The Significance of the CLDN18-ARHGAP Fusion Gene in Gastric Cancer: A Systematic Review and Meta-Analysis

Early gastric cancer with RhoGAP fusion is linked to frequent nodal metastasis and a part of microtubular-mucocellular histology

INTRODUCTION

Gastric cancer with fusion genes involving the Rho GTPase-activating protein domain (RhoGAP-GC) is mainly included in the genomically stable type of The Cancer Genome Atlas classification. Clinical implications and histological characteristics of RhoGAP-GC in the early phase remain unclear.

METHODS

We analyzed 878 consecutive pT1b GCs for RhoGAP and its partner genes using fluorescence in situ hybridization assay.

RESULTS

RhoGAP fusion was detected in 57 (6.5%) GCs. Univariate analysis revealed that female sex, middle-lower third tumor location, advanced macroscopic type, tumor diameter > 2 cm, pT1b2, lymphatic invasion, venous invasion, negative EBER-ISH, and RhoGAP fusion were significantly associated with lymph node metastasis (LNM). Multivariate analysis presented RhoGAP fusion, lymphatic invasion, tumor diameter > 2 cm, advanced macroscopic type, venous invasion, and middle-lower third tumor location as independent risk factors for LNM. Notably, RhoGAP fusion had the highest odds ratio (3.92) for LNM among analyzed parameters (95% CI 2.12-7.27; p < 0.001). Compared to non-RhoGAP-GCs, RhoGAP-GCs were significantly frequent in younger females and showed the highest incidence of lymphatic invasion (56.2%) and LNM (49.1%) (p < 0.001). Histologically, microtubular architecture with pseudo-trabecular interconnection and small aggregations of tumor cells with a varied amount of cytoplasmic mucin, named "microtubular-mucocellular (MTMC) histology," was found in 93.0% (53 of 57) of RhoGAP-GCs in the intramucosal area. MTMC histology showed high sensitivity and negative predictive value (93.0% and 99.4%, respectively) for RhoGAP fusion, albeit positive predictive value is low (34.9%).

CONCLUSION

RhoGAP-GC is linked to a characteristic MTMC histology and a high incidence of LNM.

Research advances in the molecular classification of gastric cancer

Gastric cancer (GC) is a malignant tumor with one of the lowest five-year survival rates. Traditional first-line treatment regimens, such as platinum drugs, have limited therapeutic efficacy in treating advanced GC and significant side effects, greatly reducing patient quality of life. In contrast, trastuzumab and other immune checkpoint inhibitors, such as nivolumab and pembrolizumab, have demonstrated consistent and reliable efficacy in treating GC. Here, we discuss the intrinsic characteristics of GC from a molecular perspective and provide a comprehensive review of classification and treatment advances in the disease. Finally, we suggest several strategies based on the intrinsic molecular characteristics of GC to aid in overcoming clinical challenges in the development of precision medicine and improve patient prognosis.

Claudin 18.2 as a novel therapeutic target

Claudin 18.2, a tight-junction molecule predominantly found in the nonmalignant gastric epithelium, becomes accessible on the tumour cell surface during malignant transformation, thereby providing an appealing target for cancer therapy. Data from two phase III trials testing the anti-claudin 18.2 antibody zolbetuximab have established claudin 18.2-positive advanced-stage gastric cancers as an independent therapeutic subset that derives benefit from the addition of this agent to chemotherapy. This development has substantially increased the percentage of patients eligible for targeted therapy. Furthermore, newer treatments, such as high-affinity monoclonal antibodies, bispecific antibodies, chimeric antigen receptor T cells and antibody-drug conjugates capable of bystander killing effects, have shown considerable promise in patients with claudin 18.2-expressing gastric cancers. This new development has resulted from drug developers moving beyond traditional targets, such as driver gene alterations or growth factors. In this Review, we highlight the biological rationale and explore the clinical activity of therapies that target claudin 18.2 in patients with advanced-stage gastric cancer and explore the potential for expansion of claudin 18.2-targeted therapies to patients with other claudin 18.2-positive solid tumours.

Identification of gene fusions associated with amyotrophic lateral sclerosis

INTRODUCTION/AIMS

Genetics is an important risk factor for amyotrophic lateral sclerosis (ALS), a neurodegenerative disease affecting motor neurons. Recent findings demonstrate that in addition to specific genetic mutations, structural variants caused by genetic instability can also play a causative role in ALS. Genomic instability can lead to deletions, duplications, insertions, inversions, and translocations in the genome, and these changes can sometimes lead to fusion of distinct genes into a single transcript. Gene fusion events have been studied extensively in cancer; however, they have not been thoroughly investigated in ALS. The aim of this study was to determine whether gene fusions are present in ALS.

