scholarly journals Proof-of-Concept Study on an Automatic Computational System in Detecting and Classifying Occlusal Caries Lesions from Smartphone Color Images of Unrestored Extracted Teeth

Diagnostics ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1136
Author(s):  
Duc Long Duong ◽  
Quoc Duy Nam Nguyen ◽  
Minh Son Tong ◽  
Manh Tuan Vu ◽  
Joseph Dy Lim ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Dental Caries ◽  
Sensitivity And Specificity ◽  
Color Images ◽  
Caries Detection ◽  
Support Vector ◽  
Proof Of Concept ◽  
Computational System ◽  
Occlusal Caries ◽  
Concept Study

Dental caries has been considered the heaviest worldwide oral health burden affecting a significant proportion of the population. To prevent dental caries, an appropriate and accurate early detection method is demanded. This proof-of-concept study aims to develop a two-stage computational system that can detect early occlusal caries from smartphone color images of unrestored extracted teeth according to modified International Caries Detection and Assessment System (ICDAS) criteria (3 classes: Code 0; Code 1-2; Code 3-6): in the first stage, carious lesion areas were identified and extracted from sound tooth regions. Then, five characteristic features of these areas were intendedly selected and calculated to be inputted into the classification stage, where five classifiers (Support Vector Machine, Random Forests, K-Nearest Neighbors, Gradient Boosted Tree, Logistic Regression) were evaluated to determine the best one among them. On a set of 587 smartphone images of extracted teeth, our system achieved accuracy, sensitivity, and specificity that were 87.39%, 89.88%, and 68.86% in the detection stage when compared to modified visual and image-based ICDAS criteria. For the classification stage, the Support Vector Machine model was recorded as the best model with accuracy, sensitivity, and specificity at 88.76%, 92.31%, and 85.21%. As the first step in developing the technology, our present findings confirm the feasibility of using smartphone color images to employ Artificial Intelligence algorithms in caries detection. To improve the performance of the proposed system, there is a need for further development in both in vitro and in vivo modeling. Besides that, an applicable system for accurately taking intra-oral images that can capture entire dental arches including the occlusal surfaces of premolars and molars also needs to be developed.

Detection of early occlusal caries of the first permanent molar using different techniques (An in vivo study)

2019 ◽  
Vol 31 (1) ◽  
pp. 1-8
Author(s):  
Samah F. Al-Qazzaz ◽  
Abeer M. Hassan
Keyword(s):  
Sensitivity And Specificity ◽  
Visual Inspection ◽  
Caries Detection ◽  
Occlusal Caries ◽  
Clinical Sensitivity ◽  
Permanent Molar ◽  
Permanent Molars ◽  
Early Caries ◽  
First Permanent Molars ◽  
Better Than

Background: Molars and premolars are considered as the most vulnerable teeth of caries attack, which is related to the morphology of their occlusal surfaces along with the difficulty of plaque removal. different methods were used for early caries detection that provide sensitive, accurate preoperative diagnosis of caries depths to establish adequate preventive measures and avoid premature tooth treatment by restoration. The aim of the present study was to evaluate the clinical sensitivity and specificity rates of DIAGNOdent and visual inspection as opposed to the ICDAS for the detection of initial occlusal caries in noncavitated first permanent molars. Materials and Methods: This study examined 139 occlusal surface of the first permanent molar pooled from fifty patients aged 8-9 years by three methods. The selected criteria include one occlusal site per tooth (first permanent molars) with carious lesions range from 0 to 3 according to ICDASII (gold standard) visual criteria then the clinical sensitivity and specificity of visual inspection according to Ekstrand et al.in 1997 and DIAGNOdent were performed. . Results: the highest correlation was found between the ICDASII and DIAGNOdent. The sensitivity of the DIAGNOdent for the enamel caries detection (D1) was better than that of visual inspection. The sensitivity and the specificity for the DIAGNOdent at D3 threshold were better than the D1 threshold and the visual inspection method. Conclusion: DIAGNOden pen can be used as a tool for early caries detection in cases of difficult diagnosis that provide good additional sensitivity to the visual inspection.

scholarly journals Classification of complex emotions using EEG and virtual environment: proof of concept and therapeutic implication

