Li Mao, Shen Ze-Liang, Xian Hong-Chun, Zheng Zhi-Jian, Yu Zhen-Wei, Liang Xin-Hua, Gao Rui, Tang Ya-Ling, Zhang Zhong
State Key Laboratory of Oral Diseases and National Clinical Research Center for Oral Diseases, Department of Pathology, West China Hospital of Stomatology, Sichuan University, Chengdu, China.
State Key Laboratory of Oral Diseases and National Clinical Research Center for Oral Diseases, Department of Oral and Maxillofacial Surgery, West China Hospital of Stomatology, Sichuan University, Chengdu, China.
Am J Pathol. 2025 Feb;195(2):221-231. doi: 10.1016/j.ajpath.2024.09.010. Epub 2024 Oct 26.
Salivary gland neoplasms (SGNs) represent a group of human neoplasms characterized by a remarkable cytomorphologic diversity, which frequently poses diagnostic challenges. Accurate histologic categorization of salivary gland tumors is crucial to make precise diagnoses and guide decisions regarding patient management. Within the scope of this study, a computer-aided diagnosis model using Vision Transformer (ViT), a cutting-edge deep learning model in computer vision, was developed to accurately classify the most prevalent subtypes of SGNs. These subtypes include pleomorphic adenoma, myoepithelioma, Warthin tumor, basal cell adenoma, oncocytic adenoma, cystadenoma, mucoepidermoid carcinoma, and salivary adenoid cystic carcinoma. The data set comprised 3046 whole slide images of histologically confirmed salivary gland tumors, encompassing nine distinct tissue categories. SGN-ViT exhibited impressive performance in classifying the eight salivary gland tumors, achieving an accuracy of 0.9966, an area under the receiver operating characteristic curve value of 0.9899, precision of 0.9848, recall of 0.9848, and an F1 score of 0.9848. Diagnostic performance of SGN-ViT surpassed that of benchmark models. In a subset of 100 whole slide images, SGN-ViT demonstrated comparable diagnostic performance to that of the chief pathologist while significantly reducing the diagnosis time. These observations indicate that SGN-ViT holds the potential to serve as a valuable computer-aided diagnostic tool for salivary gland tumors, enhancing the diagnostic accuracy of junior pathologists.
涎腺肿瘤（SGNs）是一组人类肿瘤，其特征是具有显著的细胞形态学多样性，这常常带来诊断挑战。涎腺肿瘤的准确组织学分类对于做出精确诊断和指导患者管理决策至关重要。在本研究范围内，开发了一种使用视觉Transformer（ViT）的计算机辅助诊断模型，ViT是计算机视觉领域的一种前沿深度学习模型，用于准确分类SGNs最常见的亚型。这些亚型包括多形性腺瘤、肌上皮瘤、沃辛瘤、基底细胞腺瘤、嗜酸性腺瘤、囊腺瘤、黏液表皮样癌和涎腺腺样囊性癌。数据集包含3046张经组织学证实的涎腺肿瘤全切片图像，涵盖九个不同的组织类别。SGN-ViT在对八种涎腺肿瘤进行分类时表现出令人印象深刻的性能，准确率达到0.9966，受试者操作特征曲线下面积值为0.9899，精确率为0.9848，召回率为0.9848，F1分数为0.9848。SGN-ViT的诊断性能超过了基准模型。在100张全切片图像的子集中，SGN-ViT表现出与首席病理学家相当的诊断性能，同时显著缩短了诊断时间。这些观察结果表明，SGN-ViT有潜力成为一种有价值的涎腺肿瘤计算机辅助诊断工具，提高初级病理学家的诊断准确性。