METHODS

Gene fusions were identified using STAR Fusion v1.10.0 software in bulk RNA-Seq data from human postmortem samples from publicly available data sets from Target ALS and the New York Genome Center ALS Consortium.

RESULTS

We report the presence of gene fusion events in several brain regions as well as in spinal cord samples in ALS. Although most gene fusions were intra-chromosomal events between neighboring genes and present in both ALS and control samples, there was a significantly greater number of unique gene fusions in ALS compared to controls. Lastly, we identified specific gene fusions with a significant burden in ALS, that were absent from both control samples and known cancer gene fusion databases.

DISCUSSION

Collectively, our findings reveal an enrichment of gene fusions in ALS and suggest that these events may be an additional genetic cause linked to ALS pathogenesis.

Saponins Derived from the Korean Endemic Plant Heloniopsis koreana Inhibit Diffuse-type Gastric Cancer Cells

Diffuse-type gastric cancer (GC) is a type of stomach cancer that occurs in small clusters of cells that are widely spread. It does not typically manifest with symptoms until the advanced stages and often goes undetected in routine imaging tests. In addition, there is no specific targeted therapy for diffuse-type GC and it has a high mortality risk. Hence, it is worthwhile to discover molecules against this cancer. In this study, the extract of Heloniopsis koreana, which is endemic to Korea, exhibited cytotoxicity against two diffuse-type GC cell lines, MKN1 and SNU668. This led to the isolation of 10 compounds, including a new cinnamic acid glycoside. Of the compounds, saponin Th (4) and SNF 11 (5) showed potent activities with IC50 values of 3.66 and 3.85 μM, respectively, in MKN1 cells, and 1.8 and 1.98 μM, respectively, in SNU668 cells. These compounds prevented cancer cell division, invasion, and colony formation in both cell lines. In addition, these compounds induced cancer cell death through conventional cell death pathways, showing an increase in ADP-ribose polymerase, caspase 3, and BAX and a decrease in BCL2.

Claudin18.2 in Advanced Gastric Cancer

Globally, the fifth most common cancer and the fourth leading cause of cancer-related mortality is gastric cancer (GC). Recent clinical trials on solid tumors enrolled patients who possess druggable genetic alterations, protein expression, and immune characteristics. In gastric or gastroesophageal junction (GEJ) cancers, trastuzumab combined with first-line chemotherapy in human epidermal growth factor receptor 2 (HER2)-positive patients and ramucirumab combined with second-line paclitaxel remarkably prolonged overall survival (OS) compared with chemotherapy alone, according to phase 3 trial results. Recently, immune checkpoint inhibitor (ICI) monotherapy was approved as third- or later-line treatment. Chemotherapy plus ICIs as first-line treatment exhibited improved survival compared with chemotherapy alone in HER2-negative patients according to Checkmate 649 trial results. Conversely, systemic chemotherapy prognosis remains poor. although some patients may achieve durable response to treatment and prolonged survival in advanced GC. Recently, a first-in-class, chimeric immunoglobulin G1 monoclonal antibody (zolbetuximab) that targets and binds to claudin 18 isoform 2 (CLDN18.2) has emerged as a new target therapy in GC treatment. Global phase Ⅲ trials revealed that the addition of zolbetuximab to first-line chemotherapy prolonged OS in CLDN18.2-positive and HER2-negative GC patients. This review summarizes recent clinical trials of CLDN18.2-targeted therapy.

Expression patterns of claudins in cancer

Claudins are four-transmembrane proteins, which were found in tight junctions. They maintain cell barriers and regulate cell differentiation and proliferation. They are involved in maintaining cellular polarity and normal functions. Different claudins show different expression patterns. The expression level and localization of claudins are altered in various cancers. They promote or inhibit proliferation, invasion, and migration of cancer cells through multiple signaling pathways. Therefore, claudins may serve as diagnostic markers, novel therapeutic targets, and prognostic risk factors. The important roles of claudins in cancer aroused our great interest. In the present review, we provide a summary of insights into expression patterns of claudins in cancer, which is more comprehensive and provides new ideas for further research.

