppler data could all be collected with SS-19-128. The imaging resolution and penetration capacity of SS-19-128 were characterized on phantoms. The gingival thickness was measured on 11 swine teeth by SS-19-128 for comparison with conventional transgingival probing via Bland-Altman analysis and Pearson correlation. Five human subjects were then recruited to demonstrate B-mode and Doppler imaging by SS-19-128.

RESULTS

The axial and lateral spatial resolution at 5.5 mm depth is 102.1 µm and 142.9 µm, respectively. The penetration depth in a tissue-mimicking phantom is over 30 mm. In vivo B-mode imaging of all 28 teeth was demonstrated on one human subject, and imaging of tooth #18 was accessed on five human subjects. Gingival thickness measurement compared with transgingival probing showed a bias of -0.015 mm and SD of 0.031 mm, and a r = 0.9235 (p < 0.0001) correlation. In vivo color and spectral Doppler imaging of the supraperiosteal artery in human gingiva was performed to generate hemodynamic information.

CONCLUSIONS

The small size of SS-19-128 offers important advantages over existing ultrasound technology-more specifically, whole-mouth scanning/charting reminiscent of radiography. This is nearly a two-fold increase in the number of teeth that can be assessed versus conventional transducers.

Advancements in Dentistry with Artificial Intelligence: Current Clinical Applications and Future Perspectives

Artificial intelligence has been widely used in the field of dentistry in recent years. The present study highlights current advances and limitations in integrating artificial intelligence, machine learning, and deep learning in subfields of dentistry including periodontology, endodontics, orthodontics, restorative dentistry, and oral pathology. This article aims to provide a systematic review of current clinical applications of artificial intelligence within different fields of dentistry. The preferred reporting items for systematic reviews (PRISMA) statement was used as a formal guideline for data collection. Data was obtained from research studies for 2009-2022. The analysis included a total of 55 papers from Google Scholar, IEEE, PubMed, and Scopus databases. Results show that artificial intelligence has the potential to improve dental care, disease diagnosis and prognosis, treatment planning, and risk assessment. Finally, this study highlights the limitations of the analyzed studies and provides future directions to improve dental care.

Clinical tooth segmentation based on local enhancement

The tooth arrangements of human beings are challenging to accurately observe when relying on dentists' naked eyes, especially for dental caries in children, which is difficult to detect. Cone-beam computer tomography (CBCT) is used as an auxiliary method to measure patients' teeth, including children. However, subjective and irreproducible manual measurements are required during this process, which wastes much time and energy for the dentists. Therefore, a fast and accurate tooth segmentation algorithm that can replace repeated calculations and annotations in manual segmentation has tremendous clinical significance. This study proposes a local contextual enhancement model for clinical dental CBCT images. The local enhancement model, which is more suitable for dental CBCT images, is proposed based on the analysis of the existing contextual models. Then, the local enhancement model is fused into an encoder-decoder framework for dental CBCT images. At last, extensive experiments are conducted to validate our method.

Automatic and quantitative measurement of alveolar bone level in OCT images using deep learning

We propose a method to automatically segment the periodontal structures of the tooth enamel and the alveolar bone using convolutional neural network (CNN) and to measure quantitatively and automatically the alveolar bone level (ABL) by detecting the cemento-enamel junction and the alveolar bone crest in optical coherence tomography (OCT) images. The tooth enamel and the alveolar bone regions were automatically segmented using U-Net, Dense-UNet, and U²-Net, and the ABL was quantitatively measured as the distance between the cemento-enamel junction and the alveolar bone crest using image processing. The mean distance difference (MDD) measured by our suggested method ranged from 0.19 to 0.22 mm for the alveolar bone crest (ABC) and from 0.18 to 0.32 mm for the cemento-enamel junction (CEJ). All CNN models showed the mean absolute error (MAE) of less than 0.25 mm in the x and y coordinates and greater than 90% successful detection rate (SDR) at 0.5 mm for both the ABC and the CEJ. The CNN models showed high segmentation accuracies in the tooth enamel and the alveolar bone regions, and the ABL measurements at the incisors by detected results from CNN predictions demonstrated high correlation and reliability with the ground truth in OCT images.

Automatic Segmentation of Periodontal Tissue Ultrasound Images with Artificial Intelligence: A Novel Method for Improving Dataset Quality

This research aimed to evaluate Mask R-CNN and U-Net convolutional neural network models for pixel-level classification in order to perform the automatic segmentation of bi-dimensional images of US dental arches, identifying anatomical elements required for periodontal diagnosis. A secondary aim was to evaluate the efficiency of a correction method of the ground truth masks segmented by an operator, for improving the quality of the datasets used for training the neural network models, by 3D ultrasound reconstructions of the examined periodontal tissue.

METHODS

Ultrasound periodontal investigations were performed for 52 teeth of 11 patients using a 3D ultrasound scanner prototype. The original ultrasound images were segmented by a low experienced operator using region growing-based segmentation algorithms. Three-dimensional ultrasound reconstructions were used for the quality check and correction of the segmentation. Mask R-CNN and U-NET were trained and used for prediction of periodontal tissue's elements identification.

RESULTS

The average Intersection over Union ranged between 10% for the periodontal pocket and 75.6% for gingiva. Even though the original dataset contained 3417 images from 11 patients, and the corrected dataset only 2135 images from 5 patients, the prediction's accuracy is significantly better for the models trained with the corrected dataset.

CONCLUSIONS

The proposed quality check and correction method by evaluating in the 3D space the operator's ground truth segmentation had a positive impact on the quality of the datasets demonstrated through higher IoU after retraining the models using the corrected dataset.

Deep convolutional neural network-based automated segmentation and classification of teeth with orthodontic brackets on cone-beam computed-tomographic images: a validation study

OBJECTIVE

Tooth segmentation and classification from cone-beam computed tomography (CBCT) is a prerequisite for diagnosis and treatment planning in the majority of digital dental workflows. However, an accurate and efficient segmentation of teeth in the presence of metal artefacts still remains a challenge. Therefore, the following study aimed to validate an automated deep convolutional neural network (CNN)-based tool for the segmentation and classification of teeth with orthodontic brackets on CBCT images.

METHODS

A total of 215 CBCT scans (1780 teeth) were retrospectively collected, consisting of pre- and post-operative images of the patients who underwent combined orthodontic and orthognathic surgical treatment. All the scans were acquired with NewTom CBCT device. A complete dentition with orthodontic brackets and high-quality images were included. The dataset were randomly divided into three subsets with random allocation of all 32 tooth classes: training set (140 CBCT scans-400 teeth), validation set (35 CBCT scans-100 teeth), and test set (pre-operative: 25, post-operative: 15 = 40 CBCT scans-1280 teeth). A multiclass CNN-based tool was developed and its performance was assessed for automated segmentation and classification of teeth with brackets by comparison with a ground truth.

RESULTS

The CNN model took 13.7 ± 1.2 s for the segmentation and classification of all the teeth on a single CBCT image. Overall, the segmentation performance was excellent with a high intersection over union (IoU) of 0.99. Anterior teeth showed a significantly lower IoU (P < 0.05) compared to premolar and molar teeth. The dice similarity coefficient score of anterior (0.99 ± 0.02) and premolar teeth (0.99 ± 0.10) in the pre-operative group was comparable to the post-operative group. The classification of teeth to the correct 32 classes had a high recall rate (99.9%) and precision (99%).

CONCLUSIONS

The proposed CNN model outperformed other state-of-the-art algorithms in terms of accuracy and efficiency. It could act as a viable alternative for automatic segmentation and classification of teeth with brackets.

CLINICAL SIGNIFICANCE

The proposed method could simplify the existing digital workflows of orthodontics, orthognathic surgery, restorative dentistry, and dental implantology by offering an accurate and efficient automated segmentation approach to clinicians, hence further enhancing the treatment predictability and outcomes.

High-resolution ultrasonography of gingival biomarkers for periodontal diagnosis in healthy and diseased subjects

OBJECTIVE

To determine the capacity of ultrasonographic image-based measurements of gingival height and alveolar bone level for monitoring periodontal health and disease.

METHODS

Sixteen subjects were recruited from patients scheduled to receive dental care and classified as periodontally healthy (n = 10) or diseased (n = 6) according to clinical guidelines. A 40-MHz ultrasound system was used to measure gingival recession, gingival height, alveolar bone level, and gingival thickness from 66 teeth for comparison to probing measurements of pocket depth and clinical attachment level. Interexaminer variability and comparison between ultrasound measurements and probing measurements was performed via Bland-Altman analysis.

