Periapical lesion detection in periapical radiographs using the latest convolutional neural network ConvNeXt and its integrated models

Abstract To overcome the limitation of a single classification model’s inability to simultaneously identify multiple lesion targets within periapical radiographs, This study proposes YoCNET (Yolov5 + ConvNeXt), a novel deep learning integrated model. YoCNET leverages the target detection capability...

Full description

Saved in:
Bibliographic Details
Main Authors: Jian Liu, Xiaohua Liu, Yu Shao, Yongzhen Gao, Kexu Pan, Chaoran Jin, Honghai Ji, Yi Du, Xijiao Yu
Format: Article
Language:English
Published: Nature Portfolio 2024-10-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-75748-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850203597389692928
author Jian Liu
Xiaohua Liu
Yu Shao
Yongzhen Gao
Kexu Pan
Chaoran Jin
Honghai Ji
Yi Du
Xijiao Yu
author_facet Jian Liu
Xiaohua Liu
Yu Shao
Yongzhen Gao
Kexu Pan
Chaoran Jin
Honghai Ji
Yi Du
Xijiao Yu
author_sort Jian Liu
collection DOAJ
description Abstract To overcome the limitation of a single classification model’s inability to simultaneously identify multiple lesion targets within periapical radiographs, This study proposes YoCNET (Yolov5 + ConvNeXt), a novel deep learning integrated model. YoCNET leverages the target detection capability of Yolov5 and the image classification capability of ConvNeXt to achieve automatic segmentation of individual teeth and concurrent detection of periapical lesions across multiple teeth. A dataset of 1,305 periapical radiographs was used to train and validate the ConvNeXt and ResNet34 models, with an 8:2 split for training and validation. Deciduous teeth were excluded from the dataset. Furthermore, 717 individual teeth images were extracted from 200 previously unused periapical radiographs for integrated model validation. Evaluation metrics included accuracy, precision, sensitivity, F1 score, AUC (Area Under Curve), and a confusion matrix.The YoCNET integrated model demonstrated values of 90.93%, 98.88%, 85.30%, 0.9159, and 0.9757 for accuracy, precision, sensitivity, F1 score, and AUC, respectively. These metrics were superior to those achieved by the YoRNET (Yolov5 + ResNet34) integrated model, which recorded 80.47%, 83.78%, 82.16%, 0.8296, and 0.8822. The integrated model achieved high accuracy and efficiency in automatic teeh segmentation by Yolov5 and in automatically detecting multiple periapical lesions by ConvNeXt. YoCNET exhibited superior overall data performance, making it a more suitable deep learning integrated model for clinical applications.
format Article
id doaj-art-d861faf89aed49c4ace2fa01730d9923
institution OA Journals
issn 2045-2322
language English
publishDate 2024-10-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-d861faf89aed49c4ace2fa01730d99232025-08-20T02:11:29ZengNature PortfolioScientific Reports2045-23222024-10-0114111010.1038/s41598-024-75748-9Periapical lesion detection in periapical radiographs using the latest convolutional neural network ConvNeXt and its integrated modelsJian Liu0Xiaohua Liu1Yu Shao2Yongzhen Gao3Kexu Pan4Chaoran Jin5Honghai Ji6Yi Du7Xijiao Yu8School of Stomatology, Shandong Second Medical UniversityDepartment of Endodontics, Jinan Stamotological Hospital, Jinan Key Laboratory of Oral Tissue Regeneration, Shandong Provincial Health Commission Key Laboratory of Oral Diseases and Tissue RegenerationShandong Xintai Huizhi Health and Medical Big Data Co., Ltd.School of Stomatology, Binzhou Medical CollegeSchool of Stomatology, Shandong Second Medical UniversitySchool of Stomatology, Shandong Second Medical UniversitySchool of Stomatology, Shandong Second Medical UniversityDepartment of Endodontics, Central Laboratory, Jinan Stamotological Hospital, Jinan Key Laboratory of Oral Tissue Regeneration, Shandong Provincial Health Commission Key Laboratory of Oral Diseases and Tissue RegenerationSchool of Stomatology, Shandong Second Medical UniversityAbstract To overcome the limitation of a single classification model’s inability to simultaneously identify multiple lesion targets within periapical radiographs, This study proposes YoCNET (Yolov5 + ConvNeXt), a novel deep learning integrated model. YoCNET leverages the target detection capability of Yolov5 and the image classification capability of ConvNeXt to achieve automatic segmentation of individual teeth and concurrent detection of periapical lesions across multiple teeth. A dataset of 1,305 periapical radiographs was used to train and validate the ConvNeXt and ResNet34 models, with an 8:2 split for training and validation. Deciduous teeth were excluded from the dataset. Furthermore, 717 individual teeth images were extracted from 200 previously unused periapical radiographs for integrated model validation. Evaluation metrics included accuracy, precision, sensitivity, F1 score, AUC (Area Under Curve), and a confusion matrix.The YoCNET integrated model demonstrated values of 90.93%, 98.88%, 85.30%, 0.9159, and 0.9757 for accuracy, precision, sensitivity, F1 score, and AUC, respectively. These metrics were superior to those achieved by the YoRNET (Yolov5 + ResNet34) integrated model, which recorded 80.47%, 83.78%, 82.16%, 0.8296, and 0.8822. The integrated model achieved high accuracy and efficiency in automatic teeh segmentation by Yolov5 and in automatically detecting multiple periapical lesions by ConvNeXt. YoCNET exhibited superior overall data performance, making it a more suitable deep learning integrated model for clinical applications.https://doi.org/10.1038/s41598-024-75748-9
spellingShingle Jian Liu
Xiaohua Liu
Yu Shao
Yongzhen Gao
Kexu Pan
Chaoran Jin
Honghai Ji
Yi Du
Xijiao Yu
Periapical lesion detection in periapical radiographs using the latest convolutional neural network ConvNeXt and its integrated models
Scientific Reports
title Periapical lesion detection in periapical radiographs using the latest convolutional neural network ConvNeXt and its integrated models
title_full Periapical lesion detection in periapical radiographs using the latest convolutional neural network ConvNeXt and its integrated models
title_fullStr Periapical lesion detection in periapical radiographs using the latest convolutional neural network ConvNeXt and its integrated models
title_full_unstemmed Periapical lesion detection in periapical radiographs using the latest convolutional neural network ConvNeXt and its integrated models
title_short Periapical lesion detection in periapical radiographs using the latest convolutional neural network ConvNeXt and its integrated models
title_sort periapical lesion detection in periapical radiographs using the latest convolutional neural network convnext and its integrated models
url https://doi.org/10.1038/s41598-024-75748-9
work_keys_str_mv AT jianliu periapicallesiondetectioninperiapicalradiographsusingthelatestconvolutionalneuralnetworkconvnextanditsintegratedmodels
AT xiaohualiu periapicallesiondetectioninperiapicalradiographsusingthelatestconvolutionalneuralnetworkconvnextanditsintegratedmodels
AT yushao periapicallesiondetectioninperiapicalradiographsusingthelatestconvolutionalneuralnetworkconvnextanditsintegratedmodels
AT yongzhengao periapicallesiondetectioninperiapicalradiographsusingthelatestconvolutionalneuralnetworkconvnextanditsintegratedmodels
AT kexupan periapicallesiondetectioninperiapicalradiographsusingthelatestconvolutionalneuralnetworkconvnextanditsintegratedmodels
AT chaoranjin periapicallesiondetectioninperiapicalradiographsusingthelatestconvolutionalneuralnetworkconvnextanditsintegratedmodels
AT honghaiji periapicallesiondetectioninperiapicalradiographsusingthelatestconvolutionalneuralnetworkconvnextanditsintegratedmodels
AT yidu periapicallesiondetectioninperiapicalradiographsusingthelatestconvolutionalneuralnetworkconvnextanditsintegratedmodels
AT xijiaoyu periapicallesiondetectioninperiapicalradiographsusingthelatestconvolutionalneuralnetworkconvnextanditsintegratedmodels