人工智能在胃癌诊疗和患者预后预测中的应用现状及未来展望

doi:10.19401/j.cnki.1007-3639.2025.05.008

摘要/Abstract

摘要：

胃癌是全球范围内高发的恶性肿瘤之一，具有起病隐匿、早期诊断困难、进展期预后不良等特点。传统诊断技术受主观因素影响较大，且在准确率和效率方面存在局限，难以满足精准医学的临床需求。近年来，人工智能（artificial intelligence，AI）技术，尤其是基于深度学习（deep learning，DL）的快速发展，为胃癌的精准诊疗带来了全新的机遇。AI辅助胃镜诊断可显著提升病变检出率及诊断效率，AI驱动的影像组学模型可精准预测肿瘤浸润深度、淋巴结及腹膜转移情况，而AI辅助病理学系统的应用则可以显著提高诊断的准确率和效率。此外，结合多组学数据的AI模型在化疗和靶向治疗反应预测以及个体化预后评估方面亦展现出巨大潜力。然而，AI技术在胃癌领域的临床转化仍面临诸多挑战，包括数据标准化不统一、模型泛化能力不足及算法可解释性较弱等问题。因此，本文系统综述AI技术在胃癌诊断、疗效评估及预后预测方面的最新研究进展，深入探讨当前技术所面临的核心挑战，并展望未来AI在胃癌精准诊疗中的发展趋势，以期推动AI技术的广泛应用和临床转化，最终实现胃癌诊疗的精准化和个体化，改善患者的临床预后。

关键词: 人工智能, 胃癌, 深度学习, 诊断, 预后

Abstract:

Gastric cancer remains one of the most prevalent and lethal malignancies worldwide, characterized by an insidious onset, challenges in early detection, and a poor prognosis in advanced stages. Conventional diagnostic approaches are often constrained by subjective interpretation and inherent limitations in accuracy and efficiency, rendering them insufficient to meet the demands of precision medicine. In recent years, the rapid advancement of artificial intelligence (AI), particularly deep learning (DL)-based techniques, has opened new avenues for the precise diagnosis and management of gastric cancer. Emerging evidence suggests that AI-assisted endoscopic systems significantly enhance lesion detection rates and diagnostic efficiency, while AI-driven radiomics models offer precise predictions of tumor invasion depth, lymph node involvement, and peritoneal metastasis. Additionally, AI-powered pathology analysis has markedly improved both diagnostic accuracy and efficiency. Moreover, integrative AI models leveraging multi-omics data have demonstrated great potential in predicting responses to chemotherapy and targeted therapies, as well as facilitating personalized prognostic assessments. However, despite these promising advancements, the clinical implementation of AI in gastric cancer remains hindered by challenges such as the lack of standardized datasets, limited model generalizability, and insufficient algorithm interpretability. This review systematically synthesized the latest advancements in AI applications for gastric cancer diagnosis, treatment response evaluation, and prognostic prediction. Furthermore, it critically examined key technical challenges in current AI methodologies and explored future directions in AI-driven precision medicine for gastric cancer. By addressing these challenges, we aimed to foster the widespread adoption and clinical translation of AI technologies, ultimately advancing precision oncology and improving patient outcomes.

Key words: Artificial intelligence, Gastric cancer, Deep learning, Diagnosis, Prognosis

中图分类号:

R735.2

彭东阁, 万子叶, 卢宁. 人工智能在胃癌诊疗和患者预后预测中的应用现状及未来展望[J]. 中国癌症杂志, 2025, 35(5): 496-504.

PENG Dongge, WAN Ziye, LU Ning. Artificial intelligence in gastric cancer diagnosis, treatment and prognostic prediction: current application and future perspective[J]. China Oncology, 2025, 35(5): 496-504.

图/表 3

图1

图2

表1

AI联合组学数据在胃癌中的研究进展"

