Yuan Yizhe, Zhao Ziyin, Fang Xin, Zhang Qing, Zhong Wenqing, Xu Midie, Li Gongqi, Jiao Rushi, Yu Heng, Wang Ruoxi, Liu Shuyu, Zu Weitao, Xue Bingsen, Chen Yuze, Wang Chengxiang, Zhang Ya, Liang Minghui, Han Bing, Jin Cheng
Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.
Department of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China.
NPJ Precis Oncol. 2025 Jul 25;9(1):261. doi: 10.1038/s41698-025-01042-0.
A whole pathology section contains approximately 1,000,000 cells of various types, this large-scale heterogeneity of cells and non-cellular constituents constructs a mutually competitive community. Conventional pixel-based visual processing techniques are insufficient to accurately capture the complexities inherent with cell-entity deployment and formation strategy. Here, we conquered segmentation and classification of all cells on the whole pathology sections from 387 hepatocellular carcinoma (HCC) patients across six cohorts with 57 pathologists assisted. Further, an AI system called Hybrid Graph Neural Network-Transformer system (HGTs) was proposed. It precisely predicted local recurrence of postoperative HCC by analyzing cell interactions across multiple scales, from cell-to-cell, cell-community, to tissue-level interactions. The proposed HGTs outperformed existing SOTA methods, with the C-index improving by 23.1% to reach 0.823, by further integrating multimodal data, including clinical information and immunohistochemical markers. A set of spatial relational biomarkers influencing tumor prognosis was discovered and quantitatively validated. They include the frequency of tumor-lymphocyte and tumor-tumor interactions, the distribution and sparsity of key cellular communities, and the degree of fibrosis in adjacent peritumoral tissues. Utilizing the anti-tumor potential of this marker set, we're developing therapies to enhance the immune system's fight against cancer. All cell semantic segmentation datasets and code are publicly available: https://github.com/Yuan1z0825/HGTs .
一个完整的病理切片包含大约100万个不同类型的细胞，细胞和非细胞成分的这种大规模异质性构建了一个相互竞争的群落。传统的基于像素的视觉处理技术不足以准确捕捉细胞实体部署和形成策略所固有的复杂性。在这里，我们在57名病理学家的协助下，完成了来自六个队列的387例肝细胞癌（HCC）患者的全病理切片上所有细胞的分割和分类。此外，还提出了一种名为混合图神经网络-Transformer系统（HGTs）的人工智能系统。它通过分析从细胞到细胞、细胞群落再到组织水平的多尺度细胞相互作用，精确预测术后HCC的局部复发。通过进一步整合包括临床信息和免疫组化标记在内的多模态数据，所提出的HGTs优于现有的最优方法，C指数提高了23.1%，达到0.823。发现并定量验证了一组影响肿瘤预后的空间关系生物标志物。它们包括肿瘤-淋巴细胞和肿瘤-肿瘤相互作用的频率、关键细胞群落的分布和稀疏性，以及肿瘤周围相邻组织的纤维化程度。利用这组标志物的抗肿瘤潜力，我们正在开发增强免疫系统抗癌能力的疗法。所有细胞语义分割数据集和代码均可公开获取：https://github.com/Yuan1z0825/HGTs 。
