Cone-Beam Computed Tomography Findings in the Early Diagnosis of Calcified Atheromas

Detection of extracranial and intracranial calcified carotid artery atheromas in cone beam computed tomography using a deep learning convolutional neural network image segmentation approach

OBJECTIVE

We leveraged an artificial intelligence deep-learning convolutional neural network (DL CNN) to detect calcified carotid artery atheromas (CCAAs) on cone beam computed tomography (CBCT) images.

STUDY DESIGN

We obtained 137 full-volume CBCT scans with previously diagnosed CCAAs. The DL model was trained on 170 single axial CBCT slices, 90 with extracranial CCAAs and 80 with intracranial CCAAs. A board-certified oral and maxillofacial radiologist confirmed the presence of each CCAA. Transfer learning through a U-Net-based CNN architecture was utilized. Data allocation was 60% training, 10% validation, and 30% testing. We determined the accuracy of the DL model in detecting CCAA by calculating the mean training and validation accuracy and the area under the receiver operating characteristic curve (AUC). We reserved 5 randomly selected unseen full CBCT volumes for final testing.

RESULTS

The mean training and validation accuracy of the model in detecting extracranial CCAAs was 92% and 82%, respectively, and the AUC was 0.84 with 1.0 sensitivity and 0.69 specificity. The mean training and validation accuracy in detecting intracranial CCAAs was 61% and 70%, respectively, and the AUC was 0.5 with 0.93 sensitivity and 0.08 specificity. Testing of full-volume scans yielded an AUC of 0.72 and 0.55 for extracranial and intracranial CCAAs, respectively.

CONCLUSION

Our DL model showed excellent discrimination in detecting extracranial CCAAs on axial CBCT images and acceptable discrimination on full-volumes but poor discrimination in detecting intracranial CCAAs, for which further research is required.

Orthopantomography Detection of Atheroma Plaques and Its Relationship with Periodontal Disease and Missing Teeth

Background

The aim of this study is to determine the atheromatous plaques' prevalence in orthopantomography and their relationship with periodontal disease and missing teeth. Material and Methods. Orthopantomographs of 1,254 patients over 18 years of age from Clínica Arlanza in Lerma, Burgos, were examined between 2017 and 2021. A Planmeca ProOne® orthopantomograph (68 kV, 7 mA, and 10 sg) was used. Statistical analysis was carried out using SPSS Statistics® version 25. The results of the categorical variables were described as frequencies (%). Contingency tables were made with the qualitative variables, and the chi-square test was applied to study the relationship among them. The measure of statistical power used was the relative risk (RR), which was described with its respective 95% confidence interval (CI). Student's t-test was applied to study the relationship between the qualitative variable "presence or absence of atheroma plaque" and the quantitative variable "number of teeth."

Results

A 6.2% prevalence of atheroma plaques was obtained from 1,079 selected X-rays. The risk in patients with periodontal disease increased as periodontal disease worsened. The risk in patients with periodontal disease increased as periodontal disease worsened as follows: healthy patients vs. periodontal patients with less than 30% bone loss in radiography: RR 0.434, 95% CI 0.181-1.041, p = 0.053 healthy patients vs. patients with between 30%-60% bone loss: RR 0.177, 95% CI 0.075-0.418, p < 0.05 healthy patients vs. patients with more than 60% bone loss: RR 0.121, 95% CI 0.041-0.355, p < 0.05. Patients with calcifications on their orthopantomograms had a lower mean teeth number (20.9 teeth) compared to patients without calcifications (24 teeth), which was statistically significant, t (1077) = -3.125, p < 0.05.

Conclusions

Orthopantomography can be considered a screening method to detect patients at increased cardiovascular risk who are referred for individualized study. It is important to continue research to know the real significance of these findings. Dentists should be aware of the importance of our work in our patients' systemic health.

Incidental findings in cone beam computed tomography volumes: Calcified head-and-neck atheromas detected during dental evaluation

PURPOSE

Atheromas can be detected incidentally in routine dental cone beam computed tomography (CBCT) images. This study aims to assess prevalence and risk factors associated with these vascular lesions.

MATERIALS AND METHODS

The maxillofacial CBCTs of 458 subjects were evaluated and divided into 4 groups based on the presence of calcified atheroma: subjects with no calcified atheroma, subjects with intracranial calcified atheroma (ICA), subjects with extracranial calcified atheroma (ECA), and subjects exhibiting combined lesions. Age, sex, medical conditions, family history, and size were documented. Analysis of variance followed by a multiple comparison test was used for data satisfying parametric test assumptions. Chi-squared tests were used to assess categorical data. The Spearman Rho test was used to assess the correlation between the incidence of calcified atheroma and subjects' medical condition.

RESULTS

Of the 458 CBCTs evaluated, 29.90% presented with calcified atheroma. Calcified atheroma prevalence was significantly higher in older patients versus younger patients (p = 0.004) and in males compared to females (p = 0.004). Males were more likely to have the combination of ICA and ECA, whereas females were more likely to have ICA alone (p ≤ 0.040). Patients with calcified atheroma were significantly more likely to have a history of hyperlipidemia (p = 0.001), hypertension (p = 0.001), and myocardial infarction/coronary artery diseases (p = 0.001). Overall, patients exhibiting both intracranial and extracranial lesions were more likely to have cardiovascular risk factors (p = 0.001).