Colorectal cancer cell-secreted exosomal miRNA N-72 promotes tumor angiogenesis by targeting CLDN18

Angiogenesis is essential for the growth and metastasis of several malignant tumors including colorectal cancer (CRC). The molecular mechanism underlying CRC angiogenesis has not been fully elucidated. Emerging evidence indicates that secreted microRNAs (miRNAs) may mediate the intercellular communication between tumor cells and neighboring endothelial cells to regulate tumor angiogenesis. In addition, exosomes have been shown to carry and deliver miRNAs to regulate angiogenesis. miRNA N-72 is a novel miRNA that plays a regulatory role in the EGF-induced migration of human amnion mesenchymal stem cells. However, the relation between miRNA N-72 and cancer remains unclear. We here found that CRC cells could secrete miRNA N-72. A high miRNA N-72 level was detected in the serum of CRC patients and the cultured CRC cells. Moreover, the CRC cell-secreted miRNA N-72 could promote the migration, tubulogenesis, and permeability of endothelial cells. In addition, the mouse xenograft model was used to verify the facilitating effects of miRNA N-72 on CRC growth, angiogenesis, and metastasis in vivo. Further mechanism analysis revealed that CRC cell-secreted miRNA N-72 could be delivered into endothelial cells via exosomes, which then inhibited cell junctions of endothelial cells by targeting CLDN18 and consequently promoted angiogenesis. Our findings reveal a novel mechanism of CRC angiogenesis and highlight the potential of secreted miRNA N-72 as a therapeutic target and a biomarker for CRC.

Molecular profile of poorly cohesive gastric carcinoma with special reference to survival

BACKGROUND

Patients with poorly cohesive gastric carcinoma (PCC) are known to have poor survival. However, detailed molecular biology of PCC has not been elucidated, except for mutations in CDH1 and RHOA. Additionally, the molecular profiles of signet-ring cell carcinoma (SRC) have not been fully investigated. We aimed to investigate the association between molecular profiles and survival in PCC and PCC subtypes.

METHODS

The present study included 455 patients with gastric adenocarcinoma underwent radical gastrectomy. Whole-exome sequencing and gene expression profiling were conducted. Patients were classified according to the WHO classification as PCC or non-PCC, with PCC being further classified into SRC, combined, and PCC not-otherwise-specified (NOS). Clinicopathological factors and survival were compared with molecular profiles.

RESULTS

Of the patients, 159 were classified with PCC, while 296 were classified with non-PCC. Among PCC, 44 were classified with SRC, 64 with combined, and 51 with PCC-NOS. Mutations in CDH1 and RHOA were remarkably more frequent in PCC than in non-PCC. PCC had worse overall survival (OS) and disease-specific survival (DSS) compared to non-PCC. For PCC, the SRC group had good OS and DSS, whereas PCC-NOS classification with CDH1 mutations was associated with extremely poor survival. In the PCC-NOS and combined groups, patients with mutations in the extracellular domain 1 of CDH1 had poor survival.

CONCLUSIONS

Our findings suggest that PCC has poorer survival than non-PCC. Accumulation of CDH1 and RHOA mutations are unique profiles in PCC. Among PCC, CDH1 mutations may play a crucial role in the survival of non-SRC PCC.

Targeting CLDN18.2 in cancers of the gastrointestinal tract: New drugs and new indications

Cancers of the gastrointestinal (GI) tract greatly contribute to the global cancer burden and cancer-related death. Claudin-18.2(CLDN18.2), a transmembrane protein, is a major component of tight junctions and plays an important role in the maintenance of barrier function. Its characteristic widespread expression in tumour tissues and its exposed extracellular loops make it an ideal target for researchers to develop targeted strategies and immunotherapies for cancers of the GI tract. In the present review, we focus on the expression pattern of CLDN18.2 and its clinical significance in GI cancer. We also discuss the tumour-promoting and/or tumour-inhibiting functions of CLDN18.2, the mechanisms regulating its expression, and the current progress regarding the development of drugs targeting CLDN18.2 in clinical research.

