Publications
Peer-reviewed work on the models and the products built on them, with the cohorts they were tested on. Newest first.
- November 2025Octo ImmuneAI-powered immune profiling from histopathology slides for chemo-radiotherapy outcome prediction in rectal cancer: a study using clinical trial and real-world cohortsShen Z., Brand D., Simard M., et al. · The Lancet eBioMedicine
This study examines routine pathology images using AI to measure the types and abundance of key immune cells surrounding rectal cancer tumors to predict survival and disease recurrence.
Read the paper → - October 2025Octo CellularityTumour Cell Density Quantified by Artificial Intelligence Enables Precise Chemo-Radiotherapy Planning for Locally Advanced Rectal Cancer Patients: A Post-hoc Study of the Phase 3 ARISTOTLE TrialShen Z., Brand D., Simard M., et al. · The Lancet Oncology
This post-hoc study of the Phase 3 ARISTOTLE trial utilizes artificial intelligence to quantify tumour cell density, enabling precise chemo-radiotherapy planning for patients with locally advanced rectal cancer.
Read the paper → - December 2024Octo MitosisA deep learning framework deploying segment anything to detect pan-cancer mitotic figures from haematoxylin and eosin-stained slidesShen Z., Simard M., Brand D., et al. · Nature Communications Biology
This study presents an artificial intelligence-based approach to detect mitotic figures in digitised whole-slide images, introducing a generalisable data creation pipeline and a high-performance detection model.
Read the paper → - June 2024Training dataImmunocto: a massive immune cell database auto-generated for histopathologySimard M., Shen Z., Bräutigam K., et al. · Medical Image Analysis
We introduce Immunocto, a massive, multi-million automatically generated database of immune cells to support the development of new classification models and provide a benchmark for evaluating existing ones.
Read the paper →
Preprints, talks and datasets
[Title]
[Venue, year]
[Title]
[Venue, year]
Immunocto
Automatically generated immune-cell database; access on request.
Working on a related question?
We co-author with clinical and academic groups. Tell us about the cohort.