Download the PDF poster:
Watch the presentation on-demand:
Presented at Digital Pathology & AI Congress USA 2025 | In support of the INCISE Project
As part of the INCISE project, an ambitious collaboration between the University of Glasgow, NHS Greater Glasgow and Clyde, and a network of industry partners, OracleBio led the Digital Pathology work package, helping to advance bowel cancer surveillance through scalable image analysis.
Our role focused on developing and deploying an automated pipeline to quantify Ki67 biomarker expression across a large cohort of colorectal polyp samples. This data forms part of a wider effort to create a multi-omics risk model that can help stratify patients and personalise future screening pathways.
What you’ll learn:
- A four-stage AI-driven image analysis workflow – Built in Visiopharm and validated by expert pathologists, our pipeline included tissue QC, adenoma classification, gland segmentation, and single-cell phenotyping.
- Execution at scale – The final pipeline was used to process over 2,200 Ki67-stained whole slide images, executed in parallel across 75 GPU-enabled cloud nodes.
- Fast, reliable performance – All 2,211 samples were analysed in just 45 hours—demonstrating the pipeline’s robustness, scalability, and future potential to support high-throughput diagnostic workflows.
Click the thumbnail above to download the full poster and see how OracleBio’s image analysis expertise is helping power the next generation of bowel cancer surveillance.
Stay up to date with OracleBio
Sign up to our mailing list to stay informed about news, webinars, events and more
You might also like these Posters:
Utilizing multiplex chromogenic IHC and digital image analysis to evaluate immune cell content and spatial distribution within NSCLC tumor tissue
OracleBio presented a poster at the 2017 Annual Meeting of the American Association for Cancer Research (AACR), which took place from the 1st to the 5th April in Washington D.C. The poster, made in collaboration with Asterand Bioscience, is entitled ‘Utilizing...
Quantitative Image Analysis of Fibrotic Lesion Progression in the Mouse Bleomycin Model of Pulmonary Fibrosis
OracleBio data was presented on a poster at the Keystone Symposia Injury, Inflammation and Fibrosis Conference, taking place 26th – 30th March 2017. The poster, made in collaboration with Charles River and Grünenthal, is entitled ‘Quantitative Image Analysis of...
Content and Spatial Distribution Analysis of PD-L1 Positive Tumor Cells and CD8 Positive T-Cells within Multiplex IHC Stained NSCLC Tumor Tissue
OracleBio data was presented on a poster at the International Molecular Medicine Tri-Conference, which took place in San Francisco on the 19th – 24th February 2017. The poster, made in collaboration with Asterand Bioscience, is entitled ‘Content and Spatial...



