RESUMEN
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.
RESUMEN
Objective: Forensic dentistry has used some methods for the human identification process. However, there is a need to study characteristics that are able to perform identification more specifically, increasing accuracy. Considering the role of dental arch assessment in prediction of gender and ethnicity, the purpose of this study was to assess the volume of pulp chamber as a mean to obtain new forensic evidence. Material and methods: For this task, 1.190 cone beam computed tomography (CBCT) images were retrospectively selected and subdivided according to the population number, gender, age and ethnicity. All DICOM files were imported to the open-source software ITK-SNAP®(http://www.itksnap.org/pmwiki/pmwiki.php). The segmentation process was performed in all pulp chamber aiming to obtain pulp tissue Ìs volume. Results: As a result, the pulp chamber volume of mandibular canine teeth showed to be larger in white population than in non-white (P-value = 0.003) and in male individuals in comparison with female (P-value = 0.038). Conclusion: These results, however, must be confirmed by future studies with a larger sample size and by the assessment of other variables, including texture analysis and density of dental tissues. (AU)
Objetivo: A odontologia forense tem usado alguns métodos para o processo de identificação humana. Porém, há a necessidade de estudar características que consigam de forma mais específica realizar a identificação aumentando a precisão. Considerando o papel da avaliação da arcada dentária na predição de gênero e etnia, o objetivo deste estudo foi avaliar o volume da câmara pulpar mandibular como meio de obtenção de novas evidências periciais. Material e métodos: Foram selecionadas 1.190 imagens de tomografia computadorizada de feixe cônico (TCFC) e subdivididas de acordo com o número da população, sexo, idade e etnia. Todos os arquivos em formato DICOM foram importados para o software de código aberto ITK-SNAP® (http://www.itksnap.org/pmwiki/pmwiki.php) onde o processo de segmentação foi realizado em todas as câmaras pulpares visando a obtenção da volumetria. Resultados: Como resultado, o volume da câmara pulpar dos caninos inferiores mostrou-se maior na população branca do que na não branca (P-valor = 0,003), no sexo masculino em comparação ao feminino (P-valor = 0,038). Conclusão: Esses resultados, entretanto, devem ser confirmados por estudos futuros com maior tamanho amostral e pela avaliação de outras variáveis, incluindo análise de textura e densidade dos tecidos dentários. (AU)
