Abstract：
OBJECTIVE: 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.
CONCLUSIONS: 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.
METHODS: 4 Laryngoscope, 2024.
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.
CONCLUSIONS: 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.
METHODS: 4 Laryngoscope, 2024.
摘要：
目的：评估视觉变压器衍生的图像嵌入在口咽中区分正常组织和肿瘤组织的性能，并研究计算机视觉（CV）基础模型在医学成像中的潜力。
方法：使用内窥镜框架的计算研究，重点是自我监督的视觉转换模型（DINOv2）在组织分类中的应用。使用高清内窥镜图像提取图像块，然后使用DINOv2模型进行归一化和处理以获得嵌入。这些嵌入用作标准支持向量机(SVM)的输入,以将组织分类为肿瘤或正常。使用80-20个列车验证分割来验证模型的判别性能。
结果：来自38个内窥镜NBI视频，分析了327个图像块。验证队列中的分类结果显示出较高的准确性（92％）和准确性（89％），完美的召回（100％）和94％的F1得分。受试者工作特征(ROC)曲线产生0.96的曲线下面积(AUC)。
结论：使用基于大视觉模型的嵌入可以有效区分肿瘤组织和正常口咽组织。本研究支持采用CV基础模型如DINOv2在内镜下评估粘膜病变的可行性。可能提高耳鼻咽喉科的诊断精度。
方法：4喉镜，2024.
方法：使用内窥镜框架的计算研究，重点是自我监督的视觉转换模型（DINOv2）在组织分类中的应用。使用高清内窥镜图像提取图像块，然后使用DINOv2模型进行归一化和处理以获得嵌入。这些嵌入用作标准支持向量机(SVM)的输入,以将组织分类为肿瘤或正常。使用80-20个列车验证分割来验证模型的判别性能。
结果：来自38个内窥镜NBI视频，分析了327个图像块。验证队列中的分类结果显示出较高的准确性（92％）和准确性（89％），完美的召回（100％）和94％的F1得分。受试者工作特征(ROC)曲线产生0.96的曲线下面积(AUC)。
结论：使用基于大视觉模型的嵌入可以有效区分肿瘤组织和正常口咽组织。本研究支持采用CV基础模型如DINOv2在内镜下评估粘膜病变的可行性。可能提高耳鼻咽喉科的诊断精度。
方法：4喉镜，2024.
