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

Machine Learning for Automated Identification of Anatomical Landmarks in Ultrasound Periodontal Imaging

OBJECTIVES

To identify landmarks in ultrasound periodontal images and automate the image-based measurements of gingival recession (iGR), gingival height (iGH), and alveolar bone level (iABL) using machine learning.

METHODS

We imaged 184 teeth from 29 human subjects. The dataset included 1580 frames for training and validating the U-Net CNN machine learning model, and 250 frames from new teeth that were not used in training for testing the generalization performance. The predicted landmarks including the tooth, gingiva, bone, gingival margin (GM), cementoenamel junction (CEJ), and alveolar bone crest (ABC), were compared to manual annotations. We further demonstrated automated measurements of the clinical metrics iGR, iGH, and iABL.

RESULTS

Over 98% of predicted GM, CEJ, and ABC distances are within 200 µm of the manual annotation. Bland-Altman analysis revealed biases (bias of machine learning versus ground truth) of -0.1 µm, -37.6 µm, and -40.9 µm, with 95% limits of agreement of [-281.3, 281.0] µm, [-203.1, 127.9] µm, and [-297.6, 215.8] µm for iGR, iGH, and iABL, respectively, when compared to manual annotations. On the test dataset, the biases were 167.5 µm, 40.1 µm, and 78.7 µm with 95% CIs of [-1175, 1510] µm, [-910.3, 990.4] µm, and [-1954, 1796] µm for iGR, iGH, and iABL, respectively.

CONCLUSIONS

The proposed machine learning model demonstrates robust prediction performance, with the potential to enhance the efficiency of clinical periodontal diagnosis by automating landmark identification and clinical metrics measurements.

Ultrasound identification of the cementoenamel junction and clinical correlation through ex vivo analysis

Accurately identifying periodontal landmarks via acoustic imaging is increasingly important. Here, we evaluated the accuracy of cementoenamel junction (CEJ) identification using ultrasound by comparing it to clinical methods in 153 extracted human teeth. The distance between the CEJ to a reference point was measured using two clinical methods (visual examination and tactile sensation) as well as ultrasound imaging. Statistical analyses were performed across all teeth and sub-groups, including tooth types (incisors, cuspids, and molars/premolars), and two classifications: A- vs. B- (visually detectable or undetectable CEJ, respectively); and CL-S vs. CL-D (shallow or deep cervical lesions). In A- or CL-S teeth, ultrasound measurements highly agreed with clinical measurements, showing a 1.72-mm 95% CI for A- and 1.99-mm 95% CI for CL-S compared to visual examination, and a 1.77-mm 95% CI for A- and a 2.10-mm 95% CI for CL-S compared to tactile sensation, respectively. For 80% of A- and 76% of CL-S teeth, the difference between ultrasound and visual examination was within ± 20%. For 81% of A- and 80% of CL-S teeth, the difference between ultrasound and tactile sensation was within ± 20%. The variance of ultrasound versus clinical CEJ identifications showed a significant correlation (r = 0.6607) to the cervical lesion depth. The errors between ultrasound and clinical measurements show no significant bias across different tooth types.

The Stresses and Deformations in the Abfraction Lesions of the Lower Premolars Studied by the Finite Element Analyses: Case Report and Review of Literature

BACKGROUND

The purpose of the study was to investigate the behavior of hard dental structures of the teeth with abfraction lesions when experimental occlusal loads were applied.

METHODS

A 65-year-old patient came to the dentist because she had painful sensitivity in the temporomandibular joints and the lower right premolars. The patient was examined, and cone-beam computed tomography (CBCT) of the orofacial area was indicated. The data provided from the CBCT were processed with Mimics Innovation Suite 17 software to create the desired anatomical area in 3D format. Then, the structural calculation module was used in order to perform a finite element analysis of the lower right premolar teeth. A focused review of articles published between 2014 and 2023 from specialty literature regarding the FEA of premolars with abfraction lesions was also conducted.

RESULTS

The parcel area and the cervical third of the analyzed premolars proved to be the most vulnerable areas under the inclined direction of occlusal loads. The inclined application of experimental loads induced 3-4 times higher maximum shears, stresses, and deformations than the axial application of the same forces.

