Oya Kaori, Kokomoto Kazuma, Nozaki Kazunori, Toyosawa Satoru
Division of Clinical Laboratory, Osaka University Dental Hospital, 1-8 Yamadaoka, Suita, Osaka, Japan.
Division for Medical Informatics, Osaka University Dental Hospital, 1-8 Yamadaoka, Suita, Osaka, Japan.
J Dent Sci. 2023 Jan;18(1):322-329. doi: 10.1016/j.jds.2022.08.017. Epub 2022 Sep 8.
BACKGROUND/PURPOSE: Diagnostic methods of oral squamous cell carcinoma (SCC) using artificial intelligence (AI) and digital-histopathologic images have been developed. However, previous AI training methods have focused on the cellular atypia given by the training of high-magnification images, and little attention has been paid to structural atypia provided by low-power wide fields. Since oral SCC has histopathologic types with bland cytology, both cellular atypia and structural atypia must be considered as histopathologic features. This study aimed to investigate AI ability to judge oral SCC in a novel training method considering cellular and structural atypia and their suitability.
We examined digitized histological whole-slide images from 90 randomly selected patients with tongue SCC who attended a dental hospital. Image patches of 1000 × 1000 pixels were cut from whole-slide images at 0.3125-, 1.25-, 5-, and 20-fold magnification, and 90,059 image patches were used for training and evaluation. These image patches were resized into 224 × 224, 384 × 384, 512 × 512, and 768 × 768 pixels, and the differences in input size were analyzed. EfficientNet B0 was utilized as the convolutional neural network model. Gradient-weighted class activation mapping (Grad-CAM) was used to elucidate its validity.
The proposed method achieved a peak accuracy of 99.65% with an input size of 512 × 512 pixels. Grad-CAM suggested that AI focused on both cellular and structural atypia of SCC, and tended to focus on the region surrounding the basal layer.
Training AI regarding both cellular and structural atypia using various magnification images simultaneously may be suitable for the diagnosis of oral SCC.
背景/目的：利用人工智能（AI）和数字组织病理学图像的口腔鳞状细胞癌（SCC）诊断方法已得到发展。然而，以往的AI训练方法主要关注高倍图像训练所呈现的细胞异型性，而对低倍宽视野提供的结构异型性关注较少。由于口腔SCC存在细胞形态学表现平淡的组织病理学类型，细胞异型性和结构异型性都必须被视为组织病理学特征。本研究旨在探讨一种考虑细胞和结构异型性及其适用性的新型训练方法中AI判断口腔SCC的能力。
我们检查了从一家牙科医院随机选取的90例舌SCC患者的数字化组织学全切片图像。从全切片图像中以0.3125倍、1.25倍、5倍和20倍放大倍数裁剪出1000×1000像素的图像块，共90059个图像块用于训练和评估。这些图像块被调整为224×224、384×384、512×512和768×768像素，并分析输入大小的差异。采用高效网络B0作为卷积神经网络模型。利用梯度加权类激活映射（Grad-CAM）来阐明其有效性。
所提出的方法在输入大小为512×512像素时达到了99.65%的峰值准确率。Grad-CAM表明AI既关注SCC的细胞异型性又关注结构异型性，并且倾向于聚焦基底层周围区域。
同时使用各种放大倍数图像对AI进行细胞和结构异型性的训练可能适用于口腔SCC的诊断。
