Automated Prediction of Dental Implant Success Using a Mask Region-Based Convolutional Neural Network on Preoperative Cone-Beam Computed Tomography Scans.
Source check: Source checked. Not independent scientific confirmation.
Finding: Original full text describes a retrospective 210-implant cohort, preoperative CBCT, a Mask R-CNN transfer-learning classifier and clinical success/failure follow-up. On 42 held-out implants the model reached accuracy .821/AUC .790 and exceeded two human observers; small single-center dataset limits generalization. The result is reported in Cureus. The study does not establish generalization beyond its reported setting or prospective real-world benefit.
Technology: n=210, held-out n=42, ground truth clinical follow-up, Mask R-CNN
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- n=210, held-out n=42, ground truth clinical follow-up, Mask R-CNN
- Test and result
- Original full text describes a retrospective 210-implant cohort, preoperative CBCT, a Mask R-CNN transfer-learning classifier and clinical success/failure follow-up. On 42 held-out implants the model reached accuracy .821/AUC .790 and exceeded two human observers; small single-center dataset limits generalization.
- Limitation / still unknown
- Independent replication and prospective real-world benefit are not established in the reviewed study.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://europepmc.org/article/MED/41164056 · https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_xml/PMC12559766/unicode
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.