Diagnostic capability of artificial intelligence tools for detecting and classifying odontogenic cysts and tumors: a systematic review and meta-analysis

Oral Surg Oral Med Oral Pathol Oral Radiol. 2024 Sep;138(3):414-426. doi: 10.1016/j.oooo.2024.03.004. Epub 2024 Mar 19.

Abstract

Objective: To evaluate the diagnostic capability of artificial intelligence (AI) for detecting and classifying odontogenic cysts and tumors, with special emphasis on odontogenic keratocyst (OKC) and ameloblastoma.

Study design: Nine electronic databases and the gray literature were examined. Human-based studies using AI algorithms to detect or classify odontogenic cysts and tumors by using panoramic radiographs or CBCT were included. Diagnostic tests were evaluated, and a meta-analysis was performed for classifying OKCs and ameloblastomas. Heterogeneity, risk of bias, and certainty of evidence were evaluated.

Results: Twelve studies concluded that AI is a promising tool for the detection and/or classification of lesions, producing high diagnostic test values. Three articles assessed the sensitivity of convolutional neural networks in classifying similar lesions using panoramic radiographs, specifically OKC and ameloblastoma. The accuracy was 0.893 (95% CI 0.832-0.954). AI applied to cone beam computed tomography produced superior accuracy based on only 4 studies. The results revealed heterogeneity in the models used, variations in imaging examinations, and discrepancies in the presentation of metrics.

Conclusion: AI tools exhibited a relatively high level of accuracy in detecting and classifying OKC and ameloblastoma. Panoramic radiography appears to be an accurate method for AI-based classification of these lesions, albeit with a low level of certainty. The accuracy of CBCT model data appears to be high and promising, although with limited available data.

Publication types

  • Meta-Analysis
  • Systematic Review

MeSH terms

  • Algorithms
  • Ameloblastoma / classification
  • Ameloblastoma / diagnostic imaging
  • Ameloblastoma / pathology
  • Artificial Intelligence*
  • Cone-Beam Computed Tomography*
  • Humans
  • Jaw Neoplasms / classification
  • Jaw Neoplasms / diagnostic imaging
  • Odontogenic Cysts* / classification
  • Odontogenic Cysts* / diagnostic imaging
  • Odontogenic Tumors* / classification
  • Odontogenic Tumors* / diagnostic imaging
  • Radiography, Panoramic