Dataset Information

Automatic Evaluation of the Severity of Gastric Intestinal Metaplasia With Pathology Artificial Intelligence Diagnosis System

ABSTRACT: The OLGIM staging system is highly recommended for a comprehensive assessment of GIM severity to evaluate patients’ gastric cancer risk. However, its need to take at least 4 biopsies is not clinically feasible due to a serious shortage of pathologists compared with the large number of gastric cancer screening population. We plan to develop a Digital Pathology artificial intelligence diagnosis system (DPAIDS), to automatically identify tumor areas in whole slide images(WSI) and quickly and accurately quantify the severity of intestinal metaplasia according to the proportion of intestinal metaplasia areas.

DISEASE(S): Metaplasia,Pathology,Gastric Intestinal Metaplasia,Artificial Intelligence,Gastric Cancer,Stomach Neoplasms

PROVIDER: 2740125 | ecrin-mdr-crc |

REPOSITORIES: ECRIN MDR

ACCESS DATA

Similar Datasets

Project description:Background: Intestinal metaplasia (IM) is a gastric precancerous lesion that precedes the development of gastric cancer in up to 3.77 cases/1000 person-years. It consists in a trans-differentiation process of gastric to intestinal tissue. Two histological subtypes exist, complete (CIM) and incomplete (IIM), the latter having higher progression rates to gastric cancer . Our objective was to identify molecular processes responsible for the tumoral transition from intestinal metaplasia to GC and the initial steps of this lesion Methods: We used expression microarray to compare the transcriptome of intestinal metaplasia subtypes that progress to gastric cancer (IIM-GC and CIM-GC) after a follow-up period with respect to those that do not progress (IIM control and CIM control). Also, IM-NoGC (IM control, comprising both IIM and CIM Control) was compared with healthy gastric mucosa. Differentially expressed genes were obtained and functional analyses (GSEA and IPA softwares) were performed. Some deregulated genes were validated by qPCR. Results: Histological subtypes of intestinal metaplasia that progress or not to GC differ less among them than to healthy mucosa. Incomplete intestinal metaplasia has a higher number of over-expressed carcinogenic genes and molecular processes than the complete subtype. Most relevant molecular processes and genes in this group include antigenic processing, inflammation, activation of cell cycle and cell proliferation, oncogenes and tumor suppressors. When IM-NoGC is compared with healthy gastric mucosa new identified transcripts include TRIM, TMEM, homeobox, transporters and nucleolar RNAs SNORDs116. We confirm previously reported processes such us intestinal differentiation, metabolism of lipids and of xenobiotics and identify new ones such as non tumoral Warburg effect and melatonin degradation. Conclusions: Differentially expressed genes and molecular processes have been identified for the first time in intestinal metaplasia that progress to gastric cancer. New genes and molecular processes have also been identified in intestinal metaplasia in comparison with healthy gastric mucosa.

Dataset Information

Automatic Evaluation of the Severity of Gastric Intestinal Metaplasia With Pathology Artificial Intelligence Diagnosis System

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure