通过临床摄影成像鉴别诊断口腔黏膜病变的深度学习系统。

IF 3.4 3区 医学 Q1 DENTISTRY, ORAL SURGERY & MEDICINE
An-Yu Su , Ming-Long Wu , Yu-Hsueh Wu
{"title":"通过临床摄影成像鉴别诊断口腔黏膜病变的深度学习系统。","authors":"An-Yu Su ,&nbsp;Ming-Long Wu ,&nbsp;Yu-Hsueh Wu","doi":"10.1016/j.jds.2024.10.019","DOIUrl":null,"url":null,"abstract":"<div><h3>Background/purpose</h3><div>Oral mucosal lesions are associated with a variety of pathological conditions. Most deep-learning-based convolutional neural network (CNN) systems for computer-aided diagnosis of oral lesions have typically concentrated on determining limited aspects of differential diagnosis. This study aimed to develop a CNN-based diagnostic model capable of classifying clinical photographs of oral ulcerative and associated lesions into five different diagnoses, thereby assisting clinicians in making accurate differential diagnoses.</div></div><div><h3>Materials and methods</h3><div>A set of clinical images were selected, including 506 images of five different diagnoses. The images were pre-processed and randomly divided into two sets for training and testing the CNN model. The model architecture was composed of convolutional layers, batch normalization layers, max pooling layers, the dropout layer and fully-connected layers. Evaluation metrics included weighted-precision, weighted-recall, weighted-F1 score, average specificity, Cohen’s Kappa coefficient, normalized confusion matrix and AUC.</div></div><div><h3>Results</h3><div>The overall performance for the image classification showed a weighted-precision of 88.8%, a weighted-recall of 88.2%, a weighted-F1 score of 0.878, an average pecificity of 97.0%, a Kappa coefficient of 0.851, and an average AUC of 0.985.</div></div><div><h3>Conclusion</h3><div>The model achieved a decent classification performance (overall AUC=0.985), showing the capacity to discern between benign and malignant potential lesions, and laid the foundation of a novel tool that can help clinical differential diagnosis of oral mucosal lesions. The main challenges were the small and imbalanced dataset. Enlarging the minority classes, incorporating more oral mucosal lesion diagnoses, employing transfer learning and cross-validation might be included in future works to optimize the image classification model.</div></div>","PeriodicalId":15583,"journal":{"name":"Journal of Dental Sciences","volume":"20 1","pages":"Pages 54-60"},"PeriodicalIF":3.4000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11763237/pdf/","citationCount":"0","resultStr":"{\"title\":\"Deep learning system for the differential diagnosis of oral mucosal lesions through clinical photographic imaging\",\"authors\":\"An-Yu Su ,&nbsp;Ming-Long Wu ,&nbsp;Yu-Hsueh Wu\",\"doi\":\"10.1016/j.jds.2024.10.019\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background/purpose</h3><div>Oral mucosal lesions are associated with a variety of pathological conditions. Most deep-learning-based convolutional neural network (CNN) systems for computer-aided diagnosis of oral lesions have typically concentrated on determining limited aspects of differential diagnosis. This study aimed to develop a CNN-based diagnostic model capable of classifying clinical photographs of oral ulcerative and associated lesions into five different diagnoses, thereby assisting clinicians in making accurate differential diagnoses.</div></div><div><h3>Materials and methods</h3><div>A set of clinical images were selected, including 506 images of five different diagnoses. The images were pre-processed and randomly divided into two sets for training and testing the CNN model. The model architecture was composed of convolutional layers, batch normalization layers, max pooling layers, the dropout layer and fully-connected layers. Evaluation metrics included weighted-precision, weighted-recall, weighted-F1 score, average specificity, Cohen’s Kappa coefficient, normalized confusion matrix and AUC.</div></div><div><h3>Results</h3><div>The overall performance for the image classification showed a weighted-precision of 88.8%, a weighted-recall of 88.2%, a weighted-F1 score of 0.878, an average pecificity of 97.0%, a Kappa coefficient of 0.851, and an average AUC of 0.985.</div></div><div><h3>Conclusion</h3><div>The model achieved a decent classification performance (overall AUC=0.985), showing the capacity to discern between benign and malignant potential lesions, and laid the foundation of a novel tool that can help clinical differential diagnosis of oral mucosal lesions. The main challenges were the small and imbalanced dataset. Enlarging the minority classes, incorporating more oral mucosal lesion diagnoses, employing transfer learning and cross-validation might be included in future works to optimize the image classification model.</div></div>\",\"PeriodicalId\":15583,\"journal\":{\"name\":\"Journal of Dental Sciences\",\"volume\":\"20 1\",\"pages\":\"Pages 54-60\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2025-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11763237/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Dental Sciences\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1991790224003623\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"DENTISTRY, ORAL SURGERY & MEDICINE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Dental Sciences","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1991790224003623","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}
引用次数: 0

