skip to main content
Idioma:

Artificial intelligence assisted identification of therapy history from periapical films for dental root canal

Xu, Tongkai ; Zhu, Yuang ; Peng, Li ; Cao, Yin ; Zhao, Xiaoting ; Meng, Fanchao ; Ding, Jinmin ; Liang, Sheng

Displays, 2022-01, Vol.71, p.102119, Article 102119 [Periódico revisado por pares]

Elsevier B.V

Texto completo disponível

Citações Citado por
  • Título:
    Artificial intelligence assisted identification of therapy history from periapical films for dental root canal
  • Autor: Xu, Tongkai ; Zhu, Yuang ; Peng, Li ; Cao, Yin ; Zhao, Xiaoting ; Meng, Fanchao ; Ding, Jinmin ; Liang, Sheng
  • Assuntos: Artificial intelligence ; Auxiliary diagnosis ; History of root canal therapy ; Machine learning ; Periapical films
  • É parte de: Displays, 2022-01, Vol.71, p.102119, Article 102119
  • Descrição: •According to the characteristics of tooth morphology, we have proposed a method for extracting Region of Interest (ROI) tooth root canal.•Three machine learning methods have been utilized for training and testing, respectively, with and without our proposed ROI extraction operation.•The data enhancement method improves the generalization ability of the model.•The result proved that our proposed method of ROI extraction is effective for the artificial intelligence assisted diagnosis on the history of root canal therapy. In this work, we aim to develop and validate an AI-assisted method for identifying the history of root canal therapy by using periapical films. First, we propose a pre-processing method to extract the regions of interest (ROI) containing the root canals. Then, in order to improve the generalization ability, data augmentation is adopted to expand the dataset. Finally, three machine learning methods, including SIFT-SVM, CNN, and transfer learning are used. All the models are validated based on the receiving operating characteristic (ROC) curve analysis. The accuracies for the three machine learning methods are above 95%. The AUC, sensitivity, and specificity of the best model are also presented and analyzed.
  • Editor: Elsevier B.V
  • Idioma: Inglês
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.