ARHGAP6 inhibits bladder cancer cell viability, migration, and invasion via β-catenin signaling and enhances mitomycin C sensitivity

The Rho/ROCK pathway regulates diverse cellular processes and contributes to the development and advancement of several types of human cancers. This study investigated the role of specific Rho GTPase-activating proteins (RhoGAP), ARHGAP6, in bladder cancer (BC). In this study, ARHGAP6 expression in BC and its clinical significance were investigated. In vitro and in vivo assays were used to explore the tumor-related function and the underlying molecular mechanism ARHGAP6 of in BC. The mRNA and protein levels of ARHGAP6 significantly reduced in human BC tissues and cell lines compared with corresponding adjacent non-cancerous tissues and normal urothelial cells. In vitro, ARHGAP6 overexpression markedly decreased the viability, migration, and invasion of BC cells. Interestingly, low ARHGAP6 expression in BC strongly correlated with poor patient survival and was highly associated with metastasis and β-catenin signaling. Furthermore, ARHGAP6 expression strongly influenced the sensitivity of BC cells to mitomycin C treatment. Together, our results demonstrate that ARHGAP6 plays critical roles in regulating the proliferation, migration, invasion, and metastasis of BC cells possibly via the modulation of β-catenin and strongly influences the chemosensitivity of BC cells.

Artificial intelligence-guided discovery of gastric cancer continuum

BACKGROUND

Detailed understanding of pre-, early and late neoplastic states in gastric cancer helps develop better models of risk of progression to gastric cancers (GCs) and medical treatment to intercept such progression.

METHODS

We built a Boolean implication network of gastric cancer and deployed machine learning algorithms to develop predictive models of known pre-neoplastic states, e.g., atrophic gastritis, intestinal metaplasia (IM) and low- to high-grade intestinal neoplasia (L/HGIN), and GC. Our approach exploits the presence of asymmetric Boolean implication relationships that are likely to be invariant across almost all gastric cancer datasets. Invariant asymmetric Boolean implication relationships can decipher fundamental time-series underlying the biological data. Pursuing this method, we developed a healthy mucosa → GC continuum model based on this approach.

RESULTS

Our model performed better against publicly available models for distinguishing healthy versus GC samples. Although not trained on IM and L/HGIN datasets, the model could identify the risk of progression to GC via the metaplasia → dysplasia → neoplasia cascade in patient samples. The model could rank all publicly available mouse models for their ability to best recapitulate the gene expression patterns during human GC initiation and progression.

CONCLUSIONS

A Boolean implication network enabled the identification of hitherto undefined continuum states during GC initiation. The developed model could now serve as a starting point for rationalizing candidate therapeutic targets to intercept GC progression.

Artificial intelligence in pancreatic cancer: diagnosis, limitations, and the future prospects-a narrative review

PURPOSE

This review aims to explore the role of AI in the application of pancreatic cancer management and make recommendations to minimize the impact of the limitations to provide further benefits from AI use in the future.

METHODS

A comprehensive review of the literature was conducted using a combination of MeSH keywords, including "Artificial intelligence", "Pancreatic cancer", "Diagnosis", and "Limitations".

RESULTS

The beneficial implications of AI in the detection of biomarkers, diagnosis, and prognosis of pancreatic cancer have been explored. In addition, current drawbacks of AI use have been divided into subcategories encompassing statistical, training, and knowledge limitations; data handling, ethical and medicolegal aspects; and clinical integration and implementation.

CONCLUSION

Artificial intelligence (AI) refers to computational machine systems that accomplish a set of given tasks by imitating human intelligence in an exponential learning pattern. AI in gastrointestinal oncology has continued to provide significant advancements in the clinical, molecular, and radiological diagnosis and intervention techniques required to improve the prognosis of many gastrointestinal cancer types, particularly pancreatic cancer.

The role and mechanism of claudins in cancer

Claudins are a tetraspan membrane protein multigene family that plays a structural and functional role in constructing tight junctions. Claudins perform crucial roles in maintaining cell polarity in epithelial and endothelial cell sheets and controlling paracellular permeability. In the last two decades, increasing evidence indicates that claudin proteins play a major role in controlling paracellular permeability and signaling inside cells. Several types of claudins are dysregulated in various cancers. Depending on where the tumor originated, claudin overexpression or underexpression has been shown to regulate cell proliferation, cell growth, metabolism, metastasis and cell stemness. Epithelial-to-mesenchymal transition is one of the most important functions of claudin proteins in disease progression. However, the exact molecular mechanisms and signaling pathways that explain why claudin proteins are so important to tumorigenesis and progression have not been determined. In addition, claudins are currently being investigated as possible diagnostic and treatment targets. Here, we discuss how claudin-related signaling pathways affect tumorigenesis, tumor progression, and treatment sensitivity.

