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. AIDA is an initiative within the Strategic innovation program Medtech4Health, jointly supported by VINNOVA, Formas and the Swedish Energy Agency.
Artificial Intelligence in Healthcare
The technical development within AI has been extremely strong in recent years. Modern AI is a toolbox that fits perfectly into the healthcare vision of “precision medicine”, the fully tailored treatment for each patient. The potential is particularly accentuated in diagnostic imaging, that is, radiology and pathology, where many research studies have shown that AI solutions have tremendous potential for improving quality and efficiency of care.
Despite the recognized potential, very few AI solutions have yet reached actual use in healthcare. The reason is that the step from experiments to clinical routine entails many challenges that you don’t come across in a research lab. Unlike the lab environment, this “clinical wilderness” requires robust handling of all situations, even where incoming data are of poor quality, are contradictory or incomplete, as well as managing constant change of, for example, the set of data sources and human operators. Even the most powerful algorithms need to be carefully placed in a context of workflow and interaction innovations to be useful.
AIDA’s objective is to develop AI-based decision support solutions for imaging diagnostics that reach all the way to clinical use. An underpinning fundamental insight is that this complex challenge requires both interdisciplinary and cross-sectoral collaboration.
AIDA – an Arena for National Collaboration
AIDA is built on the three cornerstones shown in the picture. Most resources are used for projects developing AI-based decision support solutions. These are run by research groups in industry and academia across Sweden, in collaboration with health care providers. Opportunities to suggest projects are published regularly, and those approved are partially funded by AIDA.
The second cornerstone is the AIDA core environment, physically located at CMIV at Linköping University, designed to support the development projects. All AIDA partners have access to a tailor-made technology platform for efficient AI development, run and developed by Sectra, and large amounts of training data will gradually be made available. Perhaps even more important is the meeting place aspect of the core environment, where workshops and meet-ups are frequently organized, providing valuable knowledge and exchanges.
The third cornerstone is clinical competence development, to give healthcare the right knowledge base to drive the AI development in the most effective direction. The main AIDA offering is clinical fellowships including partial funding. In a fellowship a care provider employee in AIDA:s area, for instance a radiologist or pathologist, gets continued education through carrying out an individual project concerning AI decision support. AIDA also regularly offers AI courses for physicians.
Engaging with AIDA
All companies, academic groups and health care providers interested in AI in diagnostic imaging are welcome to join AIDA. There are many possibilities to formal AIDA efforts with partial funding. But you can join also without defined project ideas as a Network partner (full description here), and among other benefits take part of the knowledge exchange and shared data sources within AIDA.
I september besökte NVIDIA AIDA-dagarna. Craig Rhodes gav en överblick av NVIDIA verksamhet inom sjukvårdsområdet och Nicola Rieke presenterade den tekniska plattformen. Presentationerna följdes av intressanta diskussioner om hur AIDA och NVIDIA kan samarbeta. Att [...]
Part of my job is to spread knowledge on AI, foremost with respect to imaging diagnostics, to audiences with limited experience in the domain. From those interactions I’ve learnt that one issue is particularly puzzling [...]
Två nya Clinical Fellows har anslutits till AIDA efter den senaste ansökningsomgången. Det finns nu sammanlagt fyra fellows. Collaboration on Simultaneous landmark detection and organ segmentation in medical images using multi-task deep neural network Bryan [...]
Alla pratar om AI - men hur ska det göra skillnad för vården? AIDA är en nationell satsning på AI inom bildanalys som förhoppningsvis kan få in ett par användningsområden i klinik.
I andra ansökningsomgången beviljade AIDAs styrgrupp medel till tre nya projekt. Två av projekten är inom patologi och ett inom radiologi. Den tredje och sista omgången har deadline 22 december 2017. Decision Support for Classification [...]
I första ansökningsomgången har AIDAs styrgrupp beviljat medel till två clinical felloships. Under projekttiden kommer forskarna att regelbundet vistas i Linköping för att ta del av AIDAs infrastruktur. Image- and AI-based cytological cancer screening Eva [...]
AIDA är en nationell kraftsamling kring artificiell intelligens (AI) inom bildmedicin, för forskning och innovation med tät koppling till vårdens vardag. Det kommer att vara möjligt att söka medel för projekt med AI-teknik inom bilddiagnostik. Det kan vara av två typer, antingen forskning/innovation (FoI) eller kliniska fellowships. Mer information om detta kommer före midsommar.
Under konferensen "Samverkan för Innovation" 4 maj 2017 pratade Mikael Damberg bland annat om de 700 miljoner som regeringen skjutit till i extrasatsning. 32 av dessa är antingen beviljade eller allokerade för kommande år för två projekt inom Medtech4Health.
AIDA has a physical base at Center for Medical Image Science and Visualization, CMIV, at Linköping University. CMIV has a long experience of working with techniqual challenges within medical imaging and implement innovations in clinical practice. CMIV is also internationally recognized for its interdisciplinary excellence in medical image science and the close collaboration with the clinic. You can read more about CMIV and AIDA at liu.se/research/aida.