Application	Research content	AI method	Results
Endoscopic diagnosis	Validation of AI model consistency with pathological diagnosis of gastric lesions^[16]	U-Net deep learning model	The AI model exhibited superior consistency with pathological diagnoses during real-time endoscopic video monitoring, surpassing endoscopists in diagnostic accuracy
	Effectiveness of AI-assisted real-time monitoring and diagnosis of endoscopic lesions ^[19]	CNN-based deep learning model	The AI-assisted system achieved an accuracy of 84.7%, sensitivity of 100%, and specificity of 84.3% in gastric cancer detection, enhancing the quality of endoscopic examinations
Imaging diagnosis	Prediction of preoperative lymph node metastasis in gastric cancer^[30]	DLRN based on CNN	DLRN effectively distinguished lymph node metastasis stages in advanced gastric cancer, outperforming clinical N staging methods and showing significant correlation with OS
	Prediction of occult peritoneal metastasis in advanced gastric cancer^[35]	GAN-based deep learning model (PMetNet)	The nomogram model, incorporating Lauren classification and tumor differentiation, significantly improved the diagnostic accuracy of preoperative occult peritoneal metastasis, with AUC values of 0.950 and 0.953, respectively
Pathological diagnosis	Development of an AI-assisted rapid pathological diagnosis system^[40]	CNN-based deep learning pathology diagnostic system	The system rapidly identified suspicious tumor regions, demonstrating robust diagnostic performance (AUC: 0.986; accuracy: 0.873; sensitivity: 0.996; specificity: 0.806)
	Identification of lymph nodes and tumor regions to assist in gastric cancer lymph node metastasis diagnosis^[42]	CNN-based deep reinforcement learning	The model achieved a sensitivity of 98.5% and specificity of 96.1%, significantly reducing the time required for pathologists to diagnose lymph node metastasis
Therapeutic response prediction	Prediction of targeted therapy efficacy in HER2-positive gastric cancer patients^[46]	Hybrid predictive model (MuMo) based on CNN and Transformer architecture	MuMo exhibited AUC values of 0.821 and 0.914 in predicting responses to targeted therapy in HER2-positive gastric cancer patients, effectively stratifying them into high-risk and low-risk groups
Prognostic assessment	Development of a RFS prediction model for advanced gastric cancer patients based on radiomic features^[54]	CNN-based deep learning model	The model optimized RFS prediction and high-risk stratification in gastric cancer patients

