Related Experiment Video
Updated: Jun 4, 2025
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
766
Dental bur detection system based on asymmetric double convolution and adaptive feature fusion
HongLing Hou1,2, Ao Yang3, Xiangyao Li3
1School of Mechanical Engineering, Shaanxi University of Technology, Hanzhong, 723001, China. xjtuhhl@163.com.
Scientific Reports
|December 31, 2024
Summary
This study introduces YOLO-DB, a deep learning model for detecting small dental burs with 99.3% accuracy. The efficient method achieves flawless counting and outperforms existing algorithms.
Area of Science:
- Computer Vision
- Medical Imaging
- Deep Learning
Background:
- Dental burs are challenging to detect due to their small size and shape.
- Existing detection methods lack precision and efficiency for these objects.
Purpose of the Study:
- To develop an accurate and efficient deep learning model for dental bur detection and counting.
- To introduce the You Only Look Once-Dental bur (YOLO-DB) methodology.
Main Methods:
- Developed a novel deep learning model, YOLO-DB, incorporating a Lightweight Asymmetric Dual Convolution (LADC) module.
- Introduced a fusion network combining SlimNeck with BiFPN-Concat for enhanced feature integration.
- Created a specialized platform for dental bur detection and counting with rigorous experimental validation.
Main Results:
- Achieved a Mean Average Precision (mAP@0.5) of 99.3% on the dental bur dataset.
- Demonstrated a 3.2% increase in mAP@0.5:0.95 and a detection speed of 128 frames per second.
- Reduced parameter volume by 14.4% and computational cost by 17.9%, with 100% counting accuracy.
Conclusions:
- YOLO-DB offers superior detection capability and efficiency for dental burs compared to current algorithms.
- The model provides a novel approach for precise detection and counting of elongated objects.
- This methodology enhances automated inspection in relevant industrial applications.
