Detecting the presence of taurodont teeth on panoramic radiographs using a deep learning-based convolutional neural network algorithm


DUMAN S., Yılmaz E. F., EŞER G., ÇELİK Ö., BAYRAKDAR İ. Ş., BİLGİR E., ...Daha Fazla

ORAL RADIOLOGY, cilt.39, sa.1, ss.207-214, 2023 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 39 Sayı: 1
  • Basım Tarihi: 2023
  • Doi Numarası: 10.1007/s11282-022-00622-1
  • Dergi Adı: ORAL RADIOLOGY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, CINAHL, EMBASE, MEDLINE
  • Sayfa Sayıları: ss.207-214
  • Anahtar Kelimeler: Taurodontism, Artificial intelligence, Deep learning, Panoramic radiographs, Dentistry, ARTIFICIAL-INTELLIGENCE
  • Eskişehir Osmangazi Üniversitesi Adresli: Evet

Özet

Objectives Artificial intelligence (AI) techniques like convolutional neural network (CNN) are a promising breakthrough that can help clinicians analyze medical imaging, diagnose taurodontism, and make therapeutic decisions. The purpose of the study is to develop and evaluate the function of CNN-based AI model to diagnose teeth with taurodontism in panoramic radiography. Methods 434 anonymized, mixed-sized panoramic radiography images over the age of 13 years were used to develop automatic taurodont tooth segmentation models using a Pytorch implemented U-Net model. Datasets were split into train, validation, and test groups of both normal and masked images. The data augmentation method was applied to images of trainings and validation groups with vertical flip images, horizontal flip images, and both flip images. The Confusion Matrix was used to determine the model performance. Results Among the 43 test group images with 126 labels, there were 109 true positives, 29 false positives, and 17 false negatives. The sensitivity, precision, and F1-score values of taurodont tooth segmentation were 0.8650, 0.7898, and 0.8257, respectively. Conclusions CNN's ability to identify taurodontism produced almost identical results to the labeled training data, and the CNN system achieved close to the expert level results in its ability to detect the taurodontism of teeth.