Automatic classification and segmentation of multiclass jaw lesions in cone-beam CT using deep learning.

IF 2.9 2区 医学 Q1 DENTISTRY, ORAL SURGERY & MEDICINE Dento maxillo facial radiology Pub Date : 2024-10-01 DOI:10.1093/dmfr/twae028
Wei Liu, Xiang Li, Chang Liu, Ge Gao, Yutao Xiong, Tao Zhu, Wei Zeng, Jixiang Guo, Wei Tang
{"title":"Automatic classification and segmentation of multiclass jaw lesions in cone-beam CT using deep learning.","authors":"Wei Liu, Xiang Li, Chang Liu, Ge Gao, Yutao Xiong, Tao Zhu, Wei Zeng, Jixiang Guo, Wei Tang","doi":"10.1093/dmfr/twae028","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>To develop and validate a modified deep learning (DL) model based on nnU-Net for classifying and segmenting five-class jaw lesions using cone-beam CT (CBCT).</p><p><strong>Methods: </strong>A total of 368 CBCT scans (37 168 slices) were used to train a multi-class segmentation model. The data underwent manual annotation by two oral and maxillofacial surgeons (OMSs) to serve as ground truth. Sensitivity, specificity, precision, F1-score, and accuracy were used to evaluate the classification ability of the model and doctors, with or without artificial intelligence assistance. The dice similarity coefficient (DSC), average symmetric surface distance (ASSD), and segmentation time were used to evaluate the segmentation effect of the model.</p><p><strong>Results: </strong>The model achieved the dual task of classifying and segmenting jaw lesions in CBCT. For classification, the sensitivity, specificity, precision, and accuracy of the model were 0.871, 0.974, 0.874, and 0.891, respectively, surpassing oral and maxillofacial radiologists (OMFRs) and OMSs, approaching the specialist. With the model's assistance, the classification performance of OMFRs and OMSs improved, particularly for odontogenic keratocyst (OKC) and ameloblastoma (AM), with F1-score improvements ranging from 6.2% to 12.7%. For segmentation, the DSC was 87.2% and the ASSD was 1.359 mm. The model's average segmentation time was 40 ± 9.9 s, contrasting with 25 ± 7.2 min for OMSs.</p><p><strong>Conclusions: </strong>The proposed DL model accurately and efficiently classified and segmented five classes of jaw lesions using CBCT. In addition, it could assist doctors in improving classification accuracy and segmentation efficiency, particularly in distinguishing confusing lesions (eg, AM and OKC).</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"439-446"},"PeriodicalIF":2.9000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Dento maxillo facial radiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/dmfr/twae028","RegionNum":2,"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

Abstract

Objectives: To develop and validate a modified deep learning (DL) model based on nnU-Net for classifying and segmenting five-class jaw lesions using cone-beam CT (CBCT).

Methods: A total of 368 CBCT scans (37 168 slices) were used to train a multi-class segmentation model. The data underwent manual annotation by two oral and maxillofacial surgeons (OMSs) to serve as ground truth. Sensitivity, specificity, precision, F1-score, and accuracy were used to evaluate the classification ability of the model and doctors, with or without artificial intelligence assistance. The dice similarity coefficient (DSC), average symmetric surface distance (ASSD), and segmentation time were used to evaluate the segmentation effect of the model.

Results: The model achieved the dual task of classifying and segmenting jaw lesions in CBCT. For classification, the sensitivity, specificity, precision, and accuracy of the model were 0.871, 0.974, 0.874, and 0.891, respectively, surpassing oral and maxillofacial radiologists (OMFRs) and OMSs, approaching the specialist. With the model's assistance, the classification performance of OMFRs and OMSs improved, particularly for odontogenic keratocyst (OKC) and ameloblastoma (AM), with F1-score improvements ranging from 6.2% to 12.7%. For segmentation, the DSC was 87.2% and the ASSD was 1.359 mm. The model's average segmentation time was 40 ± 9.9 s, contrasting with 25 ± 7.2 min for OMSs.

Conclusions: The proposed DL model accurately and efficiently classified and segmented five classes of jaw lesions using CBCT. In addition, it could assist doctors in improving classification accuracy and segmentation efficiency, particularly in distinguishing confusing lesions (eg, AM and OKC).

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用深度学习对锥形束计算机断层扫描中的多类颌骨病变进行自动分类和分割。
目的开发并验证基于 nnU-net 的改进型深度学习(DL)模型,用于使用锥束计算机断层扫描(CBCT)对五类颌骨病变进行分类和分割:共使用了 368 次 CBCT 扫描(37 168 个切片)来训练多类分割模型。数据由两名口腔颌面外科医生(OMS)进行人工标注,作为基本真相。灵敏度、特异性、精确度、F1-分数和准确度用于评估模型和医生的分类能力,无论是否有人工智能辅助。骰子相似系数(DSC)、平均对称面距离(ASSD)和分割时间用于评估模型的分割效果:结果:该模型实现了在 CBCT 中对颌骨病变进行分类和分割的双重任务。在分类方面,模型的灵敏度、特异度、精确度和准确度分别为 0.871、0.974、0.874 和 0.891,超过了口腔颌面放射医师(OMFR)和 OMS,接近专科医师。在该模型的帮助下,口腔颌面部放射医师和口腔颌面部放射医师的分类性能有所提高,尤其是牙源性角化囊肿(OKC)和釉母细胞瘤(AM),F1 分数提高了 6.2% 到 12.7%。在分割方面,DSC 为 87.2%,ASSD 为 1.359 毫米。该模型的平均分割时间为 40 ± 9.9 秒,与 OMSs 的 25 ± 7.2 分钟形成鲜明对比:结论:所提出的 DL 模型利用 CBCT 准确、高效地对五类颌骨病变进行了分类和分割。此外,它还能帮助医生提高分类准确性和分割效率,尤其是在区分易混淆病变(如 AM 和 OKC)方面。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
5.60
自引率
9.10%
发文量
65
审稿时长
4-8 weeks
期刊介绍: Dentomaxillofacial Radiology (DMFR) is the journal of the International Association of Dentomaxillofacial Radiology (IADMFR) and covers the closely related fields of oral radiology and head and neck imaging. Established in 1972, DMFR is a key resource keeping dentists, radiologists and clinicians and scientists with an interest in Head and Neck imaging abreast of important research and developments in oral and maxillofacial radiology. The DMFR editorial board features a panel of international experts including Editor-in-Chief Professor Ralf Schulze. Our editorial board provide their expertise and guidance in shaping the content and direction of the journal. Quick Facts: - 2015 Impact Factor - 1.919 - Receipt to first decision - average of 3 weeks - Acceptance to online publication - average of 3 weeks - Open access option - ISSN: 0250-832X - eISSN: 1476-542X
期刊最新文献
Carotid calcifications in panoramic radiographs can predict vascular risk. Preparing for downstream tasks in AI for dental radiology: a baseline performance comparison of deep learning models. Temporomandibular joint assessment in MRI images using artificial intelligence tools: Where are we now? A systematic review. Gray values and noise behavior of cone-beam computed tomography machines-an in vitro study. A novel method for measuring the direction and angle of Central ray and predicting rotation center via panorama phantom.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1