基于YOLOv11模型的牙周疾病智能筛查研究

doi:10.13701/j.cnki.kqyxyj.2026.09.004

口腔医学研究 ›› 2026, Vol. 42 ›› Issue (9): 752-757.DOI: 10.13701/j.cnki.kqyxyj.2026.09.004

基于YOLOv11模型的牙周疾病智能筛查研究

张婷^1,2, 靳能皓^2,3, 李粮博^1,2, 朱亮^1,2, 李壮壮^1,2, 张海钟^1*

1.解放军总医院第一医学中心口腔科北京 100853;
2.解放军医学院北京 100853;
3.清华大学附属北京清华长庚医院,清华大学临床医学院北京 102218

收稿日期:2026-01-04 出版日期:2026-09-28 发布日期:2026-09-22
通讯作者: * 张海钟,E-mail:zhanghaizhong@301hospital.com.cn
作者简介:张婷(1994~ ),女,河北保定人,硕士,医师,研究方向:口腔医学,人工智能,牙周疾病。
基金资助:
国家卫生健康委能力建设和继续教育中心-口腔龋病标准数据库建设(编号:KQC2024JJS001)

Research on Intelligent Screening of Periodontal Diseases Based on YOLOv11

ZHANG Ting^1,2, JIN Nenghao^2,3, LI Liangbo^1,2, ZHU Liang^1,2, LI Zhuangzhuang^1,2, ZHANG Haizhong^1*

1. Department of Stomatology, Chinese PLA General Hospital, Beijing 100853, China;
2. Medical School of Chinese PLA, Beijing 100853, China;
3. Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing 102218, China

Received:2026-01-04 Online:2026-09-28 Published:2026-09-22

摘要/Abstract

摘要： 目的:构建基于深度学习的人工智能模型,利用便携式口腔内窥镜图像实现牙周疾病的早期筛查与检测。方法:收集内窥镜拍摄的1206张牙周病变图像,经整理、清洗与规范标注后,按7∶1∶1划分为训练集、验证集和测试集。采用YOLOv11模型进行训练与测试,使用精确度、召回率、F1分数及平均精度均值评估模型性能。结果:测试集中,模型在交并比(intersection over union,IoU)阈值为0.5时的平均精度为0.8044,F1分数为0.7953。牙龈退缩、牙龈红肿和牙结石的识别平均精度分别为0.7861、0.8511和0.7761。结论:所构建的深度学习模型能够低成本实现牙周疾病的早期筛查,为人工智能在牙周病早期检测中的应用提供了重要参考。

关键词: 人工智能, 牙周病, 口腔内窥镜, 深度学习

Abstract: Objective: To develop a deep learning-based AI model for early screening and detection of periodontal diseases using images from a portable oral endoscope. Methods: A dataset of 1206 periodontal disease images captured by the endoscope was constructed. After data curation, cleaning, and standardized annotation, the dataset was split into training, validation, and test sets in a 7∶1∶1 ratio. The YOLOv11 model was employed for training and evaluation, with performance assessed using precision, recall, F1-score, and mean average precision (mAP). Results: On the test set, the model achieved an mAP of 0.8044 at an IoU threshold of 0.5 and an F1-score of 0.7953. The average precision for detecting gingival recession, gingival redness and swelling, and dental calculus was 0.7861, 0.8511, and 0.7761, respectively. Conclusion: The developed deep learning model enables low-cost early screening of periodontal diseases and provides a valuable reference for the application of AI in early periodontal disease detection.

Key words: artificial intelligence, periodontal disease, intraoral endoscopy, deep learning

张婷, 靳能皓, 李粮博, 朱亮, 李壮壮, 张海钟. 基于YOLOv11模型的牙周疾病智能筛查研究[J]. 口腔医学研究, 2026, 42(9): 752-757.

ZHANG Ting, JIN Nenghao, LI Liangbo, ZHU Liang, LI Zhuangzhuang, ZHANG Haizhong. Research on Intelligent Screening of Periodontal Diseases Based on YOLOv11[J]. Journal of Oral Science Research, 2026, 42(9): 752-757.

