15 September 2020

The most important factor for training world-class artificial intelligence (AI) is access to massive amounts of data. High-quality medical data is particularly hard to come by as it often requires time-consuming processing by specialists to be useful. There is also an insecurity in the community about how to share data in a secure, legal and ethical way.

A window from the data hub.
A data set entry in the AIDA Data Hub.Images showing histology tissue from breast cancer axillary lymph nodes. from
The AIDA Data Hub provides a platform where researchers can gather and share large volumes of medical image data. So far, more than 5 TB image data from radiology and pathology has been added to the data hub.

-AI has good potential to help with many of the challenges that exist in healthcare. AI solutions perform better the more different types of data they are trained on and therefore access to data from different parts of the world is essential, says AIDAs Data Director Joel Hedlund.

The data hub has already facilitated sharing of data sets from Swedish researchers to six other researcher groups in four different countries (Spain, China, South Korea and United Kingdom) and more is in the pipeline.

- We want the data that we put a lot of resources into collecting to come to use as much as possible. We ensure this by making it available to other researchers in a legal and ethical way, Joel Hedlund explains.

Currently, AIDA exclusively uses anonymized data. However, to facilitate export and work with larger amounts of data, AIDA is developing a platform that is secure enough to store, share and process also identifiable data.

FAIR Data

AIDA supports Open Science which means that you are transparent about what you have done and which data you have used. One way to work with Open Science is to follow the FAIR data guidelines.

Findable, Accessible, Interoperable and Reusable (FAIR) data means that you make it possible for other researchers to find and use your data in their research.

In 2020, the European Open Science Cloud (EOSC)-Nordic carried out an independent evaluation of FAIR readiness among 98 data repositories in the Nordics (results to be published). The AIDA Data Hub was included in this evaluation and was shown to be among the 12% best scoring repositories in the sample.

Analytic Imaging Diagnostics Arena, AIDA

AIDA is a Swedish arena for research and innovation on artificial intelligence, AI, for medical image analysis. Here, academia, healthcare and industry will meet to translate technical advances in AI technology into patient benefit in the form of clinically useful tools. The arena is national but has its physical base at CMIV at Linköping University. AIDA is an initiative within the Strategic innovation program Medtech4Health, jointly supported by VINNOVA, Formas and the Swedish Energy Agency.

The AIDA Data Set Register: https://datasets.aida.medtech4health.se

Contact

Latest news from LiU

Kaiqian Wang.

Discovery about pain signalling may contribute to better treatment

LiU researchers have pinpointed the exact location of a specific protein fine-tuning the strength of pain signals. The knowledge can be used to develop drugs for chronic pain that are more effective and have fewer side effects.

Associate professor Jonathan Josefsson against a grey sky.

Unequal conditions for young people at UN climate summits

Today, young people can participate in major UN climate conferences. But inequality and bureaucracy make this impossible for many. This is the conclusion of a study carried out at Linköping University.

Researchers in front of a tree in a forest

LiU researchers explore sustainable forest management in the Amazon

Can climate action go hand in hand with the needs of local Amazonian communities? A research team from Linköping University is investigating this question through interdisciplinary work with communities in the Mamirauá Reserve, Brazil.