用于自动检测舌炎和OSCC的DCNN模型
Yeon-Hee Lee1,2, Seonggwang Jeon3, Junho Jung4
1Department of Orofacial Pain and Oral Medicine, Kyung Hee University Dental Hospital, Kyung Hee University, #26 Kyunghee-daero, Dongdaemun-gu, Seoul, 02447, South Korea. omod0209@gmail.com.
Scientific reports
|August 29, 2025
概括
深度卷积神经网络 (DCNN) 模型准确地从照片中分类舌头疾病,如光和口腔状细胞癌 (OSCC). 这些人工智能工具对早期检测和远程医疗具有前景,
科学领域:
- 医学成像和人工智能
- 计算病理学
- 数字健康与远程医疗
背景情况:
- 语言疾病的自动诊断对于早期发现和治疗至关重要.
- 深度卷积神经网络 (DCNNs) 提供了分析临床图像的潜力.
- 要了解医疗保健中的人工智能诊断决策,
研究的目的:
- 根据舌头照片开发和评估DCNN模型来分类口腔状细胞癌 (OSCC).
- 将Grad-CAM可视化纳入模型的可解释性.
- 评估这些人工智能模型的早期检测和远程医疗应用的潜力.
主要方法:
- 在652个语言图像上使用转移学习微调四个预训练的DCNN架构 (VGG16,VGG19,ResNet50,ResNet152).
- 使用Grad-CAM和稀疏性分析进行模型解释.
- 使用AUROC评估诊断性能,根据年龄,性别和图像细分进行分组分析.
主要成果:
- 在分类光和OSCC方面,DCNN模型表现出强的性能.
- VGG16和VGG19的组合获得了最高的AUROC (0.8731).
- 在VGG19和ResNet152的OSCC检测中观察到近乎完美的性能 (AUROC=1.0000).
- 整体图像分类表现优于补丁分类,在不同年龄和性别组中表现一致.
结论:
- 使用Grad-CAM的DCNN模型提供可解释和准确的舌头状况分类.
- 这些人工智能驱动的诊断工具显示出远程口腔健康评估的巨大潜力.
- 这项研究支持在舌头诊断中使用人工智能,
相关概念视频
01:26Assessment of the Mouth
401
A thorough mouth assessment, including inspection and palpation of the lips, gums, tongue, tonsils, uvula, and pharynx, is crucial in detecting potential health issues. Diseases ranging from oral cancer to systemic conditions like diabetes could be identified early through careful oral examination. This article provides a detailed guide on conducting a comprehensive mouth assessment.
Mouth Inspection
The inspection begins with visually examining the mouth for symmetry, color, and size.
Mouth Inspection
The inspection begins with visually examining the mouth for symmetry, color, and size.
401
00:49The Tongue and Taste Buds
37.4K
The surface of the tongue is covered with various small bumps called papillae, which either distribute what has been ingested (filiform papillae) or contain the sensory taste (or gustatory) receptor cells (fungiform, circumvallate, and foliate papillae). Embedded within each taste-related papilla are the taste buds—clusters of 30 to 100 gustatory receptor cells.
37.4K