Shimada Yoshifumi, Okuda Shujiro, Watanabe Yu, Tajima Yosuke, Nagahashi Masayuki, Ichikawa Hiroshi, Nakano Masato, Sakata Jun, Takii Yasumasa, Kawasaki Takashi, Homma Kei-Ichi, Kamori Tomohiro, Oki Eiji, Ling Yiwei, Takeuchi Shiho, Wakai Toshifumi
Division of Digestive and General Surgery, Niigata University Graduate School of Medical and Dental Sciences, 1-757 Asahimachi-dori, Chuo-ku, Niigata, Niigata, 951-8510, Japan.
Medical Genome Center, Niigata University Medical and Dental Hospital, Niigata, Japan.
J Gastroenterol. 2021 Jun;56(6):547-559. doi: 10.1007/s00535-021-01789-w. Epub 2021 Apr 28.
Tumor mutational burden-high (TMB-H), which is detected with gene panel testing, is a promising biomarker for immune checkpoint inhibitors (ICIs) in colorectal cancer (CRC). However, in clinical practice, not every patient is tested for TMB-H using gene panel testing. We aimed to identify the histopathological characteristics of TMB-H CRC for efficient selection of patients who should undergo gene panel testing. Moreover, we attempted to develop a convolutional neural network (CNN)-based algorithm to predict TMB-H CRC directly from hematoxylin and eosin (H&E) slides.
We used two CRC cohorts tested for TMB-H, and whole-slide H&E digital images were obtained from the cohorts. The Japanese CRC (JP-CRC) cohort (N = 201) was evaluated to detect the histopathological characteristics of TMB-H using H&E slides. The JP-CRC cohort and The Cancer Genome Atlas (TCGA) CRC cohort (N = 77) were used to develop a CNN-based TMB-H prediction model from the H&E digital images.
Tumor-infiltrating lymphocytes (TILs) were significantly associated with TMB-H CRC (P < 0.001). The area under the curve (AUC) for predicting TMB-H CRC was 0.910. We developed a CNN-based TMB-H prediction model. Validation tests were conducted 10 times using randomly selected slides, and the average AUC for predicting TMB-H slides was 0.934.
TILs, a histopathological characteristic detected with H&E slides, are associated with TMB-H CRC. Our CNN-based model has the potential to predict TMB-H CRC directly from H&E slides, thereby reducing the burden on pathologists. These approaches will provide clinicians with important information about the applications of ICIs at low cost.
通过基因检测面板检测到的肿瘤突变负荷高（TMB-H）是结直肠癌（CRC）中免疫检查点抑制剂（ICI）的一个有前景的生物标志物。然而，在临床实践中，并非每个患者都进行基因检测面板的TMB-H检测。我们旨在确定TMB-H CRC的组织病理学特征，以便有效选择应接受基因检测面板检测的患者。此外，我们试图开发一种基于卷积神经网络（CNN）的算法，直接从苏木精和伊红（H&E）染色切片预测TMB-H CRC。
我们使用了两个检测TMB-H的CRC队列，并从这些队列中获得了全切片H&E数字图像。对日本CRC（JP-CRC）队列（N = 201）进行评估，以使用H&E切片检测TMB-H的组织病理学特征。JP-CRC队列和癌症基因组图谱（TCGA）CRC队列（N = 77）用于从H&E数字图像开发基于CNN的TMB-H预测模型。
肿瘤浸润淋巴细胞（TILs）与TMB-H CRC显著相关（P < 0.001）。预测TMB-H CRC的曲线下面积（AUC）为0.910。我们开发了一种基于CNN的TMB-H预测模型。使用随机选择的切片进行了10次验证测试，预测TMB-H切片的平均AUC为0.934。
TILs是通过H&E切片检测到的一种组织病理学特征，与TMB-H CRC相关。我们基于CNN的模型有潜力直接从H&E切片预测TMB-H CRC，从而减轻病理学家的负担。这些方法将以低成本为临床医生提供有关ICI应用的重要信息。