表1

参考文献 57

[1]	BRAY F, LAVERSANNE M, SUNG H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2024, 74(3): 229-263.
[2]	中华人民共和国国家卫生健康委员会医政医管局. 胃癌诊疗指南(2022年版)[J]. 中华消化外科杂志, 2022, 21(9): 1137-1164.
	Bureau of Medical Administration, National Health Commission of the People’s Republic of China. Standardization for diagnosis and treatment of gastric cancer (2022 edition)[J]. Chin J Dig Surg, 2022, 21(9): 1137-1164.
[3]	HUANG S G, YANG J, SHEN N, et al. Artificial intelligence in lung cancer diagnosis and prognosis: current application and future perspective[J]. Semin Cancer Biol, 2023, 89: 30-37. doi: 10.1016/j.semcancer.2023.01.006 pmid: 36682439
[4]	LADBURY C, AMINI A, GOVINDARAJAN A, et al. Integration of artificial intelligence in lung cancer: rise of the machine[J]. Cell Rep Med, 2023, 4(2): 100933.
[5]	PEI Q, LUO Y N, CHEN Y Y, et al. Artificial intelligence in clinical applications for lung cancer: diagnosis, treatment and prognosis[J]. Clin Chem Lab Med, 2022, 60(12): 1974-1983.
[6]	PEREZ-LOPEZ R, LALEH N G, MAHMOOD F, et al. A guide to artificial intelligence for cancer researchers[J]. Nat Rev Cancer, 2024, 24(6): 427-441.
[7]	中华医学会消化内镜学分会大数据协作组. 上消化道内镜人工智能系统临床应用专家共识(2023, 武汉)[J]. 中华消化内镜杂志, 2024, 41(2): 85-96.
	Big Data Collaboration Group, Digestive Endoscopology Branch of Chinese Medical Association. Expert consensus on clinical application of upper gastrointestinal endoscopic artificial intelligence system (2023, Wuhan)[J]. Chin J Dig Endosc, 2024, 41(2): 85-96.
[8]	AI TASK FORCE A S G E, PARASA S, BERZIN T, et al. Consensus statements on the current landscape of artificial intelligence applications in endoscopy, addressing roadblocks, and advancing artificial intelligence in gastroenterology[J]. Gastrointest Endosc, 2025, 101(1): 2-9. e1.
[9]	中国抗癌协会胃癌专业委员会, 中国医师协会外科医师分会上消化道外科医师委员会, 中国人群健康风险管理协作组-胃癌专业组. 中国人群胃癌风险管理公众指南(2023版)[J]. 中华医学杂志, 2023, 103(36): 2837-2849.
	Chinese Gastric Cancer Association of Chinese Anti-Cancer Association, Chinese Society of Upper Gastrointestinal Surgeons of Chinese Medical Doctor Association, Chinese Health Risk Management Collaboration-Gastric Cancer Group. Chinese guideline on risk management of gastric cancer in the general public (2023 edition)[J]. Natl Med J China, 2023, 103(36): 2837-2849.
[10]	王士旭, 柯岩, 楚江涛, 等. 基于数据增强和混合神经网络的人工智能技术在上消化道内镜检查部位识别中的应用[J]. 中华消化内镜杂志, 2023, 40(3): 189-195.
	WANG S X, KE Y, CHU J T, et al. Application of artificial intelligence based on data enhancement and hybrid neural network to site identification during esophagogastroduodenoscopy[J]. Chin J Dig Endosc, 2023, 40(3): 189-195.
[11]	DU H L, DONG Z H, WU L L, et al. A deep-learning based system using multi-modal data for diagnosing gastric neoplasms in real-time (with video)[J]. Gastric Cancer, 2023, 26(2): 275-285.
[12]	国家卫生健康委员会医疗应急司. 胃癌筛查与早诊早治方案(2024年版)[J]. 中华肿瘤杂志, 2024, 46(10): 915-916.
	Department of Medical Emergency Response, National Health Commission. Screening, early diagnosis and treatment of gastric cancer (2024 edition)[J]. Chin J Oncol, 2024, 46(10): 915-916.
[13]	ZHAO Q C, CHI T Y. Deep learning model can improve the diagnosis rate of endoscopic chronic atrophic gastritis: a prospective cohort study[J]. BMC Gastroenterol, 2022, 22(1): 133.
[14]	ZHAO Q C, JIA Q, CHI T Y. Deep learning as a novel method for endoscopic diagnosis of chronic atrophic gastritis: a prospective nested case-control study[J]. BMC Gastroenterol, 2022, 22(1): 352.
[15]	Infection with Helicobacter pylori[M]// IARC Working Group on the Evaluation of Carcinogenic Risks to Humans. IARC monographs on the evaluation of carcinogenic risks to humans volume 61:schistosomes, liver flukes and Helicobacter pylori. Lyon (FR): international agency for research on cancer, 1994: 177-240.
[16]	YANG R X, ZHANG J L, ZHAN F S, et al. Artificial intelligence efficiently predicts gastric lesions, Helicobacter pylori infection and lymph node metastasis upon endoscopic images[J]. Chin J Cancer Res, 2024, 36(5): 489-502.
[17]	NAKASHIMA H, KAWAHIRA H, KAWACHI H, et al. Endoscopic three-categorical diagnosis of Helicobacter pylori infection using linked color imaging and deep learning: a single-center prospective study (with video)[J]. Gastric Cancer, 2020, 23(6): 1033-1040.
[18]	HORIUCHI Y, AOYAMA K, TOKAI Y, et al. Convolutional neural network for differentiating gastric cancer from gastritis using magnified endoscopy with narrow band imaging[J]. Dig Dis Sci, 2020, 65(5): 1355-1363.