2020 ◽  
Author(s):  
Eleonora De Filippi ◽  
Mara Wolter ◽  
Bruno Melo ◽  
Carlos J. Tierra-Criollo ◽  
Tiago Bortolini ◽  
...  
Keyword(s):  
Real Time ◽  
Cross Validation ◽  
Support Vector ◽  
Spectral Features ◽  
Emotional States ◽  
Proof Of Concept ◽  
Neurofeedback Training ◽  
Concept Study ◽  
Complex Emotions

AbstractDuring the last decades, neurofeedback training for emotional self-regulation has received significant attention from both the scientific and clinical communities. However, most studies have focused on broader emotional states such as “negative vs. positive”, primarily due to our poor understanding of the functional anatomy of more complex emotions at the electrophysiological level. Our proof-of-concept study aims at investigating the feasibility of classifying two complex emotions that have been implicated in mental health, namely tenderness and anguish, using features extracted from the electroencephalogram (EEG) signal in healthy participants. Electrophysiological data were recorded from fourteen participants during a block-designed experiment consisting of emotional self-induction trials combined with a multimodal virtual scenario. For the within-subject classification, the linear Support Vector Machine was trained with two sets of samples: random cross-validation of the sliding windows of all trials; and 2) strategic cross-validation, assigning all the windows of one trial to the same fold. Spectral features, together with the frontal-alpha asymmetry, were extracted using Complex Morlet Wavelet analysis. Classification results with these features showed an accuracy of 79.3% on average when doing random cross-validation, and 73.3% when applying strategic cross-validation. We extracted a second set of features from the amplitude time-series correlation analysis, which significantly enhanced random cross-validation accuracy while showing similar performance to spectral features when doing strategic cross-validation. These results suggest that complex emotions show distinct electrophysiological correlates, which paves the way for future EEG-based, real-time neurofeedback training of complex emotional states.Significance statementThere is still little understanding about the correlates of high-order emotions (i.e., anguish and tenderness) in the physiological signals recorded with the EEG. Most studies have investigated emotions using functional magnetic resonance imaging (fMRI), including the real-time application in neurofeedback training. However, concerning the therapeutic application, EEG is a more suitable tool with regards to costs and practicability. Therefore, our proof-of-concept study aims at establishing a method for classifying complex emotions that can be later used for EEG-based neurofeedback on emotion regulation. We recorded EEG signals during a multimodal, near-immersive emotion-elicitation experiment. Results demonstrate that intraindividual classification of discrete emotions with features extracted from the EEG is feasible and may be implemented in real-time to enable neurofeedback.

scholarly journals Sensitivity and Specificity of Different Diagnostic Methods in Occlusal Caries Detection of Permanent Teeth among Paediatric Patients

2021 ◽  
Vol 16 (2) ◽  
pp. 113-126
Author(s):  
Ilham Wan Mokhtar ◽  
Annapurny Venkiteswaran ◽  
Mohd Yusmiaidil Putera Mohd Yusof
Keyword(s):  
Sensitivity And Specificity ◽  
Near Infrared ◽  
Visual Detection ◽  
Diagnostic Methods ◽  
Infrared Light ◽  
Caries Detection ◽  
Permanent Teeth ◽  
Occlusal Caries ◽  
Occlusal Caries Detection ◽  
Occlusal Surfaces

Dental caries is a commonly progressive disease that proceeds through various degrees of severity that a dentist can detect. The aims of the in vivo study were to assess the accuracy of the individual model (near-infrared light transillumination [NILT] device, visual and radiographic examinations) in detecting occlusal caries, and to evaluate the performance of visual and NILT device combination for occlusal caries detection in deciding the treatment options. Fifty-two non-cavitated occlusal surfaces from 16 patients were assessed with three different diagnostic devices in random order. Identified lesions were prepared and validated. Logistic regression analysis was performed for each method. The sensitivity and specificity values for each method and the combined models were statistically measured using RStudio version 0.97.551. At the enamel level, visual detection was the most sensitive method (0.88), while NILT was the most specific (0.93). NILT scored the highest for sensitivity (0.93) at the dentine level and visual detection scored the highest for specificity (0.88). Visual detection + NILT model was significantly better (p = 0.04) compared to visual detection or NILT alone (df = 1). The visual-NILT combination is a superior model in detecting occlusal caries on permanent teeth. The model provided surplus value in caries detection hence improving the treatment decision-making in occlusal surfaces.

