Performance of artificial intelligence-based diagnosis and classification of peri-implantitis compared with periodontal surgeon assessment: a pilot study of panoramic radiograph analysis.

IF 2.2 4区 医学 Q2 DENTISTRY, ORAL SURGERY & MEDICINE
Jae-Hong Lee, Yeon-Tae Kim, Falk Schwendicke
{"title":"Performance of artificial intelligence-based diagnosis and classification of peri-implantitis compared with periodontal surgeon assessment: a pilot study of panoramic radiograph analysis.","authors":"Jae-Hong Lee, Yeon-Tae Kim, Falk Schwendicke","doi":"10.5051/jpis.2500280014","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>The aim of this study was to evaluate the diagnostic and classification performance of a deep learning (DL) model for peri-implantitis-related bone defects using panoramic radiographs, focusing on defect morphology and severity.</p><p><strong>Methods: </strong>A dataset comprising 1,075 panoramic radiographs from 426 patients with peri-implantitis was analyzed. A total of 2,250 implant sites were annotated and categorized based on defect morphology (intraosseous [class I], supracrestal/horizontal [class II], or combined [class III]) and severity (slight, moderate, or severe). The ensemble-based YOLOv8 DL model was trained on 80% of the dataset, with the remaining 20% reserved for testing. Performance was assessed using classification metrics, including accuracy, precision, recall, and F1 score. The diagnostic accuracy of the DL model was also compared with that of 2 board-certified periodontal surgeons.</p><p><strong>Results: </strong>The DL model achieved an overall accuracy of 85.33%, significantly outperforming the periodontal surgeons, who exhibited a mean accuracy of 75.6%. The DL model performed especially well for slight class II defects, with precision and recall values of 100% and 98%, respectively. In contrast, the periodontal surgeons demonstrated higher accuracy in severe cases, particularly for class II defects.</p><p><strong>Conclusions: </strong>DL enables reliable and accurate detection of peri-implantitis bone defects. It outperformed periodontal surgeons in overall accuracy, demonstrating its potential as a valuable second-opinion tool to support clinical decision-making. Future research should focus on expanding datasets and incorporating multimodal imaging.</p>","PeriodicalId":48795,"journal":{"name":"Journal of Periodontal and Implant Science","volume":" ","pages":""},"PeriodicalIF":2.2000,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Periodontal and Implant Science","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.5051/jpis.2500280014","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose: The aim of this study was to evaluate the diagnostic and classification performance of a deep learning (DL) model for peri-implantitis-related bone defects using panoramic radiographs, focusing on defect morphology and severity.

Methods: A dataset comprising 1,075 panoramic radiographs from 426 patients with peri-implantitis was analyzed. A total of 2,250 implant sites were annotated and categorized based on defect morphology (intraosseous [class I], supracrestal/horizontal [class II], or combined [class III]) and severity (slight, moderate, or severe). The ensemble-based YOLOv8 DL model was trained on 80% of the dataset, with the remaining 20% reserved for testing. Performance was assessed using classification metrics, including accuracy, precision, recall, and F1 score. The diagnostic accuracy of the DL model was also compared with that of 2 board-certified periodontal surgeons.

Results: The DL model achieved an overall accuracy of 85.33%, significantly outperforming the periodontal surgeons, who exhibited a mean accuracy of 75.6%. The DL model performed especially well for slight class II defects, with precision and recall values of 100% and 98%, respectively. In contrast, the periodontal surgeons demonstrated higher accuracy in severe cases, particularly for class II defects.

Conclusions: DL enables reliable and accurate detection of peri-implantitis bone defects. It outperformed periodontal surgeons in overall accuracy, demonstrating its potential as a valuable second-opinion tool to support clinical decision-making. Future research should focus on expanding datasets and incorporating multimodal imaging.

基于人工智能的种植周炎诊断和分类与牙周外科医生评估的比较:全景x线片分析的初步研究。
目的:本研究的目的是利用全景x线片评估深度学习(DL)模型对种植体周围相关骨缺损的诊断和分类性能,重点关注缺损形态和严重程度。方法:对426例种植体周围炎患者的1075张全景x线片数据进行分析。根据缺损形态(骨内缺损[I类]、骨上/水平缺损[II类]或合并缺损[III类])和严重程度(轻度、中度或重度),对总共2250个植入部位进行了注释和分类。基于集成的YOLOv8 DL模型在80%的数据集上进行了训练,剩下的20%用于测试。使用分类指标评估性能,包括准确性、精密度、召回率和F1分数。DL模型的诊断准确性也与2名委员会认证的牙周外科医生进行了比较。结果:DL模型的总体准确率为85.33%,明显优于牙周外科医生的平均准确率75.6%。DL模型对于轻微的II类缺陷表现得特别好,精度和召回率分别为100%和98%。相比之下,牙周外科医生在严重的病例中表现出更高的准确性,特别是对于II类缺陷。结论:深度扫描能够可靠、准确地检测种植体周围骨缺损。它在整体准确性上优于牙周外科医生,证明了它作为支持临床决策的有价值的第二意见工具的潜力。未来的研究应集中在扩展数据集和结合多模态成像。
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 求助全文
来源期刊
Journal of Periodontal and Implant Science
Journal of Periodontal and Implant Science DENTISTRY, ORAL SURGERY & MEDICINE-
CiteScore
3.30
自引率
5.30%
发文量
38
期刊介绍: Journal of Periodontal & Implant Science (JPIS) is a peer-reviewed and open-access journal providing up-to-date information relevant to professionalism of periodontology and dental implantology. JPIS is dedicated to global and extensive publication which includes evidence-based original articles, and fundamental reviews in order to cover a variety of interests in the field of periodontal as well as implant science.
×
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