Gastric cancer remains a major global health concern, with early detection playing a crucial role in improving patient outcomes. This has driven increasing interest in artificial intelligence (AI) as a tool to enhance diagnostic accuracy.

In this paper, the authors review the current applications of AI in detecting early gastric cancer (EGC). They examine AI's role in image analysis, tumor differentiation, invasion depth assessment, and boundary identification—all essential for determining appropriate treatment strategies.

Deep learning, particularly convolutional neural networks (CNNs), has demonstrated strong performance in analyzing endoscopic images, improving detection rates and enabling more precise delineation of cancerous lesions. This has been particularly beneficial in procedures such as endoscopic submucosal dissection (ESD). However, as with most AI-driven approaches, challenges remain, including the need for large, high-quality datasets, standardization across imaging technologies, and seamless integration into clinical workflows.

This review provides a comprehensive look at both the advancements and limitations of AI-assisted gastric cancer diagnosis, paving the way for further research and clinical applications.