Chuang Wen-Yu, Chang Shang-Hung, Yu Wei-Hsiang, Yang Cheng-Kun, Yeh Chi-Ju, Ueng Shir-Hwa, Liu Yu-Jen, Chen Tai-Di, Chen Kuang-Hua, Hsieh Yi-Yin, Hsia Yi, Wang Tong-Hong, Hsueh Chuen, Kuo Chang-Fu, Yeh Chao-Yuan
Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan.
Center for Vascularized Composite Allotransplantation, Chang Gung Memorial Hospital, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan.
Cancers (Basel). 2020 Feb 22;12(2):507. doi: 10.3390/cancers12020507.
Pathologic diagnosis of nasopharyngeal carcinoma (NPC) can be challenging since most cases are nonkeratinizing carcinoma with little differentiation and many admixed lymphocytes. Our aim was to evaluate the possibility to identify NPC in nasopharyngeal biopsies using deep learning. A total of 726 nasopharyngeal biopsies were included. Among them, 100 cases were randomly selected as the testing set, 20 cases as the validation set, and all other 606 cases as the training set. All three datasets had equal numbers of NPC cases and benign cases. Manual annotation was performed. Cropped square image patches of 256 × 256 pixels were used for patch-level training, validation, and testing. The final patch-level algorithm effectively identified NPC patches, with an area under the receiver operator characteristic curve (AUC) of 0.9900. Using gradient-weighted class activation mapping, we demonstrated that the identification of NPC patches was based on morphologic features of tumor cells. At the second stage, whole-slide images were sequentially cropped into patches, inferred with the patch-level algorithm, and reconstructed into images with a smaller size for training, validation, and testing. Finally, the AUC was 0.9848 for slide-level identification of NPC. Our result shows for the first time that deep learning algorithms can identify NPC.
鼻咽癌（NPC）的病理诊断颇具挑战性，因为大多数病例为低分化的非角化性癌，且伴有大量淋巴细胞浸润。我们的目的是评估利用深度学习在鼻咽活检中识别鼻咽癌的可能性。共纳入726例鼻咽活检样本。其中，随机选取100例作为测试集，20例作为验证集，其余606例作为训练集。三个数据集的鼻咽癌病例数和良性病例数相等。进行了人工标注。使用256×256像素的裁剪后方形图像块进行图像块级别的训练、验证和测试。最终的图像块级算法能够有效识别鼻咽癌图像块，其受试者操作特征曲线（AUC）下面积为0.9900。利用梯度加权类激活映射，我们证明了鼻咽癌图像块的识别是基于肿瘤细胞的形态学特征。在第二阶段，将全切片图像依次裁剪成图像块，用图像块级算法进行推断，并重建为较小尺寸的图像用于训练、验证和测试。最后，在切片级别识别鼻咽癌的AUC为0.9848。我们的结果首次表明深度学习算法能够识别鼻咽癌。
