RESUMO
INTRODUCTION: This study aimed to develop an artificial neural network (ANN) model for cervical vertebral maturation (CVM) analysis and validate the model's output with the results of human observers. METHODS: A total of 647 lateral cephalograms were selected from patients with 10-30 years of chronological age (mean ± standard deviation, 15.36 ± 4.13 years). New software with a decision support system was developed for manual labeling of the dataset. A total of 26 points were marked on each radiograph. The CVM stages were saved on the basis of the final decision of the observer. Fifty-four image features were saved in text format. A new subset of 72 radiographs was created according to the classification result, and these 72 radiographs were visually evaluated by 4 observers. Weighted kappa (wκ) and Cohen's kappa (cκ) coefficients and percentage agreement were calculated to evaluate the compatibility of the results. RESULTS: Intraobserver agreement ranges were as follows: wκ = 0.92-0.98, cκ = 0.65-0.85, and 70.8%-87.5%. Interobserver agreement ranges were as follows: wκ = 0.76-0.92, cκ = 0.4-0.65, and 50%-72.2%. Agreement between the ANN model and observers 1, 2, 3, and 4 were as follows: wκ = 0.85 (cκ = 0.52, 59.7%), wκ = 0.8 (cκ = 0.4, 50%), wκ = 0.87 (cκ = 0.55, 62.5%), and wκ = 0.91 (cκ = 0.53, 61.1%), respectively (P <0.001). An average of 58.3% agreement was observed between the ANN model and the human observers. CONCLUSIONS: This study demonstrated that the developed ANN model performed close to, if not better than, human observers in CVM analysis. By generating new algorithms, automatic classification of CVM with artificial intelligence may replace conventional evaluation methods used in the future.
Assuntos
Inteligência Artificial , Vértebras Cervicais , Vértebras Cervicais/diagnóstico por imagem , Humanos , Redes Neurais de Computação , Variações Dependentes do Observador , Radiografia , Reprodutibilidade dos TestesRESUMO
The morphology of the finger bones in hand-wrist radiographs (HWRs) can be considered as a radiological skeletal maturity indicator, along with the other indicators. This study aims to validate the anatomical landmarks envisaged to be used for classification of the morphology of the phalanges, by developing classical neural network (NN) classifiers based on a sub-dataset of 136 HWRs. A web-based tool was developed and 22 anatomical landmarks were labeled on four region of interests (proximal (PP3), medial (MP3), distal (DP3) phalanges of the third and medial phalanx (MP5) of the fifth finger) and the epiphysis-diaphysis relationships were saved as "narrow,""equal,""capping" or "fusion" by three observers. In each region, 18 ratios and 15 angles were extracted using anatomical points. The data set is analyzed by developing two NN classifiers, without (NN-1) and with (NN-2) the 5-fold cross-validation. The performance of the models was evaluated with percentage of agreement, Cohen's (cκ) and Weighted (wκ) Kappa coefficients, precision, recall, F1-score and accuracy (statistically significance: p < 0.05). Method error was found to be in the range of cκ: 0.7-1. Overall classification performance of the models was changed between 82.14% and 89.29%. On average, performance of the NN-1 and NN-2 models were found to be 85.71% and 85.52%, respectively. The cκ and wκ of the NN-1 model were changed between -0.08 (p > 0.05) and 0.91 among regions. The average performance was found to be promising except the regions without adequate samples and the anatomical points are validated to be used in the future studies, initially.
Assuntos
Inteligência Artificial , Redes Neurais de Computação , Projetos Piloto , Radiografia , MãosRESUMO
This study aims to investigate the effect of using an artificial intelligence (AI) system (Diagnocat, Inc., San Francisco, CA, USA) for caries detection by comparing cone-beam computed tomography (CBCT) evaluation results with and without the software. 500 CBCT volumes are scored by three dentomaxillofacial radiologists for the presence of caries separately on a five-point confidence scale without and with the aid of the AI system. After visual evaluation, the deep convolutional neural network (CNN) model generated a radiological report and observers scored again using AI interface. The ground truth was determined by a hybrid approach. Intra- and inter-observer agreements are evaluated with sensitivity, specificity, accuracy, and kappa statistics. A total of 6008 surfaces are determined as 'presence of caries' and 13,928 surfaces are determined as 'absence of caries' for ground truth. The area under the ROC curve of observer 1, 2, and 3 are found to be 0.855/0.920, 0.863/0.917, and 0.747/0.903, respectively (unaided/aided). Fleiss Kappa coefficients are changed from 0.325 to 0.468, and the best accuracy (0.939) is achieved with the aided results. The radiographic evaluations performed with aid of the AI system are found to be more compatible and accurate than unaided evaluations in the detection of dental caries with CBCT images.
RESUMO
OBJECTIVES: This study aimed to develop five different supervised machine learning (ML) classifier models using artificial intelligence (AI) techniques and to compare their performance for cervical vertebral maturation (CVM) analysis. A clinical decision support system (CDSS) was developed for more objective results. METHODS: A total of 647 digital lateral cephalometric radiographs with visible C2, C3, C4 and C5 vertebrae were chosen. Newly developed software was used for manually labelling the samples, with the integrated CDSS developed by evaluation of 100 radiographs. On each radiograph, 26 points were marked, and the CDSS generated a suggestion according to the points and CVM analysis performed by the human observer. For each sample, 54 features were saved in text format and classified using logistic regression (LR), support vector machine, random forest, artificial neural network (ANN) and decision tree (DT) models. The weighted κ coefficient was used to evaluate the concordance of classification and expert visual evaluation results. RESULTS: Among the CVM stage classifier models, the best result was achieved using the ANN model (κ = 0.926). Among cervical vertebrae morphology classifier models, the best result was achieved using the LR model (κ = 0.968) for the presence of concavity, and the DT model (κ = 0.949) for vertebral body shapes. CONCLUSIONS: This study has proposed ML models for CVM assessment on lateral cephalometric radiographs, which can be used for the prediction of cervical vertebrae morphology. Further studies should be done especially of forensic applications of AI models through CVM evaluations.