Deep learning analysis of the adipose tissue and the prediction of prognosis in colorectal cancer.

Abstract

139 Background: Colorectal cancer (CRC) is the third most common type of cancer and has a poor prognosis and high recurrence rate. Research has shown that the lipid microenvironment surrounding tumors is closely associated with the occurrence, development, and metastasis of CRC. Recently, advances in artificial intelligence have greatly improved the accuracy of models for CRC prognosis and survival analysis. Methods: According to pathological images from the National Center for Tumor diseases(NCT), the University Medical Center Mannheim(UMM) database and the ImageNet data set, a model called VGG19 was pre-trained. A deep convolutional neural network(CNN), VGG19CRC, was trained by the migration learning method. According to the VGG19CRC model, adipose tissue scores were calculated for TCGA-CRC hematoxylin and eosin(H&E) images and images from patients at Zhujiang Hospital of Southern Medical University and First People’s Hospital of Chenzhou. Kaplan-Meier(KM) analysis was used to compare the overall survival(OS) of patients. The XCell and MCP-Counter algorithms were used to evaluate the immune cell scores of the patients. Gene set enrichment analysis(GSEA) and single-sample GSEA(ssGSEA) were used to analyze upregulated and downregulated pathways. Results: In TCGA-CRC, patients with high-adipocytes(high-ADI) CRC had significantly shorter OS times than those with low-ADI CRC. In a validation queue from Zhujiang Hospital of Southern Medical University(Local-CRC1), patients with high-ADI had worse OS than CRC patients with low-ADI. In another validation queue from First People's Hospital of Chenzhou(Local-CRC2), patients with low-ADI CRC had significantly longer OS than patients with high-ADI CRC. In subgroup analysis, ADI could be used as a prognostic marker for patients with colon adenocarcinoma(COAD) and rectum adenocarcinoma(READ), as well as male and female CRC patients. Among these subgroups, patients with lower ADI also had significantly improved OS. Compared with the low-ADI group, high-ADI patients had significantly decreased CD8+ T cells, T cells,and monocytes in the tumor immune microenvironment(TIME), while M2 macrophages were significantly increased. According to the GSEA and ssGSEA analyses, pathways mediating anti-tumor immunity were significantly downregulated in the high-ADI group, while some oncogenic signaling pathways were significantly upregulated. Conclusions: We developed a deep convolution network to segment various tissues from pathological H&E images of CRC and automatically quantify ADI. This allowed us to further analyze and predict the survival of CRC patients according to information from their segmented pathological tissue images, such as tissue components and the tumor microenvironment. Furthermore, we found that ADI may also predict OS in CRC patients and among the subgroups.