Factors Affecting the Detection and Treatment of Occlusal Caries Using the International Caries Detection and Assessment System

2011 ◽  
Vol 36 (6) ◽  
pp. 597-607 ◽  
Author(s):  
AA Al-Khatrash ◽  
YM Badran ◽  
QD Alomari
Keyword(s):  
Dental Caries ◽  
Clinical Relevance ◽  
Assessment System ◽  
Caries Detection ◽  
Occlusal Caries ◽  
Factors Affecting ◽  
The World ◽  
Predominant Form ◽  
Dental Schools

Clinical Relevance Occlusal caries is the predominant form of dental caries at the present time. This study documents the variability in detection and treatment of occlusal caries among dentists graduating from different dental schools around the world and practicing in Kuwait. Furthermore, it shows that dentists tend to overtreat occlusal caries.

scholarly journals MALDI mass spectrometry imaging analysis of pituitary adenomas for near-real-time tumor delineation

2015 ◽  
Vol 112 (32) ◽  
pp. 9978-9983 ◽  
Author(s):  
David Calligaris ◽  
Daniel R. Feldman ◽  
Isaiah Norton ◽  
Olutayo Olubiyi ◽  
Armen N. Changelian ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Real Time ◽  
Pituitary Adenomas ◽  
Mass Spectrometry Imaging ◽  
Pituitary Tumors ◽  
Pituitary Hormones ◽  
Support Vector ◽  
Proof Of Concept ◽  
Human Pituitary ◽  
Concept Study

We present a proof of concept study designed to support the clinical development of mass spectrometry imaging (MSI) for the detection of pituitary tumors during surgery. We analyzed by matrix-assisted laser desorption/ionization (MALDI) MSI six nonpathological (NP) human pituitary glands and 45 hormone secreting and nonsecreting (NS) human pituitary adenomas. We show that the distribution of pituitary hormones such as prolactin (PRL), growth hormone (GH), adrenocorticotropic hormone (ACTH), and thyroid stimulating hormone (TSH) in both normal and tumor tissues can be assessed by using this approach. The presence of most of the pituitary hormones was confirmed by using MS/MS and pseudo-MS/MS methods, and subtyping of pituitary adenomas was performed by using principal component analysis (PCA) and support vector machine (SVM). Our proof of concept study demonstrates that MALDI MSI could be used to directly detect excessive hormonal production from functional pituitary adenomas and generally classify pituitary adenomas by using statistical and machine learning analyses. The tissue characterization can be completed in fewer than 30 min and could therefore be applied for the near-real-time detection and delineation of pituitary tumors for intraoperative surgical decision-making.

Diagnostic Classification of ADHD Versus Control: Support Vector Machine Classification Using Brief Neuropsychological Assessment

2016 ◽  
Vol 24 (11) ◽  
pp. 1547-1556 ◽  
Author(s):  
Jesse C. Bledsoe ◽  
Cao Xiao ◽  
Art Chaovalitwongse ◽  
Sonya Mehta ◽  
Thomas J. Grabowski ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Decision Tree ◽  
Sensitivity And Specificity ◽  
Neuropsychological Assessment ◽  
Feature Selection Method ◽  
Diagnostic Classification ◽  
Support Vector ◽  
Tree Model ◽  
Children With Adhd

Objective: Common methods for clinical diagnosis include clinical interview, behavioral questionnaires, and neuropsychological assessment. These methods rely on clinical interpretation and have variable reliability, sensitivity, and specificity. The goal of this study was to evaluate the utility of machine learning in the prediction and classification of children with ADHD–Combined presentation (ADHD-C) using brief neuropsychological measures (d2 Test of Attention, Children with ADHD-C and typically developing control children completed semi-structured clinical interviews and measures of attention/concentration and parents completed symptom severity questionnaires. Method: We used a forward feature selection method to identify the most informative neuropsychological features for support vector machine (SVM) classification and a decision tree model to derive a rule-based model. Results: The SVM model yielded excellent classification accuracy (100%) of individual children with and without ADHD (1.0). Decision tree algorithms identified individuals with and without ADHD-C with 100% sensitivity and specificity. Conclusion:This study observed highly accurate statistical diagnostic classification, at the individual level, in a sample of children with ADHD-C. The findings suggest data-driven behavioral algorithms based on brief neuropsychological data may present an efficient and accurate diagnostic tool for clinicians.

