Predicting response to immunotherapy in gastric cancer via assessing perineural invasion-mediated inflammation in tumor microenvironment.

BACKGROUND: The perineural invasion (PNI)-mediated inflammation of the tumor microenvironment (TME) varies among gastric cancer (GC) patients and exhibits a close relationship with prognosis and immunotherapy. Assessing the neuroinflammation of TME is important in predicting the response to immunotherapy in GC patients. METHODS: Fifteen independent cohorts were enrolled in this study. An inflammatory score was developed and validated in GC. Based on PNI-related prognostic inflammatory signatures, patients were divided into Clusters A and B using unsupervised clustering. The characteristics of clusters and the potential regulatory mechanism of key genes were verified by RT-PCR, western-blot, immunohistochemistry and immunofluorescence in cell and tumor tissue samples.The neuroinflammation infiltration (NII) scoring system was developed based on principal component analysis (PCA) and visualized in a nomogram together with other clinical characteristics. RESULTS: Inflammatory scores were higher in GC patients with PNI compared with those without PNI (P < 0.001). NII.clusterB patients with PNI had abundant immune cell infiltration in the TME but worse prognosis compared with patients in the NII.clusterA patients with PNI and non-PNI subgroups. Higher immune checkpoint expression was noted in NII.clusterB-PNI. VCAM1 is a specific signature of NII.clusterB-PNI, which regulates PD-L1 expression by affecting the phosphorylation of STAT3 in GC cells. Patients with PNI and high NII scores may benefit from immunotherapy. Patients with low nomogram scores had a better prognosis than those with high nomogram scores. CONCLUSIONS: Inflammation mediated by PNI is one of the results of tumor-nerve crosstalk, but its impact on the tumor immune microenvironment is complex. Assessing the inflammation features of PNI is a potential method in predicting the response of immunotherapy effectively.

Multi-modal analysis for accurate prediction of preoperative stage and indications of optimal treatment in gastric cancer.

BACKGROUND: Accurate preoperative clinical staging of gastric cancer helps determine therapeutic strategies. However, no multi-category grading models for gastric cancer have been established. This study aimed to develop multi-modal (CT/EHRs) artificial intelligence (AI) models for predicting tumor stages and optimal treatment indication based on preoperative CT images and electronic health records (EHRs) in patients with gastric cancer. METHODS: This retrospective study enrolled 602 patients with a pathological diagnosis of gastric cancer from Nanfang hospital retrospectively and divided them into training (n = 452) and validation sets (n = 150). A total of 1326 features were extracted of which 1316 radiomic features were extracted from the 3D CT images and 10 clinical parameters were obtained from electronic health records (EHRs). Four multi-layer perceptrons (MLPs) whose input was the combination of radiomic features and clinical parameters were automatically learned with the neural architecture search (NAS) strategy. RESULTS: Two two-layer MLPs identified by NAS approach were employed to predict the stage of the tumor showed greater discrimination with the average ACC value of 0.646 for five T stages, 0.838 for four N stages than traditional methods with ACC of 0.543 (P value = 0.034) and 0.468 (P value = 0.021), respectively. Furthermore, our models reported high prediction accuracy for the indication of endoscopic resection and the preoperative neoadjuvant chemotherapy with the AUC value of 0.771 and 0.661, respectively. CONCLUSIONS: Our multi-modal (CT/EHRs) artificial intelligence models generated with the NAS approach have high accuracy for tumor stage prediction and optimal treatment regimen and timing, which could facilitate radiologists and gastroenterologists to improve diagnosis and treatment efficiency.

An artificial intelligence method to assess the tumor microenvironment with treatment outcomes for gastric cancer patients after gastrectomy.

BACKGROUND: The tumor microenvironment (TME) plays an important role in the occurrence and development of gastric cancer (GC) and is widely used to assess the treatment outcomes of GC patients. Immunohistochemistry (IHC) and gene sequencing are the main analysis methods for the TME but are limited due to the subjectivity of observers, the high cost of equipment and the need for professional analysts. METHODS: The ImmunoScore (IS) was developed in the TCGA cohort and validated in GEO cohorts. The Radiomic ImmunoScore (RIS) was developed in the TCGA cohort and validated in the Nanfang cohort. A nomogram was developed and validated in the Nanfang cohort based on RIS and clinical features. RESULTS: For IS, the area under the curves (AUCs) were 0.798 for 2-year overall survival (OS) and 0.873 for 4-year overall survival. For RIS, in the TCGA cohort, the AUCs distinguishing High-IS or Low-IS and predicting prognosis were 0.85 and 0.81, respectively; in the Nanfang cohort, the AUC predicting prognosis was 0.72. The nomogram performed better than the TNM staging system according to the ROC curve (all P < 0.01). Patients with TNM stage II and III in the High-nomogram group were more likely to benefit from adjuvant chemotherapy than Low-nomogram group patients. CONCLUSIONS: The RIS and the nomogram can be used to assess the TME, prognosis and adjuvant chemotherapy benefit of GC patients after radical gastrectomy and are valuable additions to the current TNM staging system. High-nomogram GC patients may benefit more from adjuvant chemotherapy than Low-nomogram GC patients.

