Automated Prediction of Dental Implant Success Using a Mask Region-Based Convolutional Neural Network on Preoperative Cone-Beam Computed Tomography Scans
The Mask R-CNN model outperformed expert implantologists in predicting implant outcomes by leveraging CBCT-derived features with high reliability and interpretability. Its integration into clinical workflows could enhance risk stratification, although prospective multicenter validation is needed.
Authors
- Sandeep Yerra
- Pradeep Dilip Taide
- Mohammad Faizan (ORCID: https://orcid.org/0000-0002-3952-6558)
- Sai Govind Gavara (ORCID: https://orcid.org/0009-0003-7020-4244)
- Manish Sharma (ORCID: https://orcid.org/0000-0002-6711-1552)
- Writuraj Sutradhar
- Gaurav Salunkhe
Institutions
- Navodaya Dental College and Hospital (IN)
- Kothiwal Dental College and Research Centre (IN)
- Government Dental College and Hospital (IN)
- MNR Dental College and Hospital (IN)
- Dr D Y Patil Dental College & Hospital (IN)
- Medical Research Foundation (GB)
Publication Details
- Journal
- Cureus
- Published
- 2025-09-27
- DOI
- https://doi.org/10.7759/cureus.93378
- Primary Topic
- Dental Radiography and Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00