Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Data refinery for AI development in medical imaging

Reference number
Coordinator RECOMIA AB
Funding from Vinnova SEK 300 000
Project duration March 2019 - September 2019
Status Completed
Venture Innovative Startups

Important results from the project

The objective was to transform and commercialize experiences and resources from an academic research group in order to promote the development of AI-based tools within medical imaging. To promote the development, it is of utmost importance to expand access to relevant training data with high annotation quality and overall data integrity. The project consisted of the following four parts: 1 establish network of radiologists and hospitals to get access to medical imaging data, 2 develop commercial strategy, 3 customize and validate prototype, 4 clarify relevant legal aspects.

Expected long term effects

Vi are in contact with several new research groups and companies, and experience firsthand the significant and increasing need for medical imaging training data with annotations. More research groups are now using our platform, and we have gained valuable experience working with new imaging modalities. Additionally, we have continued to develop our platform to accommodate more users, and we have documented rules and regulations pertaining to our technology and market.

Approach and implementation

We have conducted market research and gained a better understanding of the specific market characteristics within our market. Especially relating to the risks and opportunities for commercial companies to gain access to medical imaging training data from hospitals. Vi have documented aspects relating to “data processing”, “patient de-identification”, “HIPAA and FDA compliance”, “data security”, and “privacy policy”.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 13 March 2019

Reference number 2019-00364

Page statistics