Early detection and precise preoperative staging of early gastric cancer (EGC) are critical. Therefore, this study aims to develop a deep learning model using portal venous phase CT images to accurately distinguish EGC without lymph node metastasis. This study included 3164 patients with gastric cancer (GC) who underwent radical surgery at two medical centers in China from 2006 to 2019. Moreover, 2.5D radiomic data and multi-instance learning (MIL) were novel approaches applied in this study. By basing the selection of features on 2.5D radiomic data and MIL, the ResNet101 model combined with the XGBoost model represented a satisfactory performance for diagnosing pT1N0 GC. Furthermore, the 2.5D MIL-based model demonstrated a markedly superior predictive performance compared to traditional radiomics models and clinical models. We first constructed a deep learning prediction model based on 2.5D radiomics and MIL for effectively diagnosing pT1N0 GC patients, which provides valuable information for the individualized treatment selection.
An abnormality in the regulation of adenosine deaminase acting on RNA (ADAR) enzymes, which catalyzed adenosine-to-inosine (A-to-I) RNA editing, was closely associated with the highly aggressive biologic behavior and poor prognosis in many malignancies. In the present study, we aimed to investigate the relationship among transcript factors-microRNAs regulatory network, immune environment, and ADAR gene in colorectal carcinoma (CRC). The association among the expression levels of ADAR mRNA and copy number variation, methylation, and mutation status were comprehensively analyzed using cBioPortal, Wanderer, and UALCAN databases in CRC datasets. ADAR-transcript factors (TFs) and ADAR-miRNA regulation networks were constructed by Cistrome Cancer and miRWalk2.0, respectively. The full network and subnetworks for ADAR coexpression genes were constructed using the STRING database and visualized by the MCODE module of the Cytoscape app. The relationship between ADAR mRNA expression and the abundance of infiltrating immune cells in CRC patients was explored by the Tumor Immune Estimation Resource, CIBERSORT, and single-gene gene set enrichment analysis (GSEA). ADAR mRNA was elevated and was a cancer essential gene in CRC. ADAR mRNA and transcripts P110 were significantly elevated in CRC compared to normal controls. Low-level methylation in the promoter region and high copy number amplification of ADAR were responsible for high levels of ADAR mRNA expression. ADAR coexpression genes were mainly involved in immunoregulation, especially T-lymphocyte activation. Hub genes, including CD2, CD274, and FASLG, were also significantly upregulated in the ADAR-high group compared to the control group. Besides, M1 macrophages were enriched in the ADAR-high group compared to the control group. This study demonstrated that ADAR, a new essential gene, was involved in the immune regulator and was a novel immune treatment target in CRC.
22 August 2023 in Journal of Cancer Research and Clinical Oncology
The benefit of adjuvant chemotherapy (ACT) for patients with gastric cancer (GC) after first-line neoadjuvant chemotherapy (NACT) is debated. This study de