Detecting white spot lesions on dental photography using deep learning: A pilot study

2021 ◽  
Vol 107 ◽  
pp. 103615
Author(s):  
Haitham Askar ◽  
Joachim Krois ◽  
Csaba Rohrer ◽  
Sarah Mertens ◽  
Karim Elhennawy ◽  
...  
Keyword(s):  
Deep Learning ◽  
Pilot Study ◽  
White Spot ◽  
White Spot Lesions ◽  
Dental Photography

Comparision of two fluoride varnishes for controlling white spot lesions. Randomized clinical trial

2017 ◽  
Vol 16 (1) ◽  
Author(s):  
Jesús Alberto Luengo - Fereira
Keyword(s):  
Clinical Trial ◽  
Randomized Clinical Trial ◽  
White Spot ◽  
Controlled Clinical Trial ◽  
White Spot Lesions ◽  
Randomized Controlled Clinical Trial ◽  
Chi Square ◽  
Randomized Controlled ◽  
Anterior Teeth ◽  
The Mean

Objective: To compare two fluorinated varnishes for the control of white spot lesions.Material and Methods: A randomized controlled clinical trial was conducted. A total of 103 active whitespot lesions on permanent upper anterior teeth from 24 patients, aged 7 to 9 years were randomly assigned totwo groups, G1: Duraphat® (n=52) and G2: DuraShield® (n=51). Weekly applications were perform for fourconsecutive weeks. Fifth week the dimension, regression and activity of the lesions were evaluated. Student’sT test, Wilcoxon Ranks and Chi square were used at 5% significance. Results: At the end of the study, the lesion reduction was observed in 69.7%, finding significant differences(p<0.05) in the mean of the initial and final dimensions in general (2.74 mm to 1.91 mm) and in each group, G1(2.84 mm to 2.03 mm), G2 (2.64 mm to 1.78 mm). In the activity of the lesions, it was found in the G1, 12 active and6 inactive lesions; while in G2, there were 14 active and 29 inactive; these differences were significant (p<0.05). Conclusions: The two evaluated products showed similar clinical efficacy in the remineralization of activewhite spot lesions after 4 weeks of therapy.

Endoscopic prediction of submucosal invasion in Barrett’s cancer with the use of Artificial Intelligence: A pilot Study

Endoscopy ◽  
2020 ◽  
Author(s):  
Alanna Ebigbo ◽  
Robert Mendel ◽  
Tobias Rückert ◽  
Laurin Schuster ◽  
Andreas Probst ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Pilot Study ◽  
White Light ◽  
Submucosal Invasion ◽  
Learning System ◽  
Endoscopic Images ◽  
Barrett’S Cancer ◽  
Significant Difference ◽  
Sensitivity Specificity

Background and aims: The accurate differentiation between T1a and T1b Barrett’s cancer has both therapeutic and prognostic implications but is challenging even for experienced physicians. We trained an Artificial Intelligence (AI) system on the basis of deep artificial neural networks (deep learning) to differentiate between T1a and T1b Barrett’s cancer white-light images. Methods: Endoscopic images from three tertiary care centres in Germany were collected retrospectively. A deep learning system was trained and tested using the principles of cross-validation. A total of 230 white-light endoscopic images (108 T1a and 122 T1b) was evaluated with the AI-system. For comparison, the images were also classified by experts specialized in endoscopic diagnosis and treatment of Barrett’s cancer. Results: The sensitivity, specificity, F1 and accuracy of the AI-system in the differentiation between T1a and T1b cancer lesions was 0.77, 0.64, 0.73 and 0.71, respectively. There was no statistically significant difference between the performance of the AI-system and that of human experts with sensitivity, specificity, F1 and accuracy of 0.63, 0.78, 0.67 and 0.70 respectively. Conclusion: This pilot study demonstrates the first multicenter application of an AI-based system in the prediction of submucosal invasion in endoscopic images of Barrett’s cancer. AI scored equal to international experts in the field, but more work is necessary to improve the system and apply it to video sequences and in a real-life setting. Nevertheless, the correct prediction of submucosal invasion in Barret´s cancer remains challenging for both experts and AI.

Role of Saliva in Caries Models

1995 ◽  
Vol 9 (3) ◽  
pp. 235-238 ◽  
Author(s):  
W.M. Edgar ◽  
S.M. Higham
Keyword(s):  
Design Of Experiments ◽  
Crucial Role ◽  
Time Course ◽  
Therapeutic Agents ◽  
White Spot ◽  
Protective Effects ◽  
White Spot Lesions ◽  
Dynamic Effects ◽  
Full Expression

The crucial role played by the actions of saliva in controlling the equilibrium between de- and remineralization in a cariogenic environment is demonstrated by the effects on caries incidence of salivary dysfunction and by the distribution of sites of caries predilection to those where salivary effects are restricted. However, of the several properties of saliva which may confer protective effects, it is not certain which are most important. A distinction can be made between static protective effects, which act continuously, and dynamic effects, which act during the time-course of the Stephan curve. Evidence implicates salivary buffering and sugar clearance as important dynamic effects of saliva to prevent demineralization; of these, the buffering of plaque acids may predominate. Enhanced remineralization of white spot lesions may also be regarded as dynamic protective effects of saliva. Fluoride in saliva (from dentifrices, ingesta, etc.) may promote remineralization and (especially fluoride in plaque) inhibit demineralization. The design of experiments using caries models must take into account the static and dynamic effects of saliva. Some models admit a full expression of these effects, while others may exclude them, restricting the range of investigations possible. The possibility is raised that protective effects of saliva and therapeutic agents may act cooperatively.

Sign in / Sign up

Export Citation Format

Share Document