Lung cancer is the first leading cause of cancer-related death in the United States, with lung adenocarcinoma as the major subtype accounting for 40% of all cases. To improve patient survival, image-based prognostic models were developed due to the ready availability of pathological images at diagnosis. However, the application of these models is hampered by two main challenges: the lack of publicly available image datasets with high-quality survival information and the poor interpretability of conventional convolutional neural network models. Here, we integrated matched transcriptomic and H&E staining data from TCGA (The Cancer Genome Atlas) to develop an image-based prognostic model, termed Deep-learning based Cell Graph (DeepCG) model. Instead of survival data, we used a gene signature to predict patient prognostic risks, which was then used as labels for training DeepCG. Importantly, by employing graph structures to capture cell patterns, DeepCG can provide cell-level interpretation, which was more biologically relevant than previous region-level insights. We validated the prognostic values of DeepCG in independent datasets and demonstrated its ability to identify prognostically informative cells in images.

中文翻译：

---

DeepCG：预测肺腺癌预后的细胞图模型

肺癌是美国癌症相关死亡的第一大原因，其中肺腺癌是主要亚型，占所有病例的 40%。为了提高患者的生存率，由于诊断时可以随时获得病理图像，因此开发了基于图像的预后模型。然而，这些模型的应用受到两个主要挑战的阻碍：缺乏具有高质量生存信息的公开图像数据集以及传统卷积神经网络模型的可解释性较差。在这里，我们整合了来自 TCGA（癌症基因组图谱）的匹配转录组和 H&E 染色数据，开发了一种基于图像的预后模型，称为基于深度学习的细胞图 (DeepCG) 模型。我们使用基因特征来预测患者的预后风险，而不是生存数据，然后将其用作训练 DeepCG 的标签。重要的是，通过采用图结构来捕获细胞模式，DeepCG 可以提供细胞级别的解释，这比以前的区域级别的见解更具生物学相关性。我们在独立数据集中验证了 DeepCG 的预后价值，并证明了其识别图像中具有预后信息的细胞的能力。