Dental wear estimation using a digital intra-oral optical scanner and an automated 3D computer vision method

Meireles, Agnes Batista; Vieira, Antônio Wilson; Corpas, Livia; Vandenberghe, Bart; Bastos, Flávia de Souza; Lambrechts, Paul; Campos, Mario Montenegro; Casas, Estevam Barbosa de Las

doi:10.1080/10255842.2015.1043627

Cited by 15 publications

(17 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, it became evident that since even the smallest morphologic changes of surfaces were relatively easy to detect. Indeed, a 3D scanner is capable of detecting volume loss from etching wear even after 1 min exposure to acid [16]. The magnification and accuracy of 3D models as well as the ability to view models from different perspectives, without any time limit, is likely to facilitate the detection of erosive wear.…”

Section: Discussionmentioning

confidence: 99%

Is a Basic Erosive Wear Examination (BEWE) reliable for recording erosive tooth wear on 3D models?

Alaraudanjoki

Saarela

Pesonen

et al. 2017

Journal of Dentistry

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Is a Basic Erosive Wear Examination (BEWE) reliable for recording erosive tooth wear on 3D models?

Alaraudanjoki

Saarela

Pesonen

et al. 2017

Journal of Dentistry

View full text Add to dashboard Cite

show abstract

“…QLF and OCT, although they can potentially be applied directly in the mouth [17], show suboptimal reproducibility in longitudinal studies involving patients [2,3,5,18,19]. The use of IOS has been recently suggested for early detection, quantification, and monitoring of tooth wear based on in vitro [20][21][22] as well as in vivo studies examining 3D data obtained directly from patients [23] or cast models [24]. Studies focusing on visual detection of early erosive tooth wear demonstrated detection with higher sensitivity using meticulous visual examination (BEWE index) on full-arch digital 3D models compared to traditional visual examination on patients [23,24].…”

Section: Introductionmentioning

confidence: 99%

“…This finding was attributed to the larger magnification and clearer image of the dentition allowed by the digital 3D model compared to the traditional visual examination directly on the patient. Other studies went further by using specific software to align multiple 3D models, from which measurements of profile or volumetric differences were obtained [20][21][22]25,26]. In order to develop an objective, automated, and reliable in vivo method for early detection and monitoring of tooth wear, the use of an accurate IOS is essential [27,28], in addition to a reliable method for 3D model alignment with minimal error [20,21,25].…”

Section: Introductionmentioning

confidence: 99%

Detecting early erosive tooth wear using an intraoral scanner system

Michou

Vannahme

Ekstrand

et al. 2020

Journal of Dentistry

View full text Add to dashboard Cite

Objectives: To assess the feasibility of detecting and monitoring early erosive tooth wear using a 3D intraoral scanner (IOS) aided by specific software. Methods: Extracted sound permanent teeth were assembled in two shortened artificial dental arches and scanned at different intervals with an IOS (3Shape TRIOS® 3) before and after an erosion/abrasion protocol (i.e. 1 h up to 24 h immersion in citric acid solution and subsequent brushing). The 3D models obtained at consecutive time points were superimposed with the baseline model using dedicated software (3Shape TRIOS® Patient Monitoring, version 2.1.1.0) and reference surface alignment. Surface profile differences between the baseline 3D model and the respective models from different time points were expressed as tooth substance loss. Non-parametric tests were used to assess the significance of tooth substance loss at different time points. Spearman's correlation was applied between the tooth substance loss at the end of each erosion/abrasion cycle and the immersion time in acid. Results: Significant tooth substance loss (0.08 mm, IQR=0.05) was detected by the software after 3 h of erosive-abrasive challenge (p=0.045). The overall median loss increased gradually from baseline to 24 h showing a strong correlation with the immersion time in acid (rs=0.971, p<0.01). Conclusions: The use of an IOS aided by specific software showed good performance for early detection and monitoring of tooth wear in vitro and has promising potential for in vivo application. Clinical significance: Detection and monitoring of early erosive tooth wear can be reliably aided by intraoral scanning supported by specific software. The measurement error and uncertainty involved in this method should be taken into consideration when interpreting the tooth substance loss measurements. Furthermore, presuming the difficulty in defining reference surfaces in vivo, clinical validation is needed to determine the system's in vivo performance.

show abstract

“…Computer vision (CV) technique (Wu, 2012a; Ji, 2014; Meireles et al, 2016) is used to help develop the CAD system that can distinguish LHLs and RHLs from HCs. The feature is defined as a piece of information for solving the computational task (here is to detect HL).…”

Section: Methodsmentioning

confidence: 99%

Wavelet Entropy and Directed Acyclic Graph Support Vector Machine for Detection of Patients with Unilateral Hearing Loss in MRI Scanning

Wang

Yang

et al. 2016

Front. Comput. Neurosci.

View full text Add to dashboard Cite

Highlights We develop computer-aided diagnosis system for unilateral hearing loss detection in structural magnetic resonance imaging.Wavelet entropy is introduced to extract image global features from brain images. Directed acyclic graph is employed to endow support vector machine an ability to handle multi-class problems.The developed computer-aided diagnosis system achieves an overall accuracy of 95.1% for this three-class problem of differentiating left-sided and right-sided hearing loss from healthy controls. Aim: Sensorineural hearing loss (SNHL) is correlated to many neurodegenerative disease. Now more and more computer vision based methods are using to detect it in an automatic way.Materials: We have in total 49 subjects, scanned by 3.0T MRI (Siemens Medical Solutions, Erlangen, Germany). The subjects contain 14 patients with right-sided hearing loss (RHL), 15 patients with left-sided hearing loss (LHL), and 20 healthy controls (HC).Method: We treat this as a three-class classification problem: RHL, LHL, and HC. Wavelet entropy (WE) was selected from the magnetic resonance images of each subjects, and then submitted to a directed acyclic graph support vector machine (DAG-SVM).Results: The 10 repetition results of 10-fold cross validation shows 3-level decomposition will yield an overall accuracy of 95.10% for this three-class classification problem, higher than feedforward neural network, decision tree, and naive Bayesian classifier.Conclusions: This computer-aided diagnosis system is promising. We hope this study can attract more computer vision method for detecting hearing loss.

show abstract

Dental wear estimation using a digital intra-oral optical scanner and an automated 3D computer vision method

Cited by 15 publications

References 21 publications

Is a Basic Erosive Wear Examination (BEWE) reliable for recording erosive tooth wear on 3D models?

Is a Basic Erosive Wear Examination (BEWE) reliable for recording erosive tooth wear on 3D models?

Detecting early erosive tooth wear using an intraoral scanner system

Wavelet Entropy and Directed Acyclic Graph Support Vector Machine for Detection of Patients with Unilateral Hearing Loss in MRI Scanning

Contact Info

Product

Resources

About