Single-step prediction of inferior alveolar nerve injury after mandibular third-molar extraction using contrastive learning and Bayesian auto-tuned deep learning model

作者
Kyubaek Yoon,Yiseul Choi,Myoungho Lee,Jaeyeon Kim,Jun‐Young Kim,Jin‐Woo Kim,Jongeun Choi,Wonse Park
出处
期刊:Dentomaxillofacial Radiology [Oxford University Press]
标识
DOI:10.1093/dmfr/twaf069
摘要

Abstract Objective Inferior alveolar nerve (IAN) injury is a critical complication of mandibular third-molar extraction. This study aimed to construct and evaluate a deep learning framework that integrates contrastive learning and Bayesian optimization to enhance predictive performance using cone-beam computed tomography (CBCT) and panoramic radiographs. Methods A retrospective dataset of 902 panoramic radiographs and 1,500 CBCT images was used. Five deep learning architectures (MobileNetV2, ResNet101D, Vision Transformer, Twins-SVT, and SSL-ResNet50) were trained with and without contrastive learning and Bayesian optimization. Model performance was evaluated using accuracy, F1-score, and comparison with oral and maxillofacial surgeons (OMFSs). Results Contrastive learning significantly improved the F1-scores across all models (e.g., MobileNetV2: 0.302 to 0.740; ResNet101D: 0.188 to 0.689; Vision Transformer: 0.275 to 0.704; Twins-SVT: 0.370 to 0.719; SSL-ResNet50: 0.109 to 0.576). Bayesian optimization further enhanced the F1-scores for MobileNetV2 (from 0.740 to 0.923), ResNet101D (from 0.689 to 0.857), Vision Transformer (from 0.704 to 0.871), Twins-SVT (from 0.719 to 0.857), and SSL-ResNet50 (from 0.576 to 0.875). The AI model outperformed OMFSs on CBCT cross-sectional images (F1-score: 0.923 vs. 0.667) but underperformed on panoramic radiographs (0.666 vs. 0.730). Conclusions The proposed single-step deep learning approach effectively predicts IAN injury, with contrastive learning addressing data imbalance and Bayesian optimization enhancing model performance. While artificial intelligence surpasses human performance on CBCT images, panoramic radiograph analysis still benefits from expert interpretation. Future work should focus on multi-center validation and explainable artificial intelligence for broader clinical adoption.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
777发布了新的文献求助10
刚刚
tlc_191026发布了新的文献求助10
刚刚
1秒前
molihuakai的应助被激动的绿竹采纳,获得10
2秒前
dbwdqqr发布了新的文献求助10
2秒前
MiyaGuo发布了新的文献求助10
2秒前
lfp发布了新的文献求助10
6秒前
小蘑菇的应助被丹皮小姐采纳,获得10
7秒前
CipherSage的应助被renn采纳,获得20
10秒前
Leon完成签到,获得积分10
11秒前
13秒前
13秒前
14秒前
14秒前
16秒前
思源的应助被聪明雨灵采纳,获得10
16秒前
速写发布了新的文献求助10
18秒前
仁兼内圣外王完成签到,获得积分10
18秒前
115完成签到,获得积分10
19秒前
19秒前
Zhangyuanjie发布了新的文献求助30
20秒前
20秒前
愉快书琴发布了新的文献求助10
20秒前
wanci的应助被lzh采纳,获得10
20秒前
21秒前
NS亦wwt完成签到,获得积分10
21秒前
无花果的应助被冷冷子采纳,获得10
21秒前
水弘的应助被corleeang采纳,获得10
22秒前
科研通AI6.4的应助被牧百川采纳,获得10
22秒前
23秒前
余海川发布了新的文献求助80
24秒前
sanshu发布了新的文献求助10
25秒前
25秒前
ycube完成签到,获得积分10
26秒前
时间发布了新的文献求助10
26秒前
bkagyin的应助被璇璇采纳,获得30
27秒前
Maestro_S的应助被对方正在输入采纳,获得10
28秒前
辉仔完成签到,获得积分10
28秒前
李健的粉丝团团长的应助被renn采纳,获得20
29秒前
29秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183449
求助须知:如何正确求助?哪些是违规求助? 9572834
关于积分的说明 21827509
捐赠科研通 7780646
什么是DOI,文献DOI怎么找? 3434016
关于科研通互助平台的介绍 2558189
邀请新用户注册赠送积分活动 2480371