Octopath
Octopath AI provides an AI-powered digital pathology platform that automates routine tasks like cell counting and tissue segmentation for pathologists. Its Kraken foundation model, trained on 14.1 million labeled cells, detects and classifies up to 23 cell types across 14 tissue and cancer types in under two minutes per slide, with reports aligned to RCPath, ICCR, or CAP standards.
- Healthcare Technology
- Artificial Intelligence
- Digital Health
- Data & Analytics
- Software Only
Funding
Raised to date
£2MRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Est. $2.5Macross 2 rounds
IU£1.5M · Seed
Announced Nov 2026 · from article date
Disclosed cumulative: $2.5M
Founders
Founder details are not available yet.
Product
Problem
Cancer cases are rising and diagnostic requirements are growing more complex, faster than the number of available pathologists. Laboratories face mounting pressure, growing delays, and increased specialist workload, while manual analysis remains time-intensive and varies between observers.
Solution
Octopath AI provides an AI-powered digital pathology platform that acts as a tireless digital assistant for pathologists, automating routine tasks like cell counting and tissue segmentation while returning quantitative insight. The platform's foundation model, Kraken, trained on 14.1 million labeled cells, detects and classifies up to 23 cell types across 14 tissue and cancer types in under two minutes per slide. Pathologists can connect any scanner in any format, run the analysis, and receive overlays, counts, and reports aligned to RCPath, ICCR, or CAP reporting standards. The goal is not to replace pathologists but to support them with intuitive, reliable, and seamlessly integrated tools developed together with medical institutions.
Target Audience
Primary customers are pathologists, clinical laboratories, and medical institutions that need quantitative, reliable cell analysis to manage rising cancer case volumes and complex diagnostic requirements.
Features
- Kraken H&E foundation model trained on 14.1 million labeled cells across 14 tissue and cancer types
- Detection and classification of up to 23 cell types in a single pass, including mitoses and lymphocytes
- End-to-end analysis in under two minutes per biopsy slide
- Scanner-agnostic workflow supporting any scanner and any slide format
- Automated report generation aligned with RCPath, ICCR, and CAP reporting standards
- Evidence-first approach with published methods and validation, including peer-reviewed publications
- Clinical co-development model where products originate from pathologist questions and are validated on real cases