scholarly journals Automated caries detection with smartphone color photography using machine learning

2021 ◽  
Vol 27 (2) ◽  
pp. 146045822110075
Author(s):  
Duc Long Duong ◽  
Malitha Humayun Kabir ◽  
Rong Fu Kuo
Keyword(s):  
Clinical Decision Making ◽  
Clinical Decision ◽  
Clinical Diagnostics ◽  
Assessment System ◽  
Caries Detection ◽  
Support Vector ◽  
Detection Scheme ◽  
Occlusal Surfaces ◽  
Icdas Ii ◽  
Untreated Caries

Untreated caries is significant problem that affected billion people over the world. Therefore, the appropriate method and accuracy of caries detection in clinical decision-making in dental practices as well as in oral epidemiology or caries research, are required urgently. The aim of this study was to introduce a computational algorithm that can automate recognize carious lesions on tooth occlusal surfaces in smartphone images according to International Caries Detection and Assessment System (ICDAS). From a group of extracted teeth, 620 unrestored molars/premolars were photographed using smartphone. The obtained images were evaluated for caries diagnosis with the ICDAS II codes, and were labeled into three classes: “No Surface Change” ( NSC); “Visually Non-Cavitated” ( VNC); “Cavitated” ( C). Then, a two steps detection scheme using Support Vector Machine (SVM) has been proposed: “ C versus (VNC  +  NSC)” classification, and “ VNC versus NSC” classification. The accuracy, sensitivity, and specificity of best model were 92.37%, 88.1%, and 96.6% for “ C versus (VNC  +  NSC),” whereas they were 83.33%, 82.2%, and 66.7% for “ VNC versus NSC.” Although the proposed SVM system required further improvement and verification, with the data only imaged from the smartphone, it performed an auspicious potential for clinical diagnostics with reasonable accuracy and minimal cost.

scholarly journals The Performance of ICDAS-II Using Low-Powered Magnification with Light-Emitting Diode Headlight and Alternating Current Impedance Spectroscopy Device for Detection of Occlusal Caries on Primary Molars

2013 ◽  
Vol 2013 ◽  
pp. 1-5 ◽  
Author(s):  
Timucin Ari ◽  
Nilgun Ari
Keyword(s):  
Impedance Spectroscopy ◽  
Light Emitting Diode ◽  
Clinical Diagnostics ◽  
Caries Detection ◽  
Primary Molars ◽  
Occlusal Caries ◽  
Light Emitting ◽  
Occlusal Surfaces ◽  
Icdas Ii

Early detection of occlusal caries in children is challenging for the dentists, because of the morphology of pit and fissures. The aim of this study was to compare in vitro the diagnostic performance of low-powered magnification with light-emitting diode headlight (LPMLED) using ICDAS-II criteria and AC Impedance Spectroscopy (ACIS) device, on occlusal surfaces of primary molars. The occlusal surfaces of 18 extracted primary molars were examined blindly by two examiners. The teeth were sectioned and examined under light microscopy using Downer’s histological criteria as gold standard. Good to excellent inter- and intraexaminer reproducibility, higher sensitivity, specificity, and AUC values were achieved by LPMLED at D1 threshold. Also the relationship between histology and LPMLED was statistically significant. In conclusion visual aids have the potential to improve the performance of early caries detection and clinical diagnostics in children. Despite its potential, ACIS device should be considered as an adjunct method in detecting caries on primary teeth.

scholarly journals Diagnostic Drama. Use of ICDAS II and Fluorescence-Based Intraoral Camera in Early Occlusal Caries Detection: A Clinical Study

2020 ◽  
Vol 17 (8) ◽  
pp. 2937
Author(s):  
Marta Mazur ◽  
Maciej Jedliński ◽  
Artnora Ndokaj ◽  
Denise Corridore ◽  
Antonello Maruotti ◽  
...  
Keyword(s):  
Subjective Evaluation ◽  
Assessment System ◽  
Diagnostic Methods ◽  
Caries Detection ◽  
Kappa Statistics ◽  
Occlusal Caries ◽  
Posterior Teeth ◽  
Invasive Approach ◽  
Occlusal Surfaces ◽  
Icdas Ii

