Gastric cancer is the fourth leading cause of cancer-related mortality across the globe, with a 5-year survival rate of less than 40%. In recent years, several applications of artificial intelligence (AI) have emerged in the gastric cancer field based on its efficient computational power and learning capacities, such as image-based diagnosis and prognosis prediction. AI-assisted diagnosis includes pathology, endoscopy, and computerized tomography, while researchers in the prognosis circle focus on recurrence, metastasis, and survival prediction. In this review, a comprehensive literature search was performed on articles published up to April 2020 from the databases of PubMed, Embase, Web of Science, and the Cochrane Library. Thereby the current status of AI-applications was systematically summarized in gastric cancer. Moreover, future directions that target this field were also analyzed to overcome the risk of overfitting AI models and enhance their accuracy as well as the applicability in clinical practice.

Background: Gastric cancer remains the third most common cause of cancer-related death worldwide. The development of novel therapeutic strategies for gastric cancer requires a deep understanding of the tumor cells and microenvironment of gastric cancer. Methods: We performed the single-cell RNA sequencing (scRNA-seq) on nine untreated non-metastatic gastric cancer patients. The transcriptomic atlas and ligand-receptor-based intercellular communication networks of the single cells were characterized. Results: Here, we profiled the transcriptomes of 47,304 cells from nine patients with gastric cancer. Tregs cells were significantly enriched in the gastric tumor tissues with increased expression of immune suppression related genes, which suggest a more immunosuppressive microenvironment. We also observed the absence of separate exhausted CD8+ T cell cluster, and the low expression level of exhaustion markers PDCD1, CTLA4, HAVCR2, LAG-3, and TIGIT in those specific cells. These may serve as molecular-level evidence for the limited benefit of immunotherapy among gastric cancer patients. In addition, we found ACKR1 specifically expressed in tumor endothelial cells, associated with poor prognosis in the cohort data and potentially provided a novel target of gastric cancer treatment. Furthermore, the tight interaction between endothelial cells and fibroblast implied the important roles of fibroblast in tumor angiogenesis and the maintenance of tumor vasculature. Conclusions:In conclusion, this single-cell atlas provide understanding the cellular heterogeneity from molecular level in gastric cancer and will serve as a valuable resource for developing innovative early and companion diagnostics, as well as discovering novel targeted therapies for gastric cancer.

No abstract

This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

No abstract