ARHGAP-RhoA signaling provokes homotypic adhesion-triggered cell death of metastasized diffuse-type gastric cancer

Genetic alteration of Rho GTPase-activating proteins (ARHGAP) and GTPase RhoA is a hallmark of diffuse-type gastric cancer and elucidating its biological significance is critical to comprehensively understanding this malignancy. Here, we report that gene fusions of ARHGAP6/ARHGAP26 are frequent genetic events in peritoneally-metastasized gastric and pancreatic cancer. From the malignant ascites of patients, we established gastric cancer cell lines that spontaneously gain hotspot RHOA mutations or four different ARHGAP6/ARHGAP26 fusions. These alterations critically downregulate RhoA-ROCK-MLC2 signaling, which elicits cell death. Omics and functional analyses revealed that the downstream signaling initiates actin stress fibers and reinforces intercellular junctions via several types of catenin. E-cadherin-centered homotypic adhesion followed by lysosomal membrane permeabilization is a pivotal mechanism in cell death. These findings support the tumor-suppressive nature of ARHGAP-RhoA signaling and might indicate a new avenue of drug discovery against this refractory cancer.

Incorporating Immunotherapy in the Management of Gastric Cancer: Molecular and Clinical Implications

Simple Summary

Gastric cancer is one of the most common malignant tumours worldwide, with the fifth and third highest morbidity and mortality, respectively, of all cancers. Survival is limited, as most of the patients are diagnosed at an advanced stage, and are not suitable for surgery with a curative intent. Chemotherapy has only modestly improved patients’ outcomes and is mainly given with a palliative intent. Immunotherapy has improved overall survival of patients with gastric cancer, and has thus become a new standard of care in clinic. In this review we discuss the strong molecular rationale for the administration of immunotherapy in this disease and analyse the clinical data supporting its use.

Abstract

Gastric cancer has a median survival of 11 months, and this poor prognosis has not improved over the last 30 years. Recent pre-clinical data suggest that there is high tumour-related neoantigen expression in gastric cancer cells, suggesting that a clinical strategy that enhances the host’s immune system against cancer cells may be a successful approach to improve clinical outcomes. Additionally, there has been an increasing amount of translational evidence highlighting the relevance of PD-L1 expression in gastric cancer cells, indicating that PD-1/PD-L1 inhibitors may be useful. Several molecular subgroups of gastric cancer have been identified to respond with excellent outcomes to immunotherapy, including microsatellite instable tumours, tumours bearing a high tumour mutational burden, and tumours related to a chronic EBV infection. In gastric cancer, immunotherapy has produced durable responses in chemo-refractory patients; however, most recently there has been a lot of enthusiasm as several large-scale clinical trials highlight the improved survival noted from the incorporation of immunotherapy in the first line setting for advanced gastric cancer. Our review aims to discuss current pre-clinical and clinical data supporting the innovative role of immunotherapy in gastric cancer.

Gastric Cancer: Mechanisms, Biomarkers, and Therapeutic Approaches

Gastric cancer (GC) remains one of the most common deadly malignancies worldwide. Recently, several targeted therapeutics for treating unresectable or metastatic GC have been developed. Comprehensive characterization of the molecular profile and of the tumor immune microenvironment of GC has allowed researchers to explore promising biomarkers for GC treatment and has enabled a new paradigm in precision-targeted immunotherapy. In this article, we review established and promising new biomarkers relevant in GC, with a focus on their clinical implications, diagnostic methods, and the efficacy of targeted agents.

Gastric cancer and genomics: review of literature

Gastric cancer (GC) is a major health concern in many countries. GC is a heterogeneous disease stratified by histopathological differences. However, these variations are not used to determine GC management. Next-generation sequencing (NGS) technologies have become widely used, and cancer genomic analysis has recently revealed the relationships between various malignant tumors and genomic information. In 2014, studies using whole-exome sequencing (WES) and whole-genome sequencing (WGS) for GC revealed the entire structure of GC genomics. Genomics with NGS has been used to identify new therapeutic targets for GC. Moreover, personalized medicine to provide specific therapy for targets based on multiplex gene panel testing of tumor tissues has become of clinical use. Recently, immune checkpoint inhibitors (ICIs) have been used for GC treatment; however, their response rates are limited. To predict the anti-tumor effects of ICIs for GC and to select patients suitable for ICI treatment, genomics also provides informative data not only of tumors but also of tumor microenvironments, such as tumor-infiltrating lymphocytes. In therapeutic strategies for unresectable or recurrent malignant tumors, the target is not only the primary lesion but also metastatic lesions, and metastatic lesions are often resistant to chemotherapy. Unlike colorectal carcinoma, there is a heterogeneous status of genetic variants between the primary and metastatic lesions in GC. Liquid biopsy analysis is also helpful for predicting the genomic status of both primary and metastatic lesions. Genomics has become an indispensable tool for GC treatment and is expected to be further developed in the future.

