Kartbak Sultan Büşra Ay, Özel Mehmet Birol, Kocakaya Duygu Nur Cesur, Çakmak Muhammet, Sinanoğlu Enver Alper
Department of Orthodontics, Faculty of Dentistry, Kocaeli University, Kocaeli 41190, Türkiye.
Private Practice, Gölcük 41650, Türkiye.
Diagnostics (Basel). 2025 Apr 22;15(9):1059. doi: 10.3390/diagnostics15091059.
: Clinical intraoral photographs are important for orthodontic diagnosis, treatment planning, and documentation. This study aimed to evaluate deep learning algorithms trained utilizing actual cephalometric measurements for the classification of intraoral clinical photographs. : This study was executed on lateral cephalograms and intraoral right-side images of 990 patients. IMPA, interincisal angle, U1-palatal plane angle, and Wits appraisal values were measured utilizing WebCeph. Intraoral photographs were divided into three groups based on cephalometric measurements. A total of 14 deep learning models (DenseNet 121, DenseNet 169, DenseNet 201, EfficientNet B0, EfficientNet V2, Inception V3, MobileNet V2, NasNetMobile, ResNet101, ResNet152, ResNet50, VGG16, VGG19, and Xception) were employed to classify the intraoral photographs. Performance metrics (F1 scores, accuracy, precision, and recall) were calculated and confusion matrices were formed. : The highest accuracy rates were 98.33% for IMPA groups, 99.00% for interincisal angle groups, 96.67% for U1-palatal plane angle groups, and 98.33% for Wits measurement groups. Lowest accuracy rates were 59% for IMPA groups, 53% for interincisal angle groups, 33.33% for U1-palatal plane angle groups, and 83.67% for Wits measurement groups. : Although accuracy rates varied among classifications and DL algorithms, successful classification could be achieved in the majority of cases. Our results may be promising for case classification and analysis without the need for lateral cephalometric radiographs.
临床口腔内照片对于正畸诊断、治疗计划制定及记录非常重要。本研究旨在评估利用实际头影测量值训练的深度学习算法对口腔内临床照片进行分类的效果。本研究对990例患者的头颅侧位片和口腔右侧图像进行。使用WebCeph测量下中切牙间角（IMPA）、切牙间角、上中切牙-腭平面角和Wits评估值。根据头影测量值将口腔内照片分为三组。共采用14种深度学习模型（DenseNet 121、DenseNet 169、DenseNet 201、EfficientNet B0、EfficientNet V2、Inception V3、MobileNet V2、NasNetMobile、ResNet101、ResNet152、ResNet50、VGG16、VGG19和Xception）对口腔内照片进行分类。计算性能指标（F1分数、准确率、精确率和召回率）并形成混淆矩阵。IMPA组的最高准确率为98.33%，切牙间角组为99.00%，上中切牙-腭平面角组为96.67%，Wits测量组为98.33%。IMPA组的最低准确率为59%，切牙间角组为53%，上中切牙-腭平面角组为33.33%，Wits测量组为83.67%。尽管不同分类和深度学习算法的准确率有所不同，但在大多数情况下仍可实现成功分类。我们的结果对于无需头颅侧位X线片的病例分类和分析可能很有前景。