Background: Early diagnosis of occlusal caries is of paramount importance for a minimally invasive approach in dentistry. The aim of the present in vivo clinical prospective study was to compare the diagnostic outcomes of visual subjective evaluation between the International Caries Detection and Assessment System (ICDAS-II) and an intraoral fluorescence-based camera (VistaCam iX Proof, Dürr Dental, Bietigheim-Bissingen, Germany) for the detection of pits and fissures in early caries lesions of posterior teeth. Methods: The study included 1011 posterior teeth in 255 patients aged 13–20 years (mean age 16 ± 2.2 years). Two blinded operators evaluated all the occlusal surfaces and the first assigned an ICDAS-II code, while the second assessed the VistaCam score: sound enamel (score 0–1.2); initial enamel decay (score 1.2–1.5); dentine caries (score 1.5–3). Results: Some 283 (28%) of the assessed teeth were ICDAS-II code 0; 334 (33%) code 1; 189 (18.7%) code 2; 176 (17.4%) code 3; and 29 (2.9%) code 4. The level of agreement between the two procedures was expressed by using Cohen’s and Fleiss’ kappa statistics and performing McNemar’s test. VistaCam assessed in 513 (50.7%) sound enamel; in 292 (28.9%) initial enamel decay; and in 206 (20.4%) dentine caries. Conclusions: This comparative study showed a poor agreement between the two diagnostic methods, especially between ICDAS-II 0, 1 and 2 codes and fluorescence assessments.

scholarly journals Multi-Centre Clinical Evaluation of Photothermal Radiometry and Luminescence Correlated with International Benchmarks for Caries Detection

2017 ◽  
Vol 11 (1) ◽  
pp. 636-647 ◽  
Author(s):  
Josh D. Silvertown ◽  
Stephen H. Abrams ◽  
Koneswaran S. Sivagurunathan ◽  
Julia Kennedy ◽  
Jinseok Jeon ◽  
...  
Keyword(s):  
Clinical Situation ◽  
Study Data ◽  
Primary Objective ◽  
Assessment System ◽  
Photothermal Radiometry ◽  
Caries Detection ◽  
Occlusal Surfaces ◽  
Icdas Ii ◽  
Decayed Tooth ◽  
Tooth Surfaces

Introduction:A clinical study was initiated to investigate a caries detection device (The Canary System (CS)), based on photothermal radiometry and modulated luminescence (PTR-LUM). The primary objective of this study was to determine if PTR-LUM values (in the form of Canary Numbers; CN) correlate with International Caries Diagnostic and Assessment System (ICDAS II) scores and clinical situations. The secondary objectives of this study were to monitor the safety of PTR-LUM, and collect data to determine how CN values could be used to differentiate healthy from decayed tooth surfaces on a normalized scale.Methods:The trial was a four site, non-blinded study. Data was collected from 92 patients, resulting in 842 scanned tooth surfaces over multiple appointments. Surfaces were assessed according to ICDAS II, and further stratified into five clinical situation categories: 1) healthy surface, 2) non-cavitated white and/or brown spots; 3) caries lesions; 4) cavitation and 5) teeth undergoing remineralization therapy.CN data was analyzed separately for smooth and occlusal surfaces. Using a semi-logarithmic graph to plot raw CN (rCN) and normalized (CN) values, rCN data was normalized into a scale of 0-100.Results:Linear correlations (R2) between CN and ICDAS II groupings for smooth and occlusal surfaces were calculated as 0.9759 and 0.9267, respectively. The mean CN values derived from smooth (20.2±0.6) and occlusal (19±1.0) surfaces identified as healthy had significantly lower CN values (P<0.05) compared with the values from the other clinical situation categories. No adverse events were reported.Conclusion:The present study demonstrated the safety of PTR-LUM for clinical application and its ability to distinguish sound from carious tooth surfaces. A clear shift from the baseline in both PTR and LUM in carious enamel was observed depending on the type and nature of the lesion, and correlated to ICDAS II classification codes, which enabled the preliminary development of a Canary Scale.

Assessment of Agreement Between Human Ratings and Lexicon-Based Sentiment Ratings of Open-Ended Responses on a Behavioral Rating Scale

Assessment ◽  
2021 ◽  
pp. 107319112199646
Author(s):  
Olivia Gratz ◽  
Duncan Vos ◽  
Megan Burke ◽  
Neelkamal Soares
Keyword(s):  
Sentiment Analysis ◽  
Language Processing ◽  
Rating Scales ◽  
Clinical Decision Making ◽  
Rating Scale ◽  
Clinical Decision ◽  
Assessment System ◽  
Word Count ◽  
Positive Correlation ◽  
Sentiment Score

To date, there is a paucity of research conducting natural language processing (NLP) on the open-ended responses of behavior rating scales. Using three NLP lexicons for sentiment analysis of the open-ended responses of the Behavior Assessment System for Children-Third Edition, the researchers discovered a moderately positive correlation between the human composite rating and the sentiment score using each of the lexicons for strengths comments and a slightly positive correlation for the concerns comments made by guardians and teachers. In addition, the researchers found that as the word count increased for open-ended responses regarding the child’s strengths, there was a greater positive sentiment rating. Conversely, as word count increased for open-ended responses regarding child concerns, the human raters scored comments more negatively. The authors offer a proof-of-concept to use NLP-based sentiment analysis of open-ended comments to complement other data for clinical decision making.

