School of Electrical Engineering, Korea University, Seoul, Republic of Korea.
Department of Pathology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea.
JAMA Netw Open. 2022 Oct 3;5(10):e2236408. doi: 10.1001/jamanetworkopen.2022.36408.
Epstein-Barr virus (EBV)-associated gastric cancer (EBV-GC) is 1 of 4 molecular subtypes of GC and is confirmed by an expensive molecular test, EBV-encoded small RNA in situ hybridization. EBV-GC has 2 histologic characteristics, lymphoid stroma and lace-like tumor pattern, but projecting EBV-GC at biopsy is difficult even for experienced pathologists.
To develop and validate a deep learning algorithm to predict EBV status from pathology images of GC biopsy.
DESIGN, SETTING, AND PARTICIPANTS: This diagnostic study developed a deep learning classifier to predict EBV-GC using image patches of tissue microarray (TMA) and whole slide images (WSIs) of GC and applied it to GC biopsy specimens from GCs diagnosed at Kangbuk Samsung Hospital between 2011 and 2020. For a quantitative evaluation and EBV-GC prediction on biopsy specimens, the area of each class and the fraction in total tissue or tumor area were calculated. Data were analyzed from March 5, 2021, to February 10, 2022.
Evaluation metrics of predictive model performance were assessed on accuracy, recall, precision, F1 score, area under the receiver operating characteristic curve (AUC), and κ coefficient.
This study included 137 184 image patches from 16 TMAs (708 tissue cores), 24 WSIs, and 286 biopsy images of GC. The classifier was able to classify EBV-GC image patches from TMAs and WSIs with 94.70% accuracy, 0.936 recall, 0.938 precision, 0.937 F1 score, and 0.909 κ coefficient. The classifier was used for predicting and measuring the area and fraction of EBV-GC on biopsy tissue specimens. A 10% cutoff value for the predicted fraction of EBV-GC to tissue (EBV-GC/tissue area) produced the best prediction results in EBV-GC biopsy specimens and showed the highest AUC value (0.8723; 95% CI, 0.7560-0.9501). That cutoff also obtained high sensitivity (0.895) and moderate specificity (0.745) compared with experienced pathologist sensitivity (0.842) and specificity (0.854) when using the presence of lymphoid stroma and a lace-like pattern as diagnostic criteria. On prediction maps, EBV-GCs with lace-like pattern and lymphoid stroma showed the same prediction results as EBV-GC, but cases lacking these histologic features revealed heterogeneous prediction results of EBV-GC and non-EBV-GC areas.
This study showed the feasibility of EBV-GC prediction using a deep learning algorithm, even in biopsy samples. Use of such an image-based classifier before a confirmatory molecular test will reduce costs and tissue waste.
Epstein-Barr 病毒（EBV）相关胃癌（EBV-GC）是 GC 的 4 种分子亚型之一，通过昂贵的分子检测 EBV 编码的小 RNA 原位杂交来证实。EBV-GC 有 2 种组织学特征，淋巴间质和花边样肿瘤模式，但即使是经验丰富的病理学家，在活检中也很难发现突出的 EBV-GC。
开发和验证一种深度学习算法，以从 GC 活检的病理图像预测 EBV 状态。
设计、设置和参与者：这项诊断研究使用 GC 的组织微阵列（TMA）和全玻片图像（WSI）的图像补丁开发了一种深度学习分类器来预测 EBV-GC，并将其应用于 2011 年至 2020 年期间在 Kangbuk Samsung 医院诊断为 GC 的 GC 活检标本。为了对活检标本进行定量评估和 EBV-GC 预测，计算了每个类别的面积和总组织或肿瘤面积中的分数。数据分析于 2021 年 3 月 5 日至 2022 年 2 月 10 日进行。
评估了预测模型性能的评估指标，包括准确性、召回率、精度、F1 分数、受试者工作特征曲线下的面积（AUC）和κ系数。
本研究包括 16 个 TMA（708 个组织芯）、24 个 WSI 和 286 个 GC 活检图像的 137184 个图像补丁。分类器能够以 94.70%的准确率、0.936 的召回率、0.938 的精度、0.937 的 F1 分数和 0.909 的κ系数对 TMA 和 WSI 的 EBV-GC 图像补丁进行分类。该分类器用于预测和测量活检组织标本中 EBV-GC 的面积和分数。当预测 EBV-GC 与组织的分数（EBV-GC/组织面积）的截断值为 10%时，在 EBV-GC 活检标本中获得了最佳预测结果，AUC 值最高（0.8723；95%CI，0.7560-0.9501）。与经验丰富的病理学家的敏感性（0.842）和特异性（0.854）相比，该截断值在使用淋巴间质和花边样模式作为诊断标准时，也具有较高的敏感性（0.895）和适度的特异性（0.745）。在预测图上，具有花边样模式和淋巴间质的 EBV-GC 显示出与 EBV-GC 相同的预测结果，但缺乏这些组织学特征的病例显示出 EBV-GC 和非 EBV-GC 区域的异质预测结果。
本研究表明，即使在活检样本中，也可以使用深度学习算法预测 EBV-GC。在进行确认性分子检测之前使用这种基于图像的分类器将降低成本和组织浪费。