参考文献

[1] Glick M, Williams DM, Kleinman DV, et al. A new definition for oral health developed by the FDI World Dental Federation opens the door to a universal definition of oral health [J]. Br Dent J, 2016, 221(12): 792-793.
[2] Jain N, Dutt U, Radenkov I, et al. WHO's global oral health status report 2022: Actions, discussion and implementation [J]. Oral Dis, 2024, 30(2): 73-79.
[3] Caton JG, Armitage G, Berglundh T, et al. A new classification scheme for periodontal and peri-implant diseases and conditions-Introduction and key changes from the 1999 classification [J]. J Periodontol, 2018, 89 Suppl 1: S1-S8.
[4] Muñoz Aguilera E, Suvan J, Buti J, et al. Periodontitis is associated with hypertension: a systematic review and meta-analysis [J]. Cardiovasc Res, 2020, 116(1): 28-39.
[5] Dominy SS, Lynch C, Ermini F, et al. Porphyromonas gingivalis in Alzheimer's disease brains: Evidence for disease causation and treatment with small-molecule inhibitors [J]. Sci Adv, 2019, 5(1): eaau3333.
[6] Offenbacher S, Katz V, Fertik G, et al. Periodontal infection as a possible risk factor for preterm low birth weight [J]. J Periodontol, 1996, 67 Suppl 10S: 1103-1113.
[7] Viet CT, Zhang M, Dharmaraj N, et al. Artificial intelligence applications in oral cancer and oral dysplasia [J]. Tissue Eng Part A, 2024, 30(19-20): 640-651.
[8] Shan T, Tay FR, Gu L. Application of artificial intelligence in dentistry [J]. J Dent Res, 2021, 100(3): 232-244.
[9] Sunnetci KM, Ulukaya S, Alkan A. Periodontal bone loss detection based on hybrid deep learning and machine learning models with a user-friendly application [J]. Biomed Signal Process Control, 2022, 77: 103844.
[10] Shon HS, Kong V, Park JS, et al. Deep learning model for classifying periodontitis stages on dental panoramic radiography [J]. Appl Sci, 2022, 12(17): 8500.
[11] Caton JG, Armitage G, Berglundh T, et al. A new classification scheme for periodontal and peri-implant diseases and conditions-introduction and key changes from the 1999 classification [J]. J Periodontol, 2018, 89 Suppl 1: S1-S8.
[12] Peres MA, Macpherson LMD, Weyant RJ, et al. Oral diseases: a global public health challenge [J]. Lancet, 2019, 394(10194): 249-260.
[13] Tonetti MS, Van Dyke TE; working group 1 of the joint EFP/AAP workshop. Periodontitis and atherosclerotic cardiovascular disease: consensus report of the Joint EFP/AAPWorkshop on Periodontitis and Systemic Diseases [J]. J Periodontol, 2013, 84 Suppl 4S: S24-S29.
[14] Bayati M, Alizadeh Savareh B, Ahmadinejad H, et al. Advanced AI-driven detection of interproximal caries in bitewing radiographs using YOLOv8 [J]. Sci Rep, 2025, 15(1): 4641.
[15] Boztuna M, Firincioglulari M, Akkaya N, et al. Segmentation of periapical lesions with automatic deep learning on panoramic radiographs: an artificial intelligence study [J]. BMC Oral Health, 2024, 24(1): 1332.
[16] Vilcapoma P, Parra Meléndez D, Fernández A, et al. Comparison of faster R-CNN, YOLO, and SSD for third molar angle detection in dental panoramic X-rays [J]. Sensors (Basel), 2024, 24(18): 6053.
[17] Li L, Pu C, Tao J, et al. Development of an oral cancer detection system through deep learning [J]. BMC Oral Health, 2024, 24(1): 1468.
[18] Kurt-Bayrakdar S, Bayrakdar ⅰŞ, Yavuz MB, et al. Detection of periodontal bone loss patterns and furcation defects from panoramic radiographs using deep learning algorithm: A retrospective study [J]. BMC Oral Health, 2024, 24(1): 155.
[19] Krois J, Ekert T, Meinhold L, et al. Deep learning for the radiographic detection of periodontal bone loss [J]. Sci Rep, 2019, 9(1): 8495.
[20] Xue T, Chen L, Sun Q. Deep learning method to automatically diagnose periodontal bone loss and periodontitis stage in dental panoramic radiograph [J]. J Dent, 2024, 150: 105373.
[21] Chen CC, Wu YF, Aung LM, et al. Automatic recognition of teeth and periodontal bone loss measurement in digital radiographs using deep-learning artificial intelligence [J]. J Dent Sci, 2023, 18(3): 1301-1309.
[22] Thanh MTG, Van Toan N, Ngoc VTN, et al. Deep learning application in dental caries detection using intraoral photos taken by smartphones [J]. Appl Sci, 2022, 12(11): 5504.
[23] Ding B, Zhang Z, Liang Y, et al. Detection of dental caries in oral photographs taken by mobile phones based on the YOLOv3 algorithm [J]. Ann Transl Med, 2021, 9(21): 1622.
[24] Rashid U, Javid A, Khan AR, et al. A hybrid mask RCNN-based tool to localize dental cavities from real-time mixed photographic images [J]. PeerJ Comput Sci, 2022, 8: e888.
[25] Kühnisch J, Meyer O, Hesenius M, et al. Caries detection on intraoral images using artificial intelligence [J]. J Dent Res, 2022, 101(2): 158-165.
[26] 朱红标,刘强冬,曾子强,等.基于口内数码照图像深度学习的牙周病早期筛查研究[J].口腔医学研究,2022,38(11): 1092-1095.
[27] Park EY, Cho H, Kang S, et al. Caries detection with tooth surface segmentation on intraoral photographic images using deep learning [J]. BMC Oral Health, 2022, 22(1): 573.
[28] Kim D, Choi J, Ahn S, et al. A smart home dental care system: integration of deep learning, image sensors, and mobile controller [J]. J Ambient Intell Humaniz Comput, 2023, 14(2): 1123-1131.
[29] Moharrami M, Farmer J, Singhal S, et al. Detecting dental caries on oral photographs using artificial intelligence: A systematic review [J]. Oral Dis, 2024, 30(4): 1765-1783.
[30] Liu Y, Cheng Y, Song Y, et al. Oral screening of dental calculus, gingivitis and dental caries through segmentation on intraoral photographic images using deep learning [J]. BMC Oral Health, 2024, 24(1): 1287.