scholarly journals Detection of Occlusal Carious Lesion using the SoproLife® Camera: A Systematic Review

2016 ◽  
Vol 17 (9) ◽  
pp. 774-779 ◽  
Author(s):  
Sophie Doméjean ◽  
Julie Rongier ◽  
Michèle Muller-Bolla
Keyword(s):  
Systematic Review ◽  
Scientific Evidence ◽  
Assessment System ◽  
Caries Detection ◽  
Permanent Teeth ◽  
Carious Lesion ◽  
Carious Lesions ◽  
Pubmed Database ◽  
Icdas Ii

ABSTRACT Aim The aim of this systematic review was to assess the in vivo scientific evidence regarding the ability of a recently developed light fluorescence device, SoproLife® (Sopro-Acteon group, La Ciotat, France) in detecting occlusal carious lesions. The PubMed database was searched for in vivo trials that evaluated the validity of the SoproLife® camera for the detection of occlusal carious lesions. Among the 11 articles originally identified with the keyword “Soprolife,” only three articles were included. The three included surveys used the International Caries Detection and Assessment System (ICDAS)-II criteria as gold standard for the assessment of SoproLife® compared or not to other detection devices (DIAGNOdent® and Spectra Caries Detection Aid®). Two of the included studies reported only on permanent teeth or both primary and permanent teeth. The SoproLife® validity values varied markedly among studies with a sensitivity ranging between 0.43 and 0.95 and a specificity between 0.55 and 1. Interobserver reproducibility with the SoproLife® was reported in two of the three studies (0.98 and 0.72) and none of the studies reported about intraobserver reproducibility. No clear-cut conclusion can be made based on the three included clinical studies; further in vivo investigations are needed to confirm the validity of the SoproLife® camera in terms of detection of occlusal carious lesions. How to cite this article Doméjean S, Rongier J, Muller-Bolla M. Detection of Occlusal Carious Lesion using the SoproLife® Camera: A Systematic Review. J Contemp Dent Pract 2016;17(9):774-779.

scholarly journals Monitoring of Sound and Carious Surfaces under Sealants over 44 Months

2014 ◽  
Vol 93 (11) ◽  
pp. 1070-1075 ◽  
Author(s):  
M. Fontana ◽  
J.A. Platt ◽  
G.J. Eckert ◽  
C. González-Cabezas ◽  
K. Yoder ◽  
...  
Keyword(s):  
Assessment System ◽  
Retention Rates ◽  
Caries Detection ◽  
Major Barrier ◽  
Occlusal Surfaces ◽  
Before And After ◽  
Permanent Molars ◽  
Caries Lesions ◽  
Sealant Retention ◽  
Lesion Severity

Although there is strong evidence for the effectiveness of sealants, one major barrier in sealant utilization is the concern of sealing over active caries lesions. This study evaluated detection and monitoring of caries lesions through a clear sealant over 44 mo. Sixty-four 7- to 10-year-old children with at least 2 permanent molars with International Caries Detection and Assessment System (ICDAS) scores 0-4 (and caries less than halfway through the dentin, radiographically) were examined with ICDAS, DIAGNOdent, and quantitative light-induced fluorescence (QLF) before sealant placement and 1, 12, 24, and 44 mo (except QLF) after. Bitewing radiographs were taken yearly. DIAGNOdent and QLF were able to distinguish between baseline ICDAS before and after sealant placement. There was no significant evidence of ICDAS progression at 12 mo, but there was small evidence of minor increases at 24 and 44 mo (14% and 14%, respectively) with only 2% ICDAS ≥ 5. Additionally, there was little evidence of radiographic progression (at 12 mo = 1%, 24 mo = 3%, and 44 mo = 9%). Sealant retention rates were excellent at 12 mo = 89%, 24 mo = 78%, and 44 mo = 70%. The small risk of sealant repair increased significantly as baseline ICDAS, DIAGNOdent, and QLF values increased. However, regardless of lesion severity, sealants were 100% effective at 12 mo and 98% effective over 44 mo in managing occlusal surfaces at ICDAS 0-4 ( i.e., only 4 of 228 teeth progressed to ICDAS ≥ 5 associated with sealants in need of repair and none to halfway or more through the dentin, radiographically). This study suggests that occlusal surfaces without frank cavitation (ICDAS 0-4) that are sealed with a clear sealant can be monitored with ICDAS, QLF, or DIAGNOdent, which may aid in predicting the need for sealant repair.