CONCLUSION

Incidentally detected calcified atheromas in CBCTs are common. Subjects with combined atheroma lesions are at higher risk for cardiovascular disease. The diagnosis of incidental calcified atheromas in CBCT's warrants early referral to medical specialists, especially if there is no medical history of existing cardiovascular disease.

The relationship between diabetes and carotid artery calcifications detected via dental cone-beam computed tomography in patients undergoing implant treatment planning

BACKGROUND

The authors investigated the association between carotid artery calcifications (CACs) detected incidentally on dental cone-beam computed tomographic scans and positive diabetes status.

METHODS

Two patient groups were identified retrospectively from a patient database: positive for CACs based on cone-beam computed tomographic scans and positive diabetes status. In addition to demographic characteristics, data including diabetes status and presence, type, and absence of CACs were obtained. A χ² statistical analysis was completed by means of dividing the data into sets of known CAC and known history of diabetes; significance level was P < .05.

RESULTS

To satisfy the a priori power analysis, records from 2010 through 2021 were used. For the positive CAC group, data were obtained from 288 patients (171 men, 117 women) and 68 patients (24%) had a positive diabetes status at the time of cone-beam computed tomography (P < .001). There were significantly more male patients (n = 47) than female patients (n = 21) with diabetes (χ² = 9.9; P = .002). For the positive diabetes group, data were obtained from 225 patients (149 men, 76 women), and 100 patients (44%) had an identifiable CAC. There were significantly more male patients (n = 73) than female patients (n = 27) with CAC (χ² = 21.2; P < .001).

CONCLUSIONS

There was a significant relationship to diabetes for patients with CACs, indicating potential undiagnosed diabetes. Male patients with diabetes are significantly more at risk of developing CACs.

PRACTICAL IMPLICATIONS

People with CAC may be at risk of having undiagnosed diabetes and require heightened awareness during implant treatment planning.

Association between internal carotid artery calcifications detected as incidental findings and clinical characteristics associated with atherosclerosis: A dental volumetric tomography study

PURPOSE

To evaluate the presence of calcifications in the internal carotid artery (ICA) in cone-beam computed tomography (CBCT), and to verify the association of these findings with sex, age, dental condition, and risk factors associated with vascular disorders.

METHODS

The CBCT scans used in this study were obtained from the database of a private dental clinic requested for the planning of rehabilitation with dental implants. The selection criteria were patients aged 40 years and above. Out of a pool of 1176 CBCT examinations, a total of 284 scans of adult patients were evaluated by two blinded observers. Data were collected from patients' medical records.

RESULTS

ICA calcifications were present in 63.0% of the examinations. Most calcifications were in the intracranial pathway (166). Despite being present in a smaller number 57 (C1), extracranial calcifications were more severe. Spearman's ρ coefficients (rS) indicated that the number of missing teeth was directly associated with the presence of calcifications (p = 0.042) and severity (p = 0.020). The age variable also had a direct relationship with the presence of calcifications (p ≤ 0.0001), increasing its frequency and severity over the years. In addition, hypertension (p = 0.036) and use of antihypertensive drugs (p = 0.015) were directly associated.

CONCLUSIONS

There is a high occurrence of ICA calcifications in CBCT as incidental findings in adult patients, and it is directly associated with age, number of missing teeth and hypertension.

Evaluation of mandibular calcification on 3D volume images

Objectives

Bone and soft-tissue calcifications are often coincidentally diagnosed on digital panoramic radiographs (DPRs). As the use of three-dimensional (3D) images has increased in the past decade for diagnostics in the mandibular region, we evaluated 3D volume images derived from 2D panoramic images to determine if this method is suitable for early detection of calcifications in this region.

Methods

In this study, three investigators retrospectively and independently evaluated 822 DPRs. If one or more calcifications were present, the 3D volume image from that patient was retrospectively evaluated to confirm the incidental findings. A radiographic system with a low-dose mode and a high-resolution 3D-image function was used. The investigators focussed on the most common calcifications, including tonsilloliths (TL), idiopathic osteosclerosis (IO) of the mandible, carotid artery calcifications (CAC), calcified submandibular lymph nodes (hereafter, CSL), and sialoliths of the submandibular salivary gland (SSG).

Results

One or more calcifications were identified in 415 (50.5%) DPRs. In total, 718 calcifications were detected, 30.2% of which were TL, 16.3% IO, 11.3% CAC, 8.8% CSL, and 1.7% SSG. Only 287 (39.97 %) of the calcifications were confirmed on 3D volume images; of these, 29.2% were TL, 58.5% IO, 0.2% CAC, and 1.4% SSG. No CSLs were detected.

Conclusions

Not all areas shown on the DPRs were visible in the retrospectively obtained 3D volume images. Whereas DPRs are used to diagnose calcifications such as IO, TL, SSG, CAC, and CSL, the 3D volume images were only useful for confirming the existence of IO, TL, and SSG calcifications.