Case studies

Advancing microsatellite instability testing with gastric cancer H&E-stained whole slide image data

Oncology
Gastric Cancer
Biomarker Pre-Screening
Clinical Data
Whole Slide Images
Pathology Data
Molecular Test Results

Background

Gastric cancer is among the leading causes of cancer death worldwide, with substantial increases in disease burden and mortality expected in the coming years1,2.

Microsatellite instability (MSI) is a key biomarker for prognosis and treatment selection across multiple tumor types, including gastric cancer.

AI-based tools for assessing MSI from H&E-stained whole-slide images show promise for improving testing efficiency, but their development and validation require large, well-labeled, real-world datasets3.

Objective

A biotechnology company approached Aigora for support in sourcing and curating a regulatory-grade multimodal dataset to facilitate validation of its AI-enabled digital pathology tool for MSI prescreening in gastric cancer.

Delivery

Aigora addressed this need by leveraging its global healthcare partner network to assess feasibility and curate a regulatory-grade dataset combining H&E-stained gastric cancer whole-slide images with comprehensive clinical, pathological, and molecular data.

The results of this work have been published with co-authorship from the Aigora team, marking a promising step toward cost-effective MSI pre-screening4. Read the abstract.

Dataset characteristics

  • Clinical data

    Patient demographics, neoadjuvant treatment information

  • Whole slides images

    De-identified H&E-stained gastric cancer whole slide images

  • Pathology data

    Tumor location, grading, staging, histological subtype

  • Molecular test results

    EBV, HER2, and MSI results

References

  1. Morgan E, Arnold M, Camargo MC, et al. The current and future incidence and mortality of gastric cancer in 185 countries, 2020–40: A population-based modelling study. eClinicalMedicine. 2022;47:101404. doi:10.1016/j.eclinm.2022.101404
  2. Park JY, Georges D, Alberts CJ, Bray F, Clifford G, Baussano I. Global lifetime estimates of expected and preventable gastric cancers across 185 countries. Nat Med. 2025;31(9):3020-3027. doi:10.1038/s41591-025-03793-6
  3. Bass C, Ntelemis F, Schmidt J, et al. H&E-based MSI/MMR testing with AI in colorectal cancer: a multi-centred blinded evaluation. npj Digit Med. 2025;9(1):44. doi:10.1038/s41746-025-02218-5
  4. Lubrano M, Samuelsson E, Filiot A, et al. 500 Beyond CRC: AI-powered MSI Status Detection Across Gastric, Endometrial and Biliary Tract Cancers— Robust Validation Across 11 International Cohorts and Novel Cross-Indication Insights. Laboratory Investigation. 2026;106(3):104785. doi:10.1016/j.labinv.2025.104785
Project metrics

  • Number of cases

    150

  • Number of variables per case

    15+

  • Delivery timeline

    3 months

More case studies

See all

Advancing microsatellite instability testing with gastric cancer H&E-stained whole slide image data

Oncology
Biomarker Pre-Screening
Pathology Data
Molecular Test Results
Read case study

Enabling AI-driven research in retinal diseases with longitudinal ophthalmic imaging data

Ophthalmology
Biomarker Discovery
Treatment Response Assessment
Multimodal Imaging Data
Clinical Data
Read case study

Identifying novel tissue biomarkers in inflammatory and autoimmune diseases with curated whole slide image data and biospecimens

Inflammatory Bowel Disease
Scleroderma
Biomarker Discovery
Translational Research
Clinical Data
Read case study