内镜中的计算机视觉基础模型:口咽癌概念验证
本研究为计算研究,利用38段内镜窄带成像视频提取327个图像块,经自监督视觉Transformer模型DINOv2提取嵌入,再用支持向量机分类肿瘤与正常组织;验证集准确率92%、精确率89%、召回率100%、F1分数94%、AUC 0.96,作者认为该基础模型在内镜评估黏膜病变中具有可行性。
要点
- 从38段内镜NBI视频中提取327个图像块进行分析。
- 验证集分类准确率92%、精确率89%、召回率100%、F1分数94%。
- ROC曲线下面积AUC为0.96。
核心结论
- 使用大型视觉模型衍生的嵌入能有效区分肿瘤性与正常口咽组织。
- 本研究支持DINOv2等计算机视觉基础模型用于内镜黏膜病变评估的可行性,可能提升耳鼻咽喉科诊断精确性。
研究设计与样本
- 计算研究,使用内镜帧图像,聚焦于自监督视觉Transformer模型DINOv2用于组织分类。
- 使用高清内镜图像提取图像块,经归一化后用DINOv2模型处理获得嵌入,嵌入作为标准支持向量机(SVM)输入将组织分类为肿瘤性或正常。
- 模型判别性能通过80-20训练-验证拆分进行验证。
- 分析来自38段内镜NBI视频的327个图像块。
- 证据等级为4级。
主要发现
- 验证队列分类结果示高准确率(92%)和精确率(89%),召回率为100%,F1分数为94%。
- 受试者工作特征(ROC)曲线得出曲线下面积(AUC)为0.96。
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
OBJECTIVES: To evaluate the performance of vision transformer-derived image embeddings for distinguishing between normal and neoplastic tissues in the oropharynx and to investigate the potential of computer vision (CV) foundation models in medical imaging. METHODS: Computational study using endoscopic frames with a focus on the application of a self-supervised vision transformer model (DINOv2) for tissue classification. High-definition endoscopic images were used to extract image patches that were then normalized and processed using the DINOv2 model to obtain embeddings. These embeddings served as input for a standard support vector machine (SVM) to classify the tissues as neoplastic or normal. The model's discriminative performance was validated using an 80-20 train-validation split. RESULTS: From 38 endoscopic NBI videos, 327 image patches were analyzed. The classification results in the validation cohort demonstrated high accuracy (92%) and precision (89%), with a perfect recall (100%) and an F1-score of 94%. The receiver operating characteristic (ROC) curve yielded an area under the curve (AUC) of 0.96. CONCLUSION: The use of large vision model-derived embeddings effectively differentiated between neoplastic and normal oropharyngeal tissues. This study supports the feasibility of employing CV foundation models like DINOv2 in the endoscopic evaluation of mucosal lesions, potentially augmenting diagnostic precision in Otorhinolaryngology. LEVEL OF EVIDENCE: 4 Laryngoscope, 134:4535-4541, 2024.
引用
- Paderno A, Rau A, Bedi N, et al. Computer Vision Foundation Models in Endoscopy: Proof of Concept in Oropharyngeal Cancer. Laryngoscope. 2024. PMID: 38850247. doi:10.1002/lary.31534
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。