Imagine swallowing a tiny camera pill that takes thousands of photos of your gut to check for cancer. Right now, doctors have to look at every single photo by hand, which takes forever and is easy to mess up. This project builds a smart computer program that acts like a high-speed assistant, spotting polyps and problems automatically so doctors only focus on the important images.
Manual reading of colon capsule endoscopy images is time-consuming, expensive, and prone to human error, making the technology less viable than traditional colonoscopies.
A set of AI algorithms for image analysis, a clinical support system for data transmission, and a validated diagnostic pathway including implementation guidelines.
If you are a hardware developer dealing with slow diagnostic workflows for camera pills — this project developed AI algorithms that automate image reading. This makes the capsule technology more clinically viable by reducing the manual labor required for analysis.
If you are a software provider dealing with the need for better clinical data handling — this project developed a clinical support system for data storage and transmission. This allows for a more efficient diagnostic pathway for colorectal screening.
If you are a clinic operator dealing with high hospital capacity burdens and patient discomfort from traditional colonoscopies — this project developed a validated AI-assisted pathway. This enables you to offer home-based CCE screenings that are faster and more acceptable to patients.
Based on available project data, specific pricing or cost figures for the AI algorithms are not provided.
Yes, the project specifically focuses on implementation guidelines and upscaling adjustments to integrate the solutions into clinical practice.
Based on available project data, there is no specific information regarding patents or licensing terms for the developed algorithms.
The consortium includes experts in regulatory affairs to ensure the AI-assisted pathway is clinically validated and viable.
The project runs from 2022-09-01 to 2026-08-31, with some algorithms being validated during the first 2 years.
It is integrated via a clinical support system for data handling, storage, and transmission, supported by specific implementation guidelines.
The consortium is heavily weighted toward academic and research expertise, with 9 universities and 1 research institute. However, it maintains a practical edge with 2 industry partners and a coordinator from a public regional authority (Region Syddanmark). With 13 partners across 6 countries, the group combines deep data science and epidemiological knowledge with regulatory and health-economic expertise to ensure the AI tools are clinically applicable.
Contact Region Syddanmark in Denmark for partnership inquiries.
Contact SciTransfer to explore licensing opportunities for the AICE AI algorithms.
