文献速递口腔黏膜病口腔颌面外科

机器学习与临床医生在口腔黏膜病变检测与分类中的对比

Machine learning versus clinicians for detection and classification of oral mucosal lesions.
PubMed 文献 · J Dent · 2025-07-20

本研究利用4079张口内照片训练YOLOv8深度学习模型,对11类口腔黏膜病变进行检测和分类,并在独立测试集上与6名全科牙医和3名口腔外科专家比较。模型整体表现与专家相当(p=0.93),显著优于全科牙医(p<0.01)。

要点

  • YOLOv8模型在口腔黏膜病变分类和检测上整体表现与口腔外科专家相当。
  • 模型性能显著优于全科牙医,有望辅助临床评估。
  • HPV相关病变分类F1-score最高(0.80),角化病最低(0.43)。

核心结论

  • 深度学习模型在口腔黏膜病变检测与分类上表现与口腔外科专家相当,且显著优于全科牙医。

研究设计与样本

  • 回顾性研究,使用4079张口内照片标注边界框并分为11类,按80:20划分训练集(n=3031)和验证集(n=766),独立测试集n=282。
  • 采用YOLOv8计算机视觉模型进行图像分类和目标检测,测试集由6名全科牙医和3名口腔外科专家评估。

主要发现

  • 分类任务中,HPV相关病变F1-score最高(0.80)、AUROC最高(0.96);角化病F1-score最低(0.43)、AUROC最低(0.78)。
  • 目标检测任务中,HPV相关病变AP25=0.82,增殖性疣状白斑AP25=0.80、AP50=0.76;白斑AP25=0.36、AP50=0.20。
  • 模型整体表现与专家相当(p=0.93),显著优于全科牙医(p<0.01)。

临床怎么用

  • 该多类模型性能与口腔外科专家相当且优于全科牙医,可支持口腔病变的临床评估,有望促进潜在恶性疾病的早期诊断。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVES: The detection and classification of oral mucosal lesions is a challenging task due to high heterogeneity and overlap in clinical appearance. Nevertheless, differentiating benign from potentially malignant lesions is essential for appropriate management. This study evaluated whether a deep learning model trained to discriminate 11 classes of oral mucosal lesions could exceed the performance of general dentists. METHODS: 4079 intraoral photographs of benign, potentially malignant and malignant oral lesions were labeled using bounding boxes and classified into 11 classes. The data were split 80:20 for training (n = 3031) and validation (n = 766), keeping an independent test set (n = 282). The YOLOv8 computer vision model was implemented for image classification and object detection. Model performance was evaluated on the test set which was also assessed by six general dentists and three specialists in oral surgery. Evaluation metrics included sensitivity, specificity, F1-score, precision, area under the receiver operating characteristic curve (AUROC), and average precision (AP) at multiple thresholds of intersection over union. RESULTS: In terms of classification, the highest F1-score (0.80) and AUROC (0.96) were observed for human papillomavirus (HPV)-related lesions, whereas the lowest F1-score (0.43) and AUROC (0.78) were obtained for keratosis. In terms of object detection, the best results were achieved for HPV-related lesions (AP25 = 0.82) and proliferative verrucous leukoplakia (AP25 = 0.80; AP50 = 0.76), while the lowest values were noted for leukoplakia (AP25 = 0.36; AP50 = 0.20). Overall, the model performed comparable to specialists (p = 0.93) and significantly better than general dentists (p < 0.01). CONCLUSION: The developed model performed as well as specialists in oral surgery, highlighting its potential as a valuable tool for oral lesion assessment. CLINICAL SIGNIFICANCE: By providing performance comparable to oral surgeons and superior to general dentists, the developed multi-class model could support the clinical evaluation of oral lesions, potentially enabling earlier diagnosis of potentially malignant disorders, enhancing patient management and improving patient prognosis.

来源:J Dent,查看原文。版权归原作者所有。

引用

  1. Schwärzler J, Tolstaya E, Tichy A, et al. Machine learning versus clinicians for detection and classification of oral mucosal lesions. J Dent. 2025. PMID: 40695439. doi:10.1016/j.jdent.2025.105992

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。