RESULTS

Gingival recession and its risk in non-recessed patients could be determined via measurement of the supra- and subgingival cementoenamel junction relative to the gingival margin. Interexaminer bias for ultrasound image analysis was negligible (<0.10 mm) for imaged gingival height (iGH) and 0.45 mm for imaged alveolar bone level (iABL). Diseased subjects had significantly higher imaging measurements (iGH, iABL) and clinical measurements (probing pocket depth, clinical attachment level) than healthy subjects (p < 0.05). Subtraction of the average biologic width from iGH resulted in 83% agreement (≤1 mm difference) between iGH and probing pocket depth measurements.

CONCLUSIONS

Ultrasonography has an equivalent diagnostic capacity as gold-standard physical probing for periodontal metrics while offering more detailed anatomical information.

Multi-class deep learning segmentation and automated measurements in periodontal sonograms of a porcine model

OBJECTIVES

Ultrasound emerges as a complement to cone-beam computed tomography in dentistry, but struggles with artifacts like reverberation and shadowing. This study seeks to help novice users recognize soft tissue, bone, and crown of a dental sonogram, and automate soft tissue height (STH) measurement using deep learning.

METHODS

In this retrospective study, 627 frames from 111 independent cine loops of mandibular and maxillary premolar and incisors collected from our porcine model (N = 8) were labeled by a reader. 274 premolar sonograms, including data augmentation, were used to train a multi class segmentation model. The model was evaluated against several test sets, including premolar of the same breed (n = 74, Yucatan) and premolar of a different breed (n = 120, Sinclair). We further proposed a rule-based algorithm to automate STH measurements using predicted segmentation masks.

RESULTS

The model reached a Dice similarity coefficient of 90.7±4.39%, 89.4±4.63%, and 83.7±10.5% for soft tissue, bone, and crown segmentation, respectively on the first test set (n = 74), and 90.0±7.16%, 78.6±13.2%, and 62.6±17.7% on the second test set (n = 120). The automated STH measurements have a mean difference (95% confidence interval) of -0.22 mm (-1.4, 0.95), a limit of agreement of 1.2 mm, and a minimum ICC of 0.915 (0.857, 0.948) when compared to expert annotation.

CONCLUSION

This work demonstrates the potential use of deep learning in identifying periodontal structures on sonograms and obtaining diagnostic periodontal dimensions.

Applications of artificial intelligence in dentistry: A comprehensive review

OBJECTIVE

To perform a comprehensive review of the use of artificial intelligence (AI) and machine learning (ML) in dentistry, providing the community with a broad insight on the different advances that these technologies and tools have produced, paying special attention to the area of esthetic dentistry and color research.

MATERIALS AND METHODS

The comprehensive review was conducted in MEDLINE/PubMed, Web of Science, and Scopus databases, for papers published in English language in the last 20 years.

RESULTS

Out of 3871 eligible papers, 120 were included for final appraisal. Study methodologies included deep learning (DL; n = 76), fuzzy logic (FL; n = 12), and other ML techniques (n = 32), which were mainly applied to disease identification, image segmentation, image correction, and biomimetic color analysis and modeling.

CONCLUSIONS

The insight provided by the present work has reported outstanding results in the design of high-performance decision support systems for the aforementioned areas. The future of digital dentistry goes through the design of integrated approaches providing personalized treatments to patients. In addition, esthetic dentistry can benefit from those advances by developing models allowing a complete characterization of tooth color, enhancing the accuracy of dental restorations.

CLINICAL SIGNIFICANCE

The use of AI and ML has an increasing impact on the dental profession and is complementing the development of digital technologies and tools, with a wide application in treatment planning and esthetic dentistry procedures.

Localization of cementoenamel junction in intraoral ultrasonographs with machine learning

OBJECTIVE

Our goal was to automatically identify the cementoenamel junction (CEJ) location in ultrasound images using deep convolution neural networks (CNNs).

METHODS

Three CNNs were evaluated using 1400 images and data augmentation. The training and validation were performed by an experienced nonclinical rater with 1000 and 200 images, respectively. Four clinical raters with different levels of experience with ultrasound tested the networks using the other 200 images. In addition to the comparison of the best approach with each rater, we also employed the simultaneous truth and performance level estimation (STAPLE) algorithm to estimate a ground truth based on all labelings by four clinical raters. The final CEJ location estimate was obtained by taking the first moment of the posterior probability computed using the STAPLE algorithm. The study also computed the machine learning-measured CEJ-alveolar bone crest distance.