The role of GTPase-activating protein ARHGAP26 in human cancers

Rho GTPases are molecular switches that play an important role in regulating the behavior of a variety of tumor cells. RhoA GTPase-activating protein 26 (ARHGAP26) is a GTPase-activating protein and inhibits the activity of Rho GTPases by promoting the hydrolytic ability of Rho GTPases. It also affects tumorigenesis and progression of various tumors through several methods, including formation of abnormal fusion genes and circular RNA. This review summarizes the biological functions and molecular mechanisms of ARHGAP26 in different tumors, proposes the potential clinical value of ARHGAP26 in cancer treatment, and discusses current issues that need to be addressed.

Association of CLDN18 Protein Expression with Clinicopathological Features and Prognosis in Advanced Gastric and Gastroesophageal Junction Adenocarcinomas

The tight junction protein claudin-18 (CLDN18), is often expressed in various cancer types including gastric (GC) and gastroesophageal adenocarcinomas (GECs). In the last years, the isoform CLDN18.2 emerged as a potential drug target in metastatic GCs, leading to the development of monoclonal antibodies against this protein. CLDN18.2 is the dominant isoform of CLDN18 in normal gastric and gastric cancer tissues. In this work, we evaluated the immunohistochemical (IHC) profile of CLDN18 and its correlation with clinical and histopathological features including p53, E-cadherin, MSH2, MSH6, MLH1, PMS2, HER2, EBER and PD-L1 combined positive score, in a large real-world and mono-institutional series of advanced GCs (n = 280) and GECs (n = 70). The association of IHC results with survival outcomes was also investigated. High membranous CLDN18 expression (2+ and 3+ intensity ≥75%) was found in 117/350 (33.4%) samples analyzed. CLDN18 expression correlated with age <70 (p = 0.0035), positive EBV status (p = 0.002), high stage (III, IV) at diagnosis (p = 0.003), peritoneal involvement (p < 0.001) and lower incidence of liver metastases (p = 0.013). CLDN18 did not correlate with overall survival. The predictive value of response of CLDN18 to targeted agents is under investigation in several clinical trials and further studies will be needed to select patients who could benefit from these therapies.

Targeting claudins in cancer: diagnosis, prognosis and therapy

Increasing evidence has linked claudins to signal transduction and tumorigenesis. The expression of claudins is frequently dysregulated in the context of neoplastic transformation, suggesting their promise as biomarkers for diagnosis and prognosis or targets for treatment. Claudin binders (Clostridium perfringens enterotoxin and monoclonal antibody) have been tested in preclinical experiments, and some of them have progressed into clinical trials involving patients with certain cancers. However, the clinical development of many of these agents has not advanced to clinical applications. Herein, I review the current status of preclinical and clinical investigations of agents targeting claudins for diagnosis, prognosis and therapy. I also discuss the potential of combining claudin binders with other currently approved therapeutic agents.

Artificial Intelligence in the Imaging of Gastric Cancer: Current Applications and Future Direction

Gastric cancer (GC) is one of the most common cancers and one of the leading causes of cancer-related death worldwide. Precise diagnosis and evaluation of GC, especially using noninvasive methods, are fundamental to optimal therapeutic decision-making. Despite the recent rapid advancements in technology, pretreatment diagnostic accuracy varies between modalities, and correlations between imaging and histological features are far from perfect. Artificial intelligence (AI) techniques, particularly hand-crafted radiomics and deep learning, have offered hope in addressing these issues. AI has been used widely in GC research, because of its ability to convert medical images into minable data and to detect invisible textures. In this article, we systematically reviewed the methodological processes (data acquisition, lesion segmentation, feature extraction, feature selection, and model construction) involved in AI. We also summarized the current clinical applications of AI in GC research, which include characterization, differential diagnosis, treatment response monitoring, and prognosis prediction. Challenges and opportunities in AI-based GC research are highlighted for consideration in future studies.