Dental bur detection system based on asymmetric double convolution and adaptive feature fusion

Abstract This study aims to improve the detection of dental burs, which are often undetected due to their minuscule size, slender profile, and substantial manufacturing output. The present study introduces You Only Look Once-Dental bur (YOLO-DB), an innovative deep learning-driven methodology for th...

Full description

Saved in:
Bibliographic Details
Main Authors: HongLing Hou, Ao Yang, Xiangyao Li, Kangkai Zhu, Yandi Zhao, Zhiqiang Wu
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-83241-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841559481654181888
author HongLing Hou
Ao Yang
Xiangyao Li
Kangkai Zhu
Yandi Zhao
Zhiqiang Wu
author_facet HongLing Hou
Ao Yang
Xiangyao Li
Kangkai Zhu
Yandi Zhao
Zhiqiang Wu
author_sort HongLing Hou
collection DOAJ
description Abstract This study aims to improve the detection of dental burs, which are often undetected due to their minuscule size, slender profile, and substantial manufacturing output. The present study introduces You Only Look Once-Dental bur (YOLO-DB), an innovative deep learning-driven methodology for the accurate detection and counting of dental burs. A Lightweight Asymmetric Dual Convolution module (LADC) was devised to diminish the detrimental effects of extraneous features on the model’s precision, thereby enhancing the feature extraction network. Moreover, to augment the efficiency of feature integration and diminish computational demands, a novel fusion network combining SlimNeck with BiFPN-Concat was introduced, effectively merging superficial spatial details with profound semantic features. A specialized platform was developed for the detection and counting of dental burs, and rigorous experimental assessments were performed. Promising results were achieved. YOLO-DB yielded a Mean Average Precision (mAP@0.5) of 99.3% on the dental bur dataset, with a notable 3.2% increase in mAP@0.5:0.95 and a sustained detection pace of 128 frames per second. The model also achieved a 14.4% reduction in parameter volume and a 17.9% decrease in computational expenditure, while achieving a flawless counting accuracy of 100%. Our approach outperforms current detection algorithms in terms of detection capability and efficiency, presenting a new method for the precise detection and counting of elongated objects such as dental burs.
format Article
id doaj-art-016fd5b6450c4d3493338004f74ed790
institution Kabale University
issn 2045-2322
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-016fd5b6450c4d3493338004f74ed7902025-01-05T12:26:54ZengNature PortfolioScientific Reports2045-23222024-12-0114111410.1038/s41598-024-83241-6Dental bur detection system based on asymmetric double convolution and adaptive feature fusionHongLing Hou0Ao Yang1Xiangyao Li2Kangkai Zhu3Yandi Zhao4Zhiqiang Wu5School of Mechanical Engineering, Shaanxi University of TechnologySchool of Mechanical Engineering, Shaanxi University of TechnologySchool of Mechanical Engineering, Shaanxi University of TechnologySchool of Mechanical Engineering, Shaanxi University of TechnologySchool of Mechanical and Precision Instrumental Engineering, Xi’an University of TechnologySchool of Mechanical Engineering, Shaanxi University of TechnologyAbstract This study aims to improve the detection of dental burs, which are often undetected due to their minuscule size, slender profile, and substantial manufacturing output. The present study introduces You Only Look Once-Dental bur (YOLO-DB), an innovative deep learning-driven methodology for the accurate detection and counting of dental burs. A Lightweight Asymmetric Dual Convolution module (LADC) was devised to diminish the detrimental effects of extraneous features on the model’s precision, thereby enhancing the feature extraction network. Moreover, to augment the efficiency of feature integration and diminish computational demands, a novel fusion network combining SlimNeck with BiFPN-Concat was introduced, effectively merging superficial spatial details with profound semantic features. A specialized platform was developed for the detection and counting of dental burs, and rigorous experimental assessments were performed. Promising results were achieved. YOLO-DB yielded a Mean Average Precision (mAP@0.5) of 99.3% on the dental bur dataset, with a notable 3.2% increase in mAP@0.5:0.95 and a sustained detection pace of 128 frames per second. The model also achieved a 14.4% reduction in parameter volume and a 17.9% decrease in computational expenditure, while achieving a flawless counting accuracy of 100%. Our approach outperforms current detection algorithms in terms of detection capability and efficiency, presenting a new method for the precise detection and counting of elongated objects such as dental burs.https://doi.org/10.1038/s41598-024-83241-6Machine visionDental burRotating object detectionCounting and detection systemYOLOv8
spellingShingle HongLing Hou
Ao Yang
Xiangyao Li
Kangkai Zhu
Yandi Zhao
Zhiqiang Wu
Dental bur detection system based on asymmetric double convolution and adaptive feature fusion
Scientific Reports
Machine vision
Dental bur
Rotating object detection
Counting and detection system
YOLOv8
title Dental bur detection system based on asymmetric double convolution and adaptive feature fusion
title_full Dental bur detection system based on asymmetric double convolution and adaptive feature fusion
title_fullStr Dental bur detection system based on asymmetric double convolution and adaptive feature fusion
title_full_unstemmed Dental bur detection system based on asymmetric double convolution and adaptive feature fusion
title_short Dental bur detection system based on asymmetric double convolution and adaptive feature fusion
title_sort dental bur detection system based on asymmetric double convolution and adaptive feature fusion
topic Machine vision
Dental bur
Rotating object detection
Counting and detection system
YOLOv8
url https://doi.org/10.1038/s41598-024-83241-6
work_keys_str_mv AT honglinghou dentalburdetectionsystembasedonasymmetricdoubleconvolutionandadaptivefeaturefusion
AT aoyang dentalburdetectionsystembasedonasymmetricdoubleconvolutionandadaptivefeaturefusion
AT xiangyaoli dentalburdetectionsystembasedonasymmetricdoubleconvolutionandadaptivefeaturefusion
AT kangkaizhu dentalburdetectionsystembasedonasymmetricdoubleconvolutionandadaptivefeaturefusion
AT yandizhao dentalburdetectionsystembasedonasymmetricdoubleconvolutionandadaptivefeaturefusion
AT zhiqiangwu dentalburdetectionsystembasedonasymmetricdoubleconvolutionandadaptivefeaturefusion