摘要

背景/目的:口腔黏膜病变与多种病理状况有关。大多数基于深度学习的卷积神经网络(CNN)系统用于口腔病变的计算机辅助诊断,通常集中在确定鉴别诊断的有限方面。本研究旨在建立一个基于cnn的诊断模型,将口腔溃疡及相关病变的临床照片分类为5种不同的诊断,从而帮助临床医生做出准确的鉴别诊断。材料与方法:选取一组临床影像,包括5种不同诊断的506张影像。对图像进行预处理,随机分成两组用于训练和测试CNN模型。该模型由卷积层、批归一化层、最大池化层、dropout层和全连接层组成。评估指标包括加权精度、加权召回率、加权f1评分、平均特异性、科恩Kappa系数、归一化混淆矩阵和AUC。结果:图像分类总体表现为加权精度为88.8%,加权召回率为88.2%,加权f1得分为0.878,平均特异性为97.0%,Kappa系数为0.851,平均AUC为0.985。结论:该模型具有较好的分类性能(总AUC=0.985),具有区分良、恶性潜在病变的能力,为帮助临床鉴别口腔黏膜病变奠定了新的工具基础。主要的挑战是小而不平衡的数据集。未来的工作可能包括扩大少数类别、纳入更多口腔粘膜病变诊断、采用迁移学习和交叉验证等方法来优化图像分类模型。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Deep learning system for the differential diagnosis of oral mucosal lesions through clinical photographic imaging

Background/purpose

Oral mucosal lesions are associated with a variety of pathological conditions. Most deep-learning-based convolutional neural network (CNN) systems for computer-aided diagnosis of oral lesions have typically concentrated on determining limited aspects of differential diagnosis. This study aimed to develop a CNN-based diagnostic model capable of classifying clinical photographs of oral ulcerative and associated lesions into five different diagnoses, thereby assisting clinicians in making accurate differential diagnoses.

Materials and methods

A set of clinical images were selected, including 506 images of five different diagnoses. The images were pre-processed and randomly divided into two sets for training and testing the CNN model. The model architecture was composed of convolutional layers, batch normalization layers, max pooling layers, the dropout layer and fully-connected layers. Evaluation metrics included weighted-precision, weighted-recall, weighted-F1 score, average specificity, Cohen’s Kappa coefficient, normalized confusion matrix and AUC.

Results

The overall performance for the image classification showed a weighted-precision of 88.8%, a weighted-recall of 88.2%, a weighted-F1 score of 0.878, an average pecificity of 97.0%, a Kappa coefficient of 0.851, and an average AUC of 0.985.

Conclusion

The model achieved a decent classification performance (overall AUC=0.985), showing the capacity to discern between benign and malignant potential lesions, and laid the foundation of a novel tool that can help clinical differential diagnosis of oral mucosal lesions. The main challenges were the small and imbalanced dataset. Enlarging the minority classes, incorporating more oral mucosal lesion diagnoses, employing transfer learning and cross-validation might be included in future works to optimize the image classification model.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Dental Sciences
Journal of Dental Sciences 医学-牙科与口腔外科
CiteScore
5.10
自引率
14.30%
发文量
348
审稿时长
6 days
期刊介绍: he Journal of Dental Sciences (JDS), published quarterly, is the official and open access publication of the Association for Dental Sciences of the Republic of China (ADS-ROC). The precedent journal of the JDS is the Chinese Dental Journal (CDJ) which had already been covered by MEDLINE in 1988. As the CDJ continued to prove its importance in the region, the ADS-ROC decided to move to the international community by publishing an English journal. Hence, the birth of the JDS in 2006. The JDS is indexed in the SCI Expanded since 2008. It is also indexed in Scopus, and EMCare, ScienceDirect, SIIC Data Bases. The topics covered by the JDS include all fields of basic and clinical dentistry. Some manuscripts focusing on the study of certain endemic diseases such as dental caries and periodontal diseases in particular regions of any country as well as oral pre-cancers, oral cancers, and oral submucous fibrosis related to betel nut chewing habit are also considered for publication. Besides, the JDS also publishes articles about the efficacy of a new treatment modality on oral verrucous hyperplasia or early oral squamous cell carcinoma.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信