基于白光与窄带成像内镜图像的深度学习模型对声带白斑进行分类
研究构建了声带白斑的白光与窄带成像(NBI)图像数据集,分为正常组织、炎性角化、轻度异型增生、中度异型增生、重度异型增生和鳞状细胞癌六类,用六种经典深度学习模型进行分类评价。GoogLeNet、DenseNet-121 和 ResNet-152 分类表现优异,白光图像最高总体准确率为 0.9583,NBI 图像最高总体准确率为 0.9478。结论认为这三种网络可提供准确的病理分类,有助于早期诊断及判断保守或手术治疗。
要点
- GoogLeNet、DenseNet-121 和 ResNet-152 对声带白斑分类表现优异。
- 白光图像分类最高总体准确率为 0.9583。
- NBI 图像分类最高总体准确率为 0.9478。
核心结论
- GoogLeNet、ResNet 和 DenseNet 可对声带白斑提供准确的病理分类,有助于早期诊断、为不同分度的保守治疗或手术治疗提供判断依据,并减轻内镜医师负担。
研究设计与样本
- 研究创建了声带白斑的白光与窄带成像(NBI)图像数据集,分为正常组织、炎性角化、轻度异型增生、中度异型增生、重度异型增生和鳞状细胞癌六类,并使用 AlexNet、VGG、Google Inception、ResNet、DenseNet 和 Vision Transformer 六种经典深度学习模型进行分类。
主要发现
- GoogLeNet(即 Google Inception V1)、DenseNet-121 和 ResNet-152 分类表现优异。
- 白光图像分类最高总体准确率为 0.9583。
- NBI 图像分类最高总体准确率为 0.9478。
- 这三种神经网络均提供非常高的灵敏度、特异度和精确率。
局限性
- 原文未报告局限性。
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
BACKGROUND: Accurate vocal cord leukoplakia classification is critical for the individualized treatment and early detection of laryngeal cancer. Numerous deep learning techniques have been proposed, but it is unclear how to select one to apply in the laryngeal tasks. This article introduces and reliably evaluates existing deep learning models for vocal cord leukoplakia classification. METHODS: We created white light and narrow band imaging (NBI) image datasets of vocal cord leukoplakia which were classified into six classes: normal tissues (NT), inflammatory keratosis (IK), mild dysplasia (MiD), moderate dysplasia (MoD), severe dysplasia (SD), and squamous cell carcinoma (SCC). Vocal cord leukoplakia classification was performed using six classical deep learning models, AlexNet, VGG, Google Inception, ResNet, DenseNet, and Vision Transformer. RESULTS: GoogLeNet (i.e., Google Inception V1), DenseNet-121, and ResNet-152 perform excellent classification. The highest overall accuracy of white light image classification is 0.9583, while the highest overall accuracy of NBI image classification is 0.9478. These three neural networks all provide very high sensitivity, specificity, and precision values. CONCLUSION: GoogLeNet, ResNet, and DenseNet can provide accurate pathological classification of vocal cord leukoplakia. It facilitates early diagnosis, providing judgment on conservative treatment or surgical treatment of different degrees, and reducing the burden on endoscopists.
引用
- You Z, Han B, Shi Z, et al. Vocal cord leukoplakia classification using deep learning models in white light and narrow band imaging endoscopy images. Head Neck. 2023. PMID: 37837264. doi:10.1002/hed.27543
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。