scholarly journals Machine Learning Enables Prediction of Cardiac Amyloidosis by Routine Laboratory Parameters: A Proof-of-Concept Study

2020 ◽  
Vol 9 (5) ◽  
pp. 1334 ◽  
Author(s):  
Asan Agibetov ◽  
Benjamin Seirer ◽  
Theresa-Marie Dachs ◽  
Matthias Koschutnik ◽  
Daniel Dalos ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Model ◽  
Sensitivity And Specificity ◽  
Cardiac Amyloidosis ◽  
Linear Prediction ◽  
Prediction Models ◽  
Characteristic Curve ◽  
Proof Of Concept ◽  
Laboratory Parameters ◽  
Concept Study

(1) Background: Cardiac amyloidosis (CA) is a rare and complex condition with poor prognosis. While novel therapies improve outcomes, many affected individuals remain undiagnosed due to a lack of awareness among clinicians. This study was undertaken to develop an expert-independent machine learning (ML) prediction model for CA relying on routinely determined laboratory parameters. (2) Methods: In a first step, we developed baseline linear models based on logistic regression. In a second step, we used an ML algorithm based on gradient tree boosting to improve our linear prediction model, and to perform non-linear prediction. Then, we compared the performance of all diagnostic algorithms. All prediction models were developed on a training cohort, consisting of patients with proven CA (positive cases, n = 121) and amyloidosis-unrelated heart failure (HF) patients (negative cases, n = 415). Performances of all prediction models were evaluated on a separate prognostic validation cohort with 37 CA-positive and 124 CA-negative patients. (3) Results: Our best model, based on gradient-boosted ensembles of decision trees, achieved an area under the receiver operating characteristic curve (ROC AUC) score of 0.86, with sensitivity and specificity of 89.2% and 78.2%, respectively. The best linear model had an ROC AUC score of 0.75, with sensitivity and specificity of 84.6 and 71.7, respectively. (4) Conclusions: Our work demonstrates that ML makes it possible to utilize basic laboratory parameters to generate a distinct CA-related HF profile compared with CA-unrelated HF patients. This proof-of-concept study opens a potential new avenue in the diagnostic workup of CA and may assist physicians in clinical reasoning.

scholarly journals A Novel Method for Evaluating the Cardiotoxicity of Traditional Chinese Medicine Compatibility by Using Support Vector Machine Model Combined with Metabonomics

2016 ◽  
Vol 2016 ◽  
pp. 1-7 ◽  
Author(s):  
Yubo Li ◽  
Haonan Zhou ◽  
Jiabin Xie ◽  
Mayassa Salum Ally ◽  
Zhiguo Hou ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Chinese Medicine ◽  
Traditional Chinese Medicine ◽  
Sensitivity And Specificity ◽  
High Sensitivity ◽  
Support Vector ◽  
Machine Model ◽  
Svm Model ◽  
Long Time ◽  
Novel Method

Traditional biochemical and histopathological tests have been used to evaluate the safety of traditional Chinese medicine (TCM) compatibility for a long time. But these methods lack high sensitivity and specificity. In the previous study, we have found ten biomarkers related to cardiotoxicity and established a support vector machine (SVM) prediction model. Results showed a good sensitivity and specificity. Therefore, in this study, we used SVM model combined with metabonomics UPLC/Q-TOF-MS technology to build a rapid and sensitivity and specificity method to predict the cardiotoxicity of TCM compatibility. This study firstly applied SVM model to the prediction of cardiotoxicity in TCM compatibility containingAconiti Lateralis Radix Praeparataand further identified whether the cardiotoxicity increased afterAconiti Lateralis Radix Praeparatacombined with other TCM. This study provides a new idea for studying the evaluation of the cardiotoxicity caused by compatibility of TCM.

Sign in / Sign up

Export Citation Format

Share Document