Development of a Fluorescence-Based Caries Scoring System for an Intraoral Scanner: An in vitro Study

2020 ◽  
Vol 54 (4) ◽  
pp. 324-335
Author(s):  
Stavroula Michou ◽  
Ana Raquel Benetti ◽  
Christoph Vannahme ◽  
Pétur Gordon Hermannsson ◽  
Azam Bakhshandeh ◽  
...  
Keyword(s):  
Scoring System ◽  
State Of The Art ◽  
Assessment System ◽  
Detection Methods ◽  
Caries Detection ◽  
Fluorescence Signal ◽  
Radiographic Assessment ◽  
Intraoral Scanner ◽  
Posterior Teeth ◽  
Occlusal Surfaces

<b><i>Objectives:</i></b> To develop an automated fluorescence-based caries scoring system for an intraoral scanner and to<i></i>test the performance of the system compared to state-of-the-art methods. <b><i>Methods:</i></b> Seventy-three permanent posterior teeth were scanned with a three-dimensional (3D) intraoral scanner prototype which emitted light at 415 nm. An overlay representing the fluorescence signal from the tissue was mapped onto 3D models of the teeth. Multiple examination sites (<i>n</i> = 139) on the occlusal surfaces were chosen, and their red and green fluorescence signal components were extracted. These components were used to calculate 4 mathematical functions upon which a caries scoring system for the scanner prototype could be based. Visual-tactile (International Caries Detection and Assessment System, ICDAS), radiographic (ICDAS), and histological assessments were conducted on the same examination sites. <b><i>Results:</i></b> Most index tests showed significant correlation with histology. The strongest correlation was observed for the visual-tactile examination (<i>r</i><sub>s</sub> = 0.80) followed by the scanner supported by the caries classification function that quantifies the overall fluorescence compared to sound surfaces (<i>r</i><sub>s</sub> = 0.78). Additionally, this function resulted in the highest intra-examiner reliability (κ = 0.964), and the highest sum of sensitivity (SE) and specificity (SP) (sum SE-SP: 1.60–1.84) at the 2 histological levels where the comparison with visual-tactile assessment was possible (κ = 0.886, sum SE-SP = 1.57–1.81) and at the 3 out of 4 histological levels where the comparison with radiographic assessment was possible (κ = 0.911, sum SE-SP = 1.37–1.78); the only exception was for the lesions in the outer third of dentin, where the radiographic assessment showed the highest sum SE-SP (1.78). <b><i>Conclusion:</i></b> A fluorescence-based caries scoring system was developed for the intraoral scanner showing promising performance compared to state-of-the-art caries detection methods. The intraoral scanner accompanied by an automated caries scoring system may improve objective caries detection and increase the efficiency and effectiveness of oral examinations. Furthermore, this device has the potential to support reliable monitoring of early caries lesions.

scholarly journals Deep Learning Based Biomedical Literature Classification Using Criteria of Scientific Rigor

Electronics ◽  
2020 ◽  
Vol 9 (8) ◽  
pp. 1253
Author(s):  
Muhammad Afzal ◽  
Beom Joo Park ◽  
Maqbool Hussain ◽  
Sungyoung Lee
Keyword(s):  
Deep Learning ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Biomedical Literature ◽  
Training Dataset ◽  
Support Vector ◽  
Scientific Rigor ◽  
Cochrane Reviews ◽  
Cumulative Score ◽  
Proposed Model

A major blockade to support the evidence-based clinical decision-making is accurately and efficiently recognizing appropriate and scientifically rigorous studies in the biomedical literature. We trained a multi-layer perceptron (MLP) model on a dataset with two textual features, title and abstract. The dataset consisting of 7958 PubMed citations classified in two classes: scientific rigor and non-rigor, is used to train the proposed model. We compare our model with other promising machine learning models such as Support Vector Machine (SVM), Decision Tree, Random Forest, and Gradient Boosted Tree (GBT) approaches. Based on the higher cumulative score, deep learning was chosen and was tested on test datasets obtained by running a set of domain-specific queries. On the training dataset, the proposed deep learning model obtained significantly higher accuracy and AUC of 97.3% and 0.993, respectively, than the competitors, but was slightly lower in the recall of 95.1% as compared to GBT. The trained model sustained the performance of testing datasets. Unlike previous approaches, the proposed model does not require a human expert to create fresh annotated data; instead, we used studies cited in Cochrane reviews as a surrogate for quality studies in a clinical topic. We learn that deep learning methods are beneficial to use for biomedical literature classification. Not only do such methods minimize the workload in feature engineering, but they also show better performance on large and noisy data.

Sign in / Sign up

Export Citation Format

Share Document