CT-based radiomics nomograms for preoperative prediction of diffuse-type and signet ring cell gastric cancer: a multicenter development and validation cohort.

BACKGROUND: The prevalence of diffuse-type gastric cancer (GC), especially signet ring cell carcinoma (SRCC), has shown an upward trend in the past decades. This study aimed to develop computed tomography (CT) based radiomics nomograms to distinguish diffuse-type and SRCC GC preoperatively. METHODS: A total of 693 GC patients from two centers were retrospectively analyzed and divided into training, internal validation and external validation cohorts. Radiomics features were extracted from CT images, and the Lauren radiomics model was established with a support vector machine (SVM) classifier to identify diffuse-type GC. The Lauren radiomics nomogram integrating radiomics features score (Rad-score) and clinicopathological characteristics were developed and evaluated regarding prediction ability. Further, the SRCC radiomics nomogram designed to identify SRCC from diffuse-type GC was developed and evaluated following the same procedures. RESULTS: Multivariate analysis revealed that Rad-scores was significantly associated with diffuse-type GC and SRCC (p < 0.001). The Lauren radiomics nomogram showed promising prediction performance with an area under the curve (AUC) of 0.895 (95%CI, 0.957-0.932), 0.841 (95%CI, 0.781-0.901) and 0.893 (95%CI, 0.831-0.955) in each cohort. The SRCC radiomics nomogram also showed good discrimination, with AUC of 0.905 (95%CI,0.866-0.944), 0.845 (95%CI, 0.775-0.915) and 0.918 (95%CI, 0.842-0.994) in each cohort. The radiomics nomograms showed great model fitness and clinical usefulness by calibration curve and decision curve analysis. CONCLUSION: Our CT-based radiomics nomograms had the ability to identify the diffuse-type and SRCC GC, providing a non-invasive, efficient and preoperative diagnosis method. They may help guide preoperative clinical decision-making and benefit GC patients in the future.

Identification and validation of methylated differentially expressed miRNAs and immune infiltrate profile in EBV-associated gastric cancer.

BACKGROUND: The recent discovery of cancer/tissue specificity of miRNA has indicated its great potential as a therapeutic target. In Epstein-Barr virus-associated gastric cancer (EBVaGC), host genes are affected by extensive DNA methylation, including miRNAs. However, the role of methylated miRNA in the development of EBVaGC and immune cell infiltration has largely remained elusive. RESULTS: After crossmatching the DNA methylation and expression profile of miRNA and mRNA in the Gene Expression Omnibus (GEO) and the Cancer Genome Atlas Research Network (TCGA), we discovered that miR-129-2-3p was significantly suppressed due to hypermethylation on its enhancer in EBVaGC. The differentially expressed genes (DEGs) added up to 30, among which AKAP12 and LARP6 were predicted to be the target genes of miR-129-2-3p and negatively correlated with patients' survival. Accordingly, miR-129-2-3p was significantly down-regulated in tumor samples in 26 (65%) out of 40 cases in our cohort (P < 0.0001). The proliferation, migration and invasion functions of GC cells were significantly promoted when transfected with miR-129-2-3p inhibitor and suppressed when transfected with mimics or treated with 5-aza-2'-deoxycytidine. Moreover, a comprehensive regulation network was established by combining the putative transcription factors, miRNA-mRNA and protein-protein interaction (PPI) analysis. Pathway enrichment analysis showed that cytokine activity, especially CCL20, was the most prominent biological process in EBVaGC development. Immune cell infiltration analysis demonstrated CD4+ T cell, macrophage and dendritic cell infiltrates were significantly enriched for the prognostic-indicated hub genes. CONCLUSION: This study has provided a comprehensive analysis of differentially expressed miRNAs and mRNAs associated with genome-wide DNA methylation by integrating multi-source data including transcriptome, methylome and clinical data from GEO and TCGA, QPCR of tumor samples and cell function assays. It also gives a hint on the relationships between methylated miRNA, DEGs and the immune infiltration. Further experimental and clinical investigations are warranted to explore the underlying mechanism and validate our findings.