基于YOLOv11模型的牙周疾病智能筛查研究

Research on Intelligent Screening of Periodontal Diseases Based on YOLOv11

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	褚青, 牟海瑜, 许针针, 孙轶群, 高艳, 高玉光, 相黎黎, 董志恒. Amelotin基因对结合上皮屏障功能影响的研究[J]. 口腔医学研究, 2026, 42(7): 569-574.
[2]	饶淇升, 张国权. 不同超声技术在腮腺肿瘤中的应用[J]. 口腔医学研究, 2026, 42(6): 467-471.
[3]	陈重颖, 刘建国. 机器人辅助系统在口腔临床中的应用与现状[J]. 口腔医学研究, 2026, 42(4): 281-285.
[4]	王晓雯, 高莺. 深度学习在种植体周围炎预测诊断中的应用研究进展[J]. 口腔医学研究, 2026, 42(3): 186-190.
[5]	李放, 潘研, 韩爽, 庄硕. 深度学习在上颌窦建模中的应用[J]. 口腔医学研究, 2026, 42(3): 206-212.
[6]	尹清, 唐倩, 包幸福. 基于YOLOv7深度学习模型的正畸患者口内照片牙菌斑目标检测研究[J]. 口腔医学研究, 2026, 42(3): 242-246.
[7]	邱岳, 韩阳平, 邓冠红, 李菁. 基于深度学习的三维牙槽骨吸收评估及牙周炎分期[J]. 口腔医学研究, 2025, 41(8): 695-699.
[8]	杨青默, 魏攀, 华红. 智能化时代下的口腔黏膜病学——人工智能应用研究的现状与展望[J]. 口腔医学研究, 2025, 41(1): 1-6.
[9]	崔宇琛, 谢元栋, 吴聿淼, 牛凌霄, 常路广达, 朱宪春. 基于ViT-B深度学习模型的口腔良恶性病变图像分类研究[J]. 口腔医学研究, 2025, 41(1): 16-20.
[10]	王蓉, 帕克扎提·色依提, 王铁梅, 张懿, 钱堃. 比较Mask-RCNN与Mimics在上颌窦建模中的应用[J]. 口腔医学研究, 2024, 40(6): 550-554.
[11]	苏莉雯, 吴杨. 生成式人工智能在口腔医学的应用潜力与挑战[J]. 口腔医学研究, 2024, 40(1): 11-17.
[12]	樊秀汝, 刘佳. 正畸治疗在牙周病联合治疗中的应用[J]. 口腔医学研究, 2023, 39(9): 780-784.
[13]	古力孜巴·艾海提, 张鹏鑫, 齐佳, 亚尔肯·阿吉, 许辉. 腭裂术后腭咽闭合不全患者面部扭曲行为与腭咽闭合程度的关系[J]. 口腔医学研究, 2023, 39(8): 696-700.
[14]	温佳欢, 傅裕杰, 任根强, 陈宇飞, 张旗. 基于深度学习的点云补全网络修复上颌磨牙钙化根管的研究[J]. 口腔医学研究, 2023, 39(5): 455-459.
[15]	杨可, 孙雅楠, 胡雅英, 吕宜楠, 郑小风, 李易玮, 张佳莉. cyclin D1表达模式深度学习识别和预测模型对HPV阴性口腔鳞状细胞癌和口咽鳞状细胞癌患者预后的预测作用[J]. 口腔医学研究, 2023, 39(4): 308-315.