[19]	WU L L, WANG J, HE X Q, et al. Deep learning system compared with expert endoscopists in predicting early gastric cancer and its invasion depth and differentiation status (with videos)[J]. Gastrointest Endosc, 2022, 95(1): 92-104.e3.
[20]	GONG E J, BANG C S, LEE J J, et al. Deep learning-based clinical decision support system for gastric neoplasms in real-time endoscopy: development and validation study[J]. Endoscopy, 2023, 55(8): 701-708.
[21]	UEMA R, HAYASHI Y, KIZU T, et al. A novel artificial intelligence-based endoscopic ultrasonography diagnostic system for diagnosing the invasion depth of early gastric cancer[J]. J Gastroenterol, 2024, 59(7): 543-555. doi: 10.1007/s00535-024-02102-1 pmid: 38713263
[22]	BISSCHOPS R, AREIA M, CORON E, et al. Performance measures for upper gastrointestinal endoscopy: a European Society of Gastrointestinal Endoscopy (ESGE) quality improvement initiative[J]. Endoscopy, 2016, 48(9): 843-864. doi: 10.1055/s-0042-113128 pmid: 27548885
[23]	YU T, HU H Y, ZHANG X S, et al. Real-time multi-label upper gastrointestinal anatomy recognition from gastroscope videos[J]. Appl Sci, 2022, 12(7): 3306.
[24]	LOCH F N, BEYER K, KREIS M E, et al. Diagnostic performance of Node Reporting and Data System (Node-RADS) for regional lymph node staging of gastric cancer by CT[J]. Eur Radiol, 2024, 34(5): 3183-3193.
[25]	KIM D J, HYUNG W J, PARK Y K, et al. Accuracy of preoperative clinical staging for locally advanced gastric cancer in KLASS-02 randomized clinical trial[J]. Front Surg, 2022, 9: 1001245.
[26]	WANG Y, LIU W, YU Y, et al. Prediction of the depth of tumor invasion in gastric cancer: potential role of CT radiomics[J]. Acad Radiol, 2020, 27(8): 1077-1084. doi: S1076-6332(19)30534-3 pmid: 31761666
[27]	ZENG Q W, FENG Z F, ZHU Y Y, et al. Deep learning model for diagnosing early gastric cancer using preoperative computed tomography images[J]. Front Oncol, 2022, 12: 1065934.
[28]	STANDARDS OF PRACTICE COMMITTEE A S G E, FORBES N, ELHANAFI S E, et al. American Society for Gastrointestinal Endoscopy guideline on endoscopic submucosal dissection for the management of early esophageal and gastric cancers: summary and recommendations[J]. Gastrointest Endosc, 2023, 98(3): 271-284. doi: 10.1016/j.gie.2023.03.015 pmid: 37498266
[29]	JIN C, JIANG Y, YU H, et al. Deep learning analysis of the primary tumour and the prediction of lymph node metastases in gastric cancer[J]. Br J Surg, 2021, 108(5): 542-549.
[30]	DONG D, FANG M J, TANG L, et al. Deep learning radiomic nomogram can predict the number of lymph node metastasis in locally advanced gastric cancer: an international multicenter study[J]. Ann Oncol, 2020, 31(7): 912-920. doi: S0923-7534(20)39294-2 pmid: 32304748
[31]	GAO X J, MA T T, CUI J L, et al. A radiomics-based model for prediction of lymph node metastasis in gastric cancer[J]. Eur J Radiol, 2020, 129: 109069.
[32]	ZHENG Y L, QIU B J, LIU S L, et al. A transformer-based deep learning model for early prediction of lymph node metastasis in locally advanced gastric cancer after neoadjuvant chemotherapy using pretreatment CT images[J]. EClinicalMedicine, 2024, 75: 102805.
[33]	YANG R, SU Y D, MA R, et al. Clinical epidemiology of peritoneal metastases in China: the construction of professional peritoneal metastases treatment centers based on the prevalence rate[J]. Eur J Surg Oncol, 2023, 49(1): 173-178.
[34]	中国抗癌协会胃癌专业委员会. 胃癌腹膜转移诊治中国专家共识(2023版)[J]. 中华胃肠外科杂志, 2023(8): 717-728.
	Gastric Cancer Committee of China Anti Cancer Association. Chinese expert consensus on the diagnosis and treatment of peritoneal metastasis of gastric cancer (2023 edition)[J]. Chin J Gastrointest Surg, 2023(8): 717-728.
[35]	JIANG Y M, LIANG X K, WANG W, et al. Noninvasive prediction of occult peritoneal metastasis in gastric cancer using deep learning[J]. JAMA Netw Open, 2021, 4(1): e2032269.
[36]	JIANG Y M, ZHANG Z C, YUAN Q Y, et al. Predicting peritoneal recurrence and disease-free survival from CT images in gastric cancer with multitask deep learning: a retrospective study[J]. Lancet Digit Health, 2022, 4(5): e340-e350.
[37]	CHEN Y Y, CAI G X, JIANG J J, et al. Proteomic profiling of gastric cancer with peritoneal metastasis identifies a protein signature associated with immune microenvironment and patient outcome[J]. Gastric Cancer, 2023, 26(4): 504-516. doi: 10.1007/s10120-023-01379-0 pmid: 36930369
[38]	《人工智能辅助胃部组织病理学诊断的数据采集和标注专家共识》编写组. 人工智能辅助胃部组织病理学诊断的数据采集和标注专家共识[J]. 中华病理学杂志, 2024, 53(9): 893-897.
