Artificial intelligence in gastric cancer diagnosis, treatment and prognostic prediction: current application and future perspective
Year: 2025
Type: article
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.
Author: PENG Dongge, WAN Ziye, LU Ning
Institutions: Xinjiang Medical University, Chinese People's Liberation Army
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6907172857
FWCI:
Cites:
Cited by:
Related to: