He Jingyang, Xu Jingli, Chen Wujie, Cao Mengxuan, Zhang Jiaqing, Yang Qing, Li Enze, Zhang Ruolan, Tong Yahang, Zhang Yanqiang, Gao Chen, Zhao Qianyu, Xu Zhiyuan, Wang Lijing, Cheng Xiangdong, Zheng Guoliang, Pan Siwei, Hu Can
Department of Gastric Surgery, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang, China.
Zhejiang Chinese Medical University, Hangzhou, Zhejiang, China.
NPJ Precis Oncol. 2025 Jul 23;9(1):249. doi: 10.1038/s41698-025-01055-9.
Early detection and precise preoperative staging of early gastric cancer (EGC) are critical. Therefore, this study aims to develop a deep learning model using portal venous phase CT images to accurately distinguish EGC without lymph node metastasis. This study included 3164 patients with gastric cancer (GC) who underwent radical surgery at two medical centers in China from 2006 to 2019. Moreover, 2.5D radiomic data and multi-instance learning (MIL) were novel approaches applied in this study. By basing the selection of features on 2.5D radiomic data and MIL, the ResNet101 model combined with the XGBoost model represented a satisfactory performance for diagnosing pT1N0 GC. Furthermore, the 2.5D MIL-based model demonstrated a markedly superior predictive performance compared to traditional radiomics models and clinical models. We first constructed a deep learning prediction model based on 2.5D radiomics and MIL for effectively diagnosing pT1N0 GC patients, which provides valuable information for the individualized treatment selection.
早期胃癌（EGC）的早期检测和精确术前分期至关重要。因此，本研究旨在开发一种深度学习模型，利用门静脉期CT图像准确区分无淋巴结转移的EGC。本研究纳入了2006年至2019年在中国两家医疗中心接受根治性手术的3164例胃癌（GC）患者。此外，2.5D放射组学数据和多实例学习（MIL）是本研究中应用的新方法。通过基于2.5D放射组学数据和MIL进行特征选择，ResNet101模型与XGBoost模型相结合在诊断pT1N0 GC方面表现出令人满意的性能。此外，基于2.5D MIL的模型与传统放射组学模型和临床模型相比，具有明显更优的预测性能。我们首先构建了基于2.5D放射组学和MIL的深度学习预测模型，以有效诊断pT1N0 GC患者，为个体化治疗选择提供有价值的信息。
