Aarhus University Seal / Aarhus Universitets segl

Artificial intelligence for detection of periapical lesions on intraoral radiographs: Comparison between convolutional neural networks and human observers

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

  • Ruben Pauwels
  • Danieli Moura Brasil, University of Campinas
  • ,
  • Mayra Cristina Yamasaki, University of Campinas
  • ,
  • Reinhilde Jacobs, Karolinska Institutet, University of Leuven
  • ,
  • Hilde Bosmans, University of Leuven
  • ,
  • Deborah Queiroz Freitas, University of Campinas
  • ,
  • Francisco Haiter-Neto, University of Campinas

Objective: The aim of this study was to compare the diagnostic performance of convolutional neural networks (CNNs) with the performance of human observers for the detection of simulated periapical lesions on periapical radiographs. Study Design: Ten sockets were prepared in bovine ribs. Periapical defects of 3 sizes were sequentially created. Periapical radiographs were acquired of each socket with no lesion and with each lesion size with a photostimulable storage phosphor system. Radiographs were evaluated with no filter and with 6 image filter settings. A CNN architecture was set up using Keras-TensorFlow. Separate CNNs were evaluated for randomly sampled training/validation data and for data split up by socket (5-fold cross-validation) and filter (7-fold cross-validation). CNN performance on validation data was compared with that of 3 oral radiologists for sensitivity, specificity, and area under the receiver operating characteristic curve (ROC-AUC). Results: Using random sampling, the CNN showed perfect accuracy for the validation data. When data were split up by socket, the mean sensitivity, specificity, and ROC-AUC values were 0.79, 0.88, and 0.86, respectively; when split up by filter, they were 0.87, 0.98, and 0.93, respectively. For radiologists, the values were 0.58, 0.83, and 0.75, respectively. Conclusions: CNNs show promise in periapical lesion detection. The pretrained CNN model yielded in this study can be used for further training on larger samples and/or clinical radiographs.

Original languageEnglish
JournalOral Surgery, Oral Medicine, Oral Pathology and Oral Radiology
Pages (from-to)610-616
Number of pages7
Publication statusPublished - May 2021

Bibliographical note

Publisher Copyright:
© 2021 Elsevier Inc.

See relations at Aarhus University Citationformats

ID: 220374834