Characteristics of subgingival calculus detection by multiphoton fluorescence microscopy

Deep learning and sub-band fluorescence imaging-based method for caries and calculus diagnosis embeddable on different smartphones

Popularizing community and home early caries screening is essential for caries prevention and treatment. However, a high-precision, low-cost, and portable automated screening tool is currently lacking. This study constructed an automated diagnosis model for dental caries and calculus using fluorescence sub-band imaging combined with deep learning. The proposed method is divided into two stages: the first stage collects imaging information of dental caries in different fluorescence spectral bands and obtains six-channel fluorescence images. The second stage employs a 2-D-3-D hybrid convolutional neural network combined with the attention mechanism for classification and diagnosis. The experiments demonstrate that the method has competitive performance compared to existing methods. In addition, the feasibility of transferring this approach to different smartphones is discussed. This highly accurate, low-cost, portable method has potential applications in community and at-home caries detection.

Machine learning-based automatic identification and diagnosis of dental caries and calculus using hyperspectral fluorescence imaging

PURPOSE

Precise diagnosis and identification of early dental caries facilitates timely intervention and reverses the progression of the disease. Developing an objective, accurate and rapid caries and calculus automatic identification method advances clinical application and facilitates the promotion and screening of oral health in the community and family.

METHODS

In this study, based on 122 dental surfaces labeled by professional dentists, hyperspectral fluorescence imaging combined with machine learning algorithms was employed to construct a model for simultaneously diagnosing dental caries and calculus. Model trained by fusion features based on spectra, textures, and colors with the integrated learning algorithm has better performance and stronger generalization capabilities.

RESULTS

The experimental results showed that the diagnostic model's accuracy, sensitivity, and specificity for identifying four different caries stages and calculus were 98.6%, 98.4%, and 99.6%, respectively.

CONCLUSIONS

The proposed method can evaluate the whole tooth surface at the pixel level and provides discrimination enhancement and a quantitative parameter, which is expected to be a new approach for early caries diagnosis.

Image-Guided Ablation of Dental Calculus From Root Surfaces Using a DPSS Er:YAG Laser

BACKGROUND AND OBJECTIVES

Recent studies have demonstrated that near-infrared (IR) imaging can be used to acquire high-contrast images of root caries and calculus on the root surfaces of extracted teeth at wavelengths longer than 1450 nm. The purpose of this study was to determine if image-guided laser ablation can be used to selectively remove calculus from tooth surfaces with minimal damage to the underlying sound cementum and dentin.

MATERIALS AND METHODS

In this study, sequential near-IR images at 1500-1700 nm were used to guide a diode-pumped (DPSS) Er:YAG laser for the removal of calculus from the root surfaces of 10 extracted teeth. The selectivity of removal was assessed using digital microscopy, optical coherence tomography, and surface profilometry.

RESULTS

Calculus was removed rapidly with minimal damage to the underlying sound cementum and dentin. Image-guided ablation achieved high-selectivity, the mean volume of calculus removal was more than 27 times higher than the mean loss of cementum.

CONCLUSIONS

We have demonstrated that near-IR image-guided laser ablation can be used for the selective removal of calculus from root surfaces ex vivo. Additionally, we have demonstrated that a diode-pumped solid-state Er:YAG laser is well suited for selective removal. Lasers Surg. Med. © 2019 Wiley Periodicals, Inc.

Cross-polarization reflectance imaging of root caries and dental calculus on extracted teeth at wavelengths from 400 to 2350 nm

The identification of root caries and calculus on tooth roots is of increasing importance with our aging population. Exposed root surfaces are often impacted by erosion, abrasion, calculus and staining which can make the identification and management of caries challenging. Identification of dental calculus on root surfaces and verification of its removal is also important for patient education and to decrease susceptibility to caries and periodontal disease. The objective of this study was to determine how the contrast of root caries lesions and dental calculus varies with wavelength in the visible to near-infrared. The contrast of suspected root caries lesions and dental calculus on 30 extracted teeth was measured using cross-polarization reflectance measurements at wavelengths from 400 to 2350 nm. Significantly higher (P < 0.05) lesion contrast was measured at wavelengths greater than 1460 nm. Stains interfered significantly at wavelengths less than 850 nm yielding non-diagnostic contrast for root caries lesions. We postulate that the high absorption of water at longer wavelengths reduced the light scattering from the surrounding and underlying normal dentin, thus increasing the lesion contrast. This study indicates that wavelengths beyond 1400 nm are advantageous for imaging calculus and caries lesions on root surfaces due to the high contrast and lack of interference from stain.

The association of tooth scaling and decreased cardiovascular disease: a nationwide population-based study

OBJECTIVE

Poor oral hygiene has been associated with an increased risk for cardiovascular disease. However, the association between preventive dentistry and cardiovascular risk reduction has remained undetermined. The aim of this study is to investigate the association between tooth scaling and the risk of cardiovascular events by using a nationwide, population-based study and a prospective cohort design.

METHODS

Our analyses were conducted using information from a random sample of 1 million persons enrolled in the nationally representative Taiwan National Health Insurance Research Database. Exposed individuals consisted of all subjects who were aged ≥ 50 years and who received at least 1 tooth scaling in 2000. The comparison group of non-exposed persons consisted of persons who did not undergo tooth scaling and were matched to exposed individuals using propensity score matching by the time of enrollment, age, gender, history of coronary artery disease, diabetes, hypertension, and hyperlipidemia.

RESULTS

During an average follow-up period of 7 years, 10,887 subjects who had ever received tooth scaling (exposed group) and 10,989 age-, gender-, and comorbidity-matched subjects who had not received tooth scaling (non-exposed group) were enrolled. The exposed group had a lower incidence of acute myocardial infarction (1.6% vs 2.2%, P<.001), stroke (8.9% vs 10%, P=.03), and total cardiovascular events (10% vs 11.6%, P<.001) when compared with the non-exposed group. After multivariate analysis, tooth scaling was an independent factor associated with less risk of developing future myocardial infarction (hazard ratio [HR], 0.69; 95% confidence interval [CI], 0.57-0.85), stroke (HR, 0.85; 95% CI, 0.78-0.93), and total cardiovascular events (HR, 0.84; 95% CI, 0.77-0.91). Furthermore, when compared with the non-exposed group, increasing frequency of tooth scaling correlated with a higher risk reduction of acute myocardial infarction, stroke, and total cardiovascular events (P for trend<.001).

CONCLUSION

Tooth scaling was associated with a decreased risk for future cardiovascular events.