RESULTS

Quantitative evaluations of the 200 images showed that the comparison of the best approach with the STAPLE-estimate yielded a mean difference (MD) of 0.26 mm, which is close to the comparison with the most experienced nonclinical rater (MD=0.25 mm) but far better than the comparison with clinical raters (MD=0.27-0.33 mm). The machine learning-measured CEJ-alveolar bone crest distances correlated strongly (R = 0.933, p < 0.001) with the manual clinical labeling and the measurements were in good agreement with the 95% Bland-Altman's lines of agreement between -0.68 and 0.57 mm.

CONCLUSIONS

The study demonstrated the feasible use of machine learning methodology to localize CEJ in ultrasound images with clinically acceptable accuracy and reliability. Likelihood-weighted ground truth by combining multiple labels by the clinical experts compared favorably with the predictions by the best deep CNN approach.

CLINICAL SIGNIFICANCE

Identification of CEJ and its distance from the alveolar bone crest play an important role in the evaluation of periodontal status. Machine learning algorithms can learn from complex features in ultrasound images and have potential to provide a reliable and accurate identification in subsecond. This will greatly assist dental practitioners to provide better point-of-care to patients and enhance the throughput of dental care.

Deep learning for categorization of endodontic lesion based on radiographic periapical index scoring system

OBJECTIVE

The study aimed to apply convolutional neural network (CNN) to score periapical lesion on an intraoral periapical radiograph (IOPAR) based on the periapical index (PAI) scoring system.

MATERIALS AND METHODS

A total of 3000 periapical root areas (PRA) on 1950 digital IOPAR were pre-scored by three endodontists. This data was used to train the CNN model-"YOLO version 3." A total of 450 PRA was used for validation of the model. Data augmentation techniques and model optimization were applied. A total of 540 PRA on 250 digital IOPAR was used to test the performance of the CNN model.

RESULTS

A total of 303 PRA (56.11%) exhibited true prediction. PAI score 1 showed the highest true prediction (90.9%). PAI scores 2 and 5 exhibited the least true prediction (30% each). PAI scores 3 and 4 had a true prediction of 60% and 71%, respectively. When the scores were dichotomized as healthy (PAI scores 1 and 2) and diseased (PAI score 3, 4, and 5), the model achieved a true prediction of 76.6% and 92%, respectively. The model exhibited a 92.1% sensitivity/recall, 76% specificity, 86.4% positive predictive value/precision, and 86.1% negative predictive value. The accuracy, F1 score, and Matthews correlation coefficient were 86.3%, 0.89, and 0.71, respectively.

CONCLUSION

The CNN model trained on a limited amount of IOPAR data showed potential for PAI scoring of the periapical lesion on digital IOPAR.

CLINICAL RELEVANCE

An automated system for PAI scoring is developed that would potentially benefit clinician and researchers.

Computer-Assisted Detection of Cemento-Enamel Junction in Intraoral Ultrasonographs

The cemento-enamel junction (CEJ) is an important reference point for various clinical measurements in oral health assessment. Identifying CEJ in ultrasound images is a challenging task for dentists. In this study, a computer-assisted detection method is proposed to identify the CEJ in ultrasound images, based on the curvature change of the junction outlining the upper edge of the enamel and cementum at the cementum–enamel intersection. The technique consists of image preprocessing steps for image enhancement, segmentation, and edge detection to locate the boundary of the enamel and cementum. The effects of the image preprocessing and the sizes of the bounding boxes enclosing the CEJ were studied. For validation, the algorithm was applied to 120 images acquired from human volunteers. The mean difference of the best performance between the proposed method and the two raters’ measurements was an average of 0.25 mm with reliability ≥ 0.98. The proposed method has the potential to assist dental professionals in CEJ identification on ultrasonographs to provide better patient care.

Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning

Accurate segmentation of the jaw (i.e., mandible and maxilla) and the teeth in cone beam computed tomography (CBCT) scans is essential for orthodontic diagnosis and treatment planning. Although various (semi)automated methods have been proposed to segment the jaw or the teeth, there is still a lack of fully automated segmentation methods that can simultaneously segment both anatomic structures in CBCT scans (i.e., multiclass segmentation). In this study, we aimed to train and validate a mixed-scale dense (MS-D) convolutional neural network for multiclass segmentation of the jaw, the teeth, and the background in CBCT scans. Thirty CBCT scans were obtained from patients who had undergone orthodontic treatment. Gold standard segmentation labels were manually created by 4 dentists. As a benchmark, we also evaluated MS-D networks that segmented the jaw or the teeth (i.e., binary segmentation). All segmented CBCT scans were converted to virtual 3-dimensional (3D) models. The segmentation performance of all trained MS-D networks was assessed by the Dice similarity coefficient and surface deviation. The CBCT scans segmented by the MS-D network demonstrated a large overlap with the gold standard segmentations (Dice similarity coefficient: 0.934 ± 0.019, jaw; 0.945 ± 0.021, teeth). The MS-D network–based 3D models of the jaw and the teeth showed minor surface deviations when compared with the corresponding gold standard 3D models (0.390 ± 0.093 mm, jaw; 0.204 ± 0.061 mm, teeth). The MS-D network took approximately 25 s to segment 1 CBCT scan, whereas manual segmentation took about 5 h. This study showed that multiclass segmentation of jaw and teeth was accurate and its performance was comparable to binary segmentation. The MS-D network trained for multiclass segmentation would therefore make patient-specific orthodontic treatment more feasible by strongly reducing the time required to segment multiple anatomic structures in CBCT scans.

Artificial Intelligence for Fast and Accurate 3-Dimensional Tooth Segmentation on Cone-beam Computed Tomography

INTRODUCTION

Tooth segmentation on cone-beam computed tomographic (CBCT) imaging is a labor-intensive task considering the limited contrast resolution and potential disturbance by various artifacts. Fully automated tooth segmentation cannot be achieved by merely relying on CBCT intensity variations. This study aimed to develop and validate an artificial intelligence (AI)-driven tool for automated tooth segmentation on CBCT imaging.

METHODS

A total of 433 Digital Imaging and Communications in Medicine images of single- and double-rooted teeth randomly selected from 314 anonymized CBCT scans were imported and manually segmented. An AI-driven tooth segmentation algorithm based on a feature pyramid network was developed to automatically detect and segment teeth, replacing manual user contour placement. The AI-driven tool was evaluated based on volume comparison, intersection over union, the Dice score coefficient, morphologic surface deviation, and total segmentation time.

RESULTS

Overall, AI-driven and clinical reference segmentations resulted in very similar segmentation volumes. The mean intersection over union for full-tooth segmentation was 0.87 (±0.03) and 0.88 (±0.03) for semiautomated (SA) (clinical reference) versus fully automated AI-driven (F-AI) and refined AI-driven (R-AI) tooth segmentation, respectively. R-AI and F-AI segmentation showed an average median surface deviation from SA segmentation of 9.96 μm (±59.33 μm) and 7.85 μm (±69.55 μm), respectively. SA segmentations of single- and double-rooted teeth had a mean total time of 6.6 minutes (±76.15 seconds), F-AI segmentation of 0.5 minutes (±8.64 seconds, 12 times faster), and R-AI segmentation of 1.2 minutes (±33.02 seconds, 6 times faster).

CONCLUSIONS

This study showed a unique fast and accurate approach for AI-driven automated tooth segmentation on CBCT imaging. These results may open doors for AI-driven applications in surgical and treatment planning in oral health care.

Mussel-Inspired Adhesive Double-Network Hydrogel for Intraoral Ultrasound Imaging

Periodontal diseases could be diagnosed through intraoral ultrasound imaging with the advantages of simple operation procedures, low cost, and low safety risks. A couplant is normally placed between transducers and tissues for better ultrasound image quality. If applied intraorally, the couplants should possess good stability in water and robust mechanical properties, as well as strong adhesiveness to transducers and tissues. However, commercial couplants, such as Aquaflex (AF) cannot fulfill these requirements. In this work, inspired by the mussel adhesion mechanism, we reported a poly(vinyl alcohol)-polyacrylamide-polydopamine (PVA-PAM-PDA) hydrogel synthesized by incorporating PDA into the PAM-PVA double-network for intraoral ultrasound imaging. The hydrogel maintains good stability in water as well as exceptional mechanical properties and can adhere to different substrates (i.e., metal, glass, and porcine skin) without losing the original adhesion strength after multiple adhesion-strip cycles. Besides, when applied to porcine mandibular incisor imaging, the PVA-PAM-PDA hydrogel possesses good image quality for diagnosis as AF does. This work provides practical insights into the fabrication of multifunctional hydrogel-based interfaces between human tissues and medical devices for disease diagnosis applications.