Related Experiment Video
Updated: Aug 5, 2026
07:32
Measuring Maxillary Posterior Tooth Movement: A Model Assessment using Palatal and Dental Superimposition
Published on: February 23, 2024
Automated Prognostic Evaluation of First Permanent Molar Extractions Using YOLOv8 with Oriented Bounding Boxes on
Aslihan Yelkenci1, Günseli Güven Polat1, Fatih Ciftci2,3,4
1Department of Pediatric Dentistry, Faculty of Dentistry, University of Health Sciences, 34668 Istanbul, Turkey.
Diagnostics (Basel, Switzerland)
|July 28, 2026
Summary
This study introduces an AI tool using deep learning to predict space closure after first permanent molar extraction in children. The AI framework accurately assesses factors like tooth development and angulation, aiding dental treatment planning.
Area of Science:
- Pediatric Dentistry
- Artificial Intelligence in Healthcare
- Radiographic Analysis
Background:
- First permanent molars (M1) are crucial for dental development but prone to decay and hypomineralization.
- Extraction of M1s necessitates careful space management for optimal outcomes.
- Current methods for predicting spontaneous space closure after M1 extraction can be subjective.
Purpose of the Study:
- To develop and validate an automated deep learning framework using YOLOv8n with oriented bounding boxes (OBB).
- To predict the likelihood of spontaneous space closure following first permanent molar extractions.
- To reduce diagnostic subjectivity and inter-observer variability in post-extraction space management.
Main Methods:
- A dataset of 200 pediatric panoramic radiographs was utilized.
- The YOLOv8n-OBB architecture was trained on segmented images, incorporating M3 presence, M2 developmental maturity, and M2 angulation.
- Inputs were mapped to an evidence-based clinical decision matrix for prognostic stratification.
Main Results:
- The YOLOv8n-OBB model demonstrated exceptional detection and localization performance (mAP@0.5 = 0.983).
- High accuracy was achieved for detecting second permanent molars (M2) (F1-score = 0.978) and third molars (M3) (F1-score = 0.904).
- Quantitative analysis confirmed accurate mapping of spatial data to clinical outcomes without error.
Conclusions:
- The YOLOv8n-OBB model is a robust and interpretable decision-support tool for pediatric dentistry.
- This framework standardizes prognostic assessments for M1 extractions.
- It optimizes treatment planning workflows, aiding clinicians in managing space closure after M1 extraction.
