Effectiveness of Artificial Intelligence Models for Detection of Vertical Root Fractures: A Systematic Review.
Authors
Affiliations (6)
Affiliations (6)
- College of Dental Medicine, Roseman University of Health Sciences, South Jordan, UT-84095, USA. Electronic address: [email protected].
- College of Dental Medicine, Roseman University of Health Sciences, South Jordan, UT-84095, USA. Electronic address: [email protected].
- College of Dental Medicine, Roseman University of Health Sciences, South Jordan, UT-84095, USA. Electronic address: [email protected].
- College of Dental Medicine, Roseman University of Health Sciences, South Jordan, UT-84095, USA. Electronic address: [email protected].
- Harvard School of Dental Medicine, Harvard University, Boston, MA 02115, USA. Electronic address: [email protected].
- College of Dental Medicine, Roseman University of Health Sciences, South Jordan, UT-84095, USA. Electronic address: [email protected].
Abstract
Vertical root fractures are diagnostically challenging lesions with significant clinical implications. Artificial intelligence models have emerged as a potential diagnostic aid. This systematic review assessed the diagnostic performance of AI-based models for VRF detection across various imaging techniques. Databases including PubMed, Scopus, and Web of Science were thoroughly searched until Jan 2025. Studies that reported on diagnostic accuracy, sensitivity, and specificity were included. Articles in languages other than English were excluded. Study quality was evaluated using QUADAS-2, and the certainty of evidence was rated following the GRADE approach. Of the initial 1,544 studies, seven met the inclusion criteria. Across these studies, CNN-based models showed a 75% to 97.8% accuracy, 75% to 98% sensitivity, and 60% to 99% specificity. Applying ResNet-50 to manually curated CBCT slices achieved the highest accuracy at 97.8%. Probabilistic neural networks and ensemble-based architectures also performed well, especially when trained on large, balanced datasets. Performance declined when lower-resolution modalities such as panoramic or periapical radiographs were used, or when automatic region-of-interest selection was applied. Models trained on CBCT consistently outperformed those using 2D radiography. There is low-level evidence that indicates CNN-based AI models, especially when trained on high-resolution CBCT and enhanced images, can achieve high diagnostic accuracy for VRF detection. The overall certainty of this evidence remains low due to methodological limitations, small sample sizes, and limited external validation. Prospective, multicenter studies using clinically acquired datasets are necessary to confirm generalizability and support clinical implementation.