基于ViT-B深度学习模型的口腔良恶性病变图像分类研究  

Research on Classification of Benign and Malignant Oral Lesions Using ViT-B Deep Learning Model

作　　者：崔宇琛 谢元栋 吴聿淼 牛凌霄 常路广达 朱宪春[1] CUI Yuchen;XIE Yuandong;WU Yumiao;NIU Lingxiao;CHANG Luguangda;ZHU Xianchun(Department of Orthodontics,Hospital of Stomatology,Jilin University,Changchun 130021,China;Jilin Provincial Key Laboratory of Tooth Development and Bone Remodeling,Changchun 130021,China;Department of Oral and Maxillofacial Surgery,School and Hospital of Stomatology,Jilin University,Changchun 130021,China)

机构地区：[1]吉林大学口腔医院正畸科,吉林长春130021 [2]吉林大学牙发育与颌骨重塑吉林省重点实验室,吉林长春130021 [3]吉林大学口腔医院颌面外科,吉林长春130021

出　　处：《口腔医学研究》2025年第1期16-20,共5页Journal of Oral Science Research

基　　金：吉林省科技厅自然科学基金项目(编号:YDZJ202201ZYTS057)。

摘　　要：目的:基于深度学习算法,对ViT-B模型检测口腔良性和恶性病变图像的性能进行分析,旨在为临床医生早期发现和准确诊断口腔癌提供有效工具。方法:使用包含口腔良性和恶性病变图像的公共数据集,对数据进行预处理和数据增强,按7∶2∶1的比例将数据随机划分为训练集、验证集和测试集。选取ViT-B、VGG16、ResNet101、DenseNet121和EfficientNetV25种深度学习模型,对模型进行训练和性能比较。通过外部数据对ViT-B模型的泛化能力进行评估,并基于注意力权重的可视化方法对ViT-B模型进行分析。结果:ViT-B在5种模型中分类性能最佳,受试者工作特征曲线下面积为0.9715,准确率为91.00%。该模型可以有效区分口腔良性和恶性病变图像,具有较强的泛化能力和临床实用性。结论:ViT-B模型在口腔良性和恶性病变图像识别中表现良好,可以为口腔癌的早期发现和准确诊断提供支持。Objective:To analyze the performance of ViT-B model in detecting oral benign and malignant lesions based on deep learning algorithms.Methods:A public dataset containing images of oral benign and malignant lesions was used,with preprocessing and data augmentation applied.The data was randomly divided into training,validation,and test sets in a 7∶2∶1 ratio.Five deep learning models,including ViT-B,VGG16,ResNet101,DenseNet121,and EfficientNetV2,were selected for training and evaluation.The generalization ability of the ViT-B model was evaluated using external data,and the model was analyzed based on the visualization of attention weights.Results:The ViT-B model demonstrated the best performance among five models,with an area under the receiver operating characteristic curve(AUC)of 0.9715 and an accuracy of 91.00%.The model effectively distinguished between images of oral benign and malignant lesions,demonstrating strong generalization ability and clinical applicability.Conclusion:The ViT-B model performs well in the recognition of oral benign and malignant lesions,supporting the early detection and accurate diagnosis of oral cancer.

关 键 词：口腔癌 口腔病变 深度学习 ViT-B 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程] R739.8[医药卫生—肿瘤]