CONCLUSIONS

FEA can be used to identify structural deficiencies in teeth with abfractions, a fact that is particularly important during dental treatments to correct occlusal imbalances.

Evaluation of Abfraction Lesions Restored with Three Dental Materials: A Comparative Study

BACKGROUND

Abfraction lesions are manifested as damage to hard tissues in the cervical area of dental crowns. The study aimed to assess the direct restoration of abfraction lesions according to the modified United States Public Health Service (USPHS) criteria for 24 months. The restorations were accomplished with Fuji Bulk-GC, Omnichroma Flow-Tokuyama, and Beautifil® II-Shofu dental materials, and the therapy was or was not associated with wearing thermoformed mouthguards.

METHODS

From the 53 selected and analyzed patients (n = 53), 28 patients (with restorations of abfraction lesions) belonged to the 1st group and 25 patients (with 105 restorations, who also wore mouthguards) belonged to the 2nd group. Blind determination assessments were effectuated at baseline and after 2, 6, 12, 18, and 24 months. Results showed that, regardless of the rating score, there are no significant statistical differences in the evaluation criteria between the two groups of patients Conclusions: For each material, the scores of USPHS criterion presented good clinical performances after 24 months, with no significant statistical differences between the fillings and the applied therapy in the two groups of patients.

Ultrasound Imaging of the Periodontium Complex: A Reliability Study

Background

Ultrasonography is a noninvasive, low-cost diagnostic tool widely used in medicine. Recent studies have demonstrated that ultrasound imaging might have the potential to be used intraorally to assess periodontal biomarkers.

Objectives

To evaluate the reliability of interlandmark distance measurements on intraoral ultrasound images of the periodontal tissues.

Materials and Methods

Sixty-four patients from the graduate periodontics (n = 33) and orthodontics (n = 31) clinics were recruited. A 20 MHz handheld intraoral ultrasound transducer was used to scan maxillary and mandibular incisors, canines, and premolars. Distances between the alveolar bone crest and cementoenamel junction (ABC-CEJ), gingival thickness (GT), and alveolar bone thickness (ABT) were measured by 3 raters. The intercorrelation coefficient (ICC) and mean absolute deviation (MAD) were calculated among and between the raters. Raters also scored images according to quality.

Results

The ICC scores for intrarater reliability were 0.940 (0.932-0.947), 0.953 (0.945-0.961), and 0.859 (0.841-0.876) for ABC-CEJ, GT, and ABT, respectively. The intrarater MAD values were 0.023 (±0.019) mm, 0.014 (±0.005) mm, and 0.005 (±0.003) mm, respectively. The ICC scores for interrater reliability were 0.872 (95% CI: 0.836-0.901), 0.958 (95% CI: 0.946-0.968), and 0.836 (95% CI: 0.789-0.873) for ABC-CEJ, GT, and ABT, respectively. The interrater MAD values were 0.063 (±0.029) mm, 0.023 (±0.018) mm, and 0.027 (±0.012) mm, respectively.

Conclusions

The present study showed the high reliability of ultrasound in both intrarater and interrater assessments. Results suggest there might be a potential use of intraoral ultrasound to assess periodontium.

Assessment of Negative Gingival Recession: A Critical Component of Periodontal Diagnosis

Accurate measurement of negative gingival recession (GR) is essential to accurately determine the clinical attachment loss, which leads to an accurate diagnosis and optimal therapy of periodontal disease. However, the accuracy of measuring the negative GR has been shown to be low and highly variable between examiners. The position of the gingiva margin in relation to the cemento-enamel junction (CEJ) varies among different stages of passive eruption. The amount of negative GR is about 2 mm on average at the mid-facial sites and ranges from 2 to 3.5 mm at interproximal sites in periodontally healthy patients. Some other clinical conditions may change the gingival dimension coronal to the CEJ, such as altered passive eruption and gingival enlargement. In addition to the traditional approach using a periodontal probe to assess the negative GR, nowadays dental ultrasound imaging may be able to assist in accurately measuring the amount of negative GR. This narrative review will discuss the existing evidence of the dimension of dentogingival tissue and the clinical assessment of negative GR using different clinical tools.