	Expert Committee of the Consensus on Data Acquisition and Annotation of Artificial Intelligence Assisted Gastric Histopathological Diagnosis. Expert consensus on data acquisition and annotation of artificial intelligence assisted gastric histopathological diagnosis[J]. Chin J Pathol, 2024, 53(9): 893-897.
[39]	WANG X Y, ZHAO J H, MAROSTICA E, et al. A pathology foundation model for cancer diagnosis and prognosis prediction[J]. Nature, 2024, 634(8035): 970-978.
[40]	SONG Z G, ZOU S M, ZHOU W X, et al. Clinically applicable histopathological diagnosis system for gastric cancer detection using deep learning[J]. Nat Commun, 2020, 11(1): 4294.
[41]	刘洋, 胡奕炀, 刘月平, 等. 人工智能辅助技术在胃癌新辅助化疗患者HER2表达评估中的价值[J]. 中国癌症杂志, 2023, 33(4): 377-387. doi: 10.19401/j.cnki.1007-3639.2023.04.008
	LIU Y, HU Y Y, LIU Y P, et al. The value of artificial intelligence-assisted technology in HER2 assessmentof gastric cancer patients receiving neoadjuvant chemotherapy[J]. China Oncol, 2023, 33(4): 377-387.
[42]	LUIK T T, ROSAS-BERTOLINI R, REITS E A J, et al. BIOMERO: a scalable and extensible image analysis framework[J]. Patterns (N Y), 2024, 5(8): 101024.
[43]	ZHAO X Y, SINGHAL A, PARK S, et al. Cancer mutations converge on a collection of protein assemblies to predict resistance to replication stress[J]. Cancer Discov, 2024, 14(3): 508-523.
[44]	WANG Q, LIU Y, LI Z Z, et al. Establishment of a novel lysosomal signature for the diagnosis of gastric cancer with in-vitro and in-situ validation[J]. Front Immunol, 2023, 14: 1182277.
[45]	GAO P, XIAO Q, TAN H, et al. Interpretable multi-modal artificial intelligence model for predicting gastric cancer response to neoadjuvant chemotherapy[J]. Cell Rep Med, 2024, 5(12): 101848.
[46]	CHEN Z F, CHEN Y, SUN Y, et al. Predicting gastric cancer response to anti-HER2 therapy or anti-HER2 combined immunotherapy based on multi-modal data[J]. Signal Transduct Target Ther, 2024, 9(1): 222.
[47]	AL-BATRAN S E, HOMANN N, PAULIGK C, et al. Perioperative chemotherapy with fluorouracil plus leucovorin, oxaliplatin, and docetaxel versus fluorouracil or capecitabine plus cisplatin and epirubicin for locally advanced, resectable gastric or gastro-oesophageal junction adenocarcinoma (FLOT4): a randomised, phase 2/3 trial[J]. Lancet, 2019, 393(10184): 1948-1957.
[48]	LI J M, ZHANG C, WEI J, et al. Intratumoral and peritumoral radiomics of contrast-enhanced CT for prediction of disease-free survival and chemotherapy response in stage Ⅱ/Ⅲ gastric cancer[J]. Front Oncol, 2020, 10: 552270.
[49]	TAN J W, WANG L, CHEN Y, et al. Predicting chemotherapeutic response for far-advanced gastric cancer by radiomics with deep learning semi-automatic segmentation[J]. J Cancer, 2020, 11(24): 7224-7236.
[50]	ZHOU Z X, JIANG Y M, SUN Z P, et al. Virtual multiplexed immunofluorescence staining from non-antibody-stained fluorescence imaging for gastric cancer prognosis[J]. EBioMedicine, 2024, 107: 105287.
[51]	CAI W Y, DONG Z N, FU X T, et al. Identification of a tumor microenvironment-relevant gene set-based prognostic signature and related therapy targets in gastric cancer[J]. Theranostics, 2020, 10(19): 8633-8647.
[52]	AJANI J A, D’AMICO T A, BENTREM D J, et al. Gastric cancer, version 2.2022, NCCN clinical practice guidelines in oncology[J]. J Natl Compr Canc Netw, 2022, 20(2): 167-192.
[53]	MA T T, CUI J L, WANG L W, et al. A multiphase contrast-enhanced CT radiomics model for prediction of human epidermal growth factor receptor 2 status in advanced gastric cancer[J]. Front Genet, 2022, 13: 968027.
[54]	SHIN J, LIM J S, HUH Y M, et al. A radiomics-based model for predicting prognosis of locally advanced gastric cancer in the preoperative setting[J]. Sci Rep, 2021, 11(1): 1879.
[55]	ARORA A, ALDERMAN J E, PALMER J, et al. The value of standards for health datasets in artificial intelligence-based applications[J]. Nat Med, 2023, 29(11): 2929-2938. doi: 10.1038/s41591-023-02608-w pmid: 37884627
[56]	张潇, 周辉, 何晶晶, 等. 数据治理法制化背景下中国临床研究数据收集和应用新考量[J]. 中华消化外科杂志, 2022(1): 89-92.
	ZHANG X, ZHOU H, HE J J, et al. New consideration for data collection and application of clinical research under the back-ground of ligalization of data administration in China[J]. Chin J Dig Surg, 2022(1): 89-92.
[57]	RIBEIRO JUNIOR H L. AI ethics in medical research: the 2024 Declaration of Helsinki[J]. Lancet, 2024, 404(10467): 2048-2049. doi: 10.1016/S0140-6736(24)02376-6 pmid: 39580196