Wang Yanan, Wang Yu Guang, Hu Changyuan, Li Ming, Fan Yanan, Otter Nina, Sam Ikuan, Gou Hongquan, Hu Yiqun, Kwok Terry, Zalcberg John, Boussioutas Alex, Daly Roger J, Montúfar Guido, Liò Pietro, Xu Dakang, Webb Geoffrey I, Song Jiangning
Biomedicine Discovery Institute and Department of Biochemistry and Molecular Biology, Monash University, Melbourne, VIC, 3800, Australia.
Institute of Natural Sciences, School of Mathematical Sciences, Key Laboratory of Scientific and Engineering Computing of Ministry of Education (MOE-LSC), and Center for Mathematics of Artificial Intelligence Institute, Shanghai Jiao Tong University, Shanghai, 200240, China.
NPJ Precis Oncol. 2022 Jun 23;6(1):45. doi: 10.1038/s41698-022-00285-5.
Gastric cancer is one of the deadliest cancers worldwide. An accurate prognosis is essential for effective clinical assessment and treatment. Spatial patterns in the tumor microenvironment (TME) are conceptually indicative of the staging and progression of gastric cancer patients. Using spatial patterns of the TME by integrating and transforming the multiplexed immunohistochemistry (mIHC) images as Cell-Graphs, we propose a graph neural network-based approach, termed Cell-Graph Signature or CG, powered by artificial intelligence, for the digital staging of TME and precise prediction of patient survival in gastric cancer. In this study, patient survival prediction is formulated as either a binary (short-term and long-term) or ternary (short-term, medium-term, and long-term) classification task. Extensive benchmarking experiments demonstrate that the CG achieves outstanding model performance, with Area Under the Receiver Operating Characteristic curve of 0.960 ± 0.01, and 0.771 ± 0.024 to 0.904 ± 0.012 for the binary- and ternary-classification, respectively. Moreover, Kaplan-Meier survival analysis indicates that the "digital grade" cancer staging produced by CG provides a remarkable capability in discriminating both binary and ternary classes with statistical significance (P value < 0.0001), significantly outperforming the AJCC 8th edition Tumor Node Metastasis staging system. Using Cell-Graphs extracted from mIHC images, CG improves the assessment of the link between the TME spatial patterns and patient prognosis. Our study suggests the feasibility and benefits of such an artificial intelligence-powered digital staging system in diagnostic pathology and precision oncology.
胃癌是全球最致命的癌症之一。准确的预后对于有效的临床评估和治疗至关重要。肿瘤微环境（TME）中的空间模式在概念上可指示胃癌患者的分期和进展。通过将多重免疫组织化学（mIHC）图像整合和转换为细胞图来利用TME的空间模式，我们提出了一种基于图神经网络的方法，称为细胞图特征（Cell-Graph Signature，简称CG），由人工智能驱动，用于TME的数字分期和胃癌患者生存的精确预测。在本研究中，患者生存预测被制定为二元（短期和长期）或三元（短期、中期和长期）分类任务。广泛的基准实验表明，CG实现了出色的模型性能，二元分类的受试者操作特征曲线下面积为0.960±0.01，三元分类的为0.771±0.024至0.904±0.012。此外，Kaplan-Meier生存分析表明，CG产生的“数字分级”癌症分期在区分二元和三元类别方面具有显著能力，具有统计学意义（P值<0.0001），明显优于美国癌症联合委员会（AJCC）第8版肿瘤淋巴结转移分期系统。使用从mIHC图像中提取的细胞图，CG改善了对TME空间模式与患者预后之间联系的评估。我们的研究表明了这种由人工智能驱动的数字分期系统在诊断病理学和精准肿瘤学中的可行性和益处。
