Periodontal evaluation using a non-invasive imaging method (ultrasonography)

A narrative review of imaging tools for imaging subgingival calculus

Background and Objective

The conventional method of detecting subgingival calculus involves using a periodontal probe to sense tactile differences on the dental root surface. Although efficient, this method can result in false positives and false negatives. This literature review explores alternative detection techniques that can detect subgingival calculus with improved accuracy and consistency. The accumulation of dental calculus below the gingival margin can foster periodontitis-inducing bacterial growth. Conventional methods of locating subgingival calculus are often inaccurate and highly dependent on clinician skill. This literature review evaluates techniques used to improve the accuracy of imaging and detecting subgingival calculus.

Methods

Google Scholar, PubMed and PubMed Central databases were searched for peer-reviewed original articles evaluating subgingival calculus imaging and detection techniques. A total of 46 relevant articles ranging from 1981 to 2021 were included.

Key Content and Findings

This narrative review discusses the subgingival calculus detection and imaging capabilities of periodontal endoscopy in an in vivo study and of optical coherence tomography (OCT), fluorescence spectroscopy, and differential reflectometry in in vitro settings. Each technique has unique benefits and limitations that distinguishes it from the others.

Conclusions

In vitro studies have revealed that techniques including periodontal endoscopy, OCT, fluorescence spectroscopy, or differential reflectometry allow for a more accurate diagnosis of subgingival calculus deposits in comparison to detection via periodontal probing. Despite the improved results, the common limitations of these techniques include longer operation times and expensive equipment. Further studies are needed to transition these imaging and detection methods to clinical environments.

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.

High-Frequency Ultrasound Assessment of Skin and Oral Mucosa in Metabolic Syndrome Patients-A Cross-Sectional Study

Background: Exogenous factors (such as sun exposure, smoking habits, and diet) and endogenous (inflammatory status, general diseases) have a direct influence on skin and soft tissue characteristics. The study’s objective was to assess the impact of metabolic syndrome (MS) on characteristics of skin layers in sun-exposed and non-exposed maxillofacial tissues evaluated by high-frequency ultrasound (HFU), as a potential diagnosis and monitoring tool for the aging process. Material and methods: The present study included 102 subjects (24 with MS; 78 without MS). Anthropometric parameters and disease history were recorded, and blood samples were harvested in order to assess biochemical parameters of MS. Sun-exposed skin (zygomatic region) and non-exposed oral mucosa of the lower lip were assessed using HFU (DUB^® cutis, Taberna Pro Medicum) with a 22 MHz probe. Results: Patients with cardiac disease had significantly lower values for epidermis density (p = 0.002). Gender was independently linked to the aged dermis depth (p < 0.001), aged dermis no. of px (pixels) (p < 0.001), dermis depth (p < 0.001), dermis no. of px (p < 0.001), and subcutaneous tissue density (p < 0.001). Patients with MS had thinner epidermis (p = 0.008) and thinner aged dermis (p = 0.037) when compared to non-MS subjects. Conclusion: Patients with MS had thinner epidermis and a lower epidermis number of pixels in sun-exposed skin. Women had lower epidermis density and thicker dermis in sun-exposed skin. Our study showed that HFU, as a non-invasive investigation approach, is useful to diagnose and monitor the aging process in skin and oral mucosa, correlated with skin phenotype pathological conditions.

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.

Alveolar Bone Segmentation in Intraoral Ultrasonographs with Machine Learning

The use of intraoral ultrasound imaging has received great attention recently due to the benefits of being a portable and low-cost imaging solution for initial and continuing care that is noninvasive and free of ionizing radiation. Alveolar bone is an important structure in the periodontal apparatus to support the tooth. Accurate assessment of alveolar bone level is essential for periodontal diagnosis. However, interpretation of alveolar bone structure in ultrasound images is a challenge for clinicians. This work is aimed at automatically segmenting alveolar bone and locating the alveolar crest via a machine learning (ML) approach for intraoral ultrasound images. Three convolutional neural network–based ML methods were trained, validated, and tested with 700, 200, and 200 images, respectively. To improve the robustness of the ML algorithms, a data augmentation approach was introduced, where 2100 additional images were synthesized through vertical and horizontal shifting as well as horizontal flipping during the training process. Quantitative evaluations of 200 images, as compared with an expert clinician, showed that the best ML approach yielded an average Dice score of 85.3%, sensitivity of 88.5%, and specificity of 99.8%, and identified the alveolar crest with a mean difference of 0.20 mm and excellent reliability (intraclass correlation coefficient ≥0.98) in less than a second. This work demonstrated the potential use of ML to assist general dentists and specialists in the visualization of alveolar bone in ultrasound images.