Hu Jing, Cui Chuanliang, Yang Wenxian, Huang Lihong, Yu Rongshan, Liu Siyang, Kong Yan
Aginome-XMU Joint Lab, School of Informatics, Xiamen University, China.
Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Department of Renal cancer and Melanoma, Peking University Cancer Hospital & Institute, Beijing, China.
Transl Oncol. 2021 Jan;14(1):100921. doi: 10.1016/j.tranon.2020.100921. Epub 2020 Oct 28.
Recent studies showed that immune-checkpoint blockade (ICB) has significantly improved clinical outcomes of melanoma and lung cancer patients. However, only a small subset of patients can benefit from ICB. Deep learning has been successfully implemented in complementary clinical diagnosis. The aim of this study is to demonstrate the potential of deep learning to facilitate the prediction of anti-PD-1 response from H&E images directly.
In this study, 190 H&E slides of melanoma were segmented into 256 × 256 tiles which were used as the training set for the convolutional neural network (CNN). Additional 54 melanoma and 55 lung cancer H&E slides were collected as independent testing sets.
An AUC of 0.778(95% CI: 63.8%-90.5%) was achieved for 54 melanoma testing samples with 15(65.2%) responders and 23(74.2%) non-responders correctly classified. We also obtained an AUC of 0.645(95% CI: 49.4%-78.4%) for 55 lung cancer samples.
To our knowledge, this is the first study of using deep learning to determine patients' anti-PD-1 response from H&E slides directly. Our CNN model achieved the state-of-the-art performance and has the potential to screen ICB beneficial patients in routine clinical practice.
近期研究表明，免疫检查点阻断（ICB）显著改善了黑色素瘤和肺癌患者的临床结局。然而，只有一小部分患者能从ICB中获益。深度学习已成功应用于辅助临床诊断。本研究的目的是证明深度学习直接从苏木精-伊红（H&E）图像预测抗程序性死亡蛋白1（PD-1）反应的潜力。
在本研究中，190张黑色素瘤的H&E切片被分割成256×256像素的图像块，用作卷积神经网络（CNN）的训练集。另外收集了54张黑色素瘤和55张肺癌的H&E切片作为独立测试集。
对于54个黑色素瘤测试样本，曲线下面积（AUC）为0.778（95%置信区间：63.8%-90.5%），15名（65.2%）反应者和23名（74.2%）无反应者被正确分类。对于55个肺癌样本，我们还获得了AUC为0.645（95%置信区间：49.4%-78.4%）。
据我们所知，这是第一项直接利用深度学习从H&E切片确定患者抗PD-1反应的研究。我们的CNN模型达到了当前的最佳性能，有潜力在常规临床实践中筛选出对ICB有益的患者。
