Making AI applications in medicine safer
Landshut University of Applied Sciences starts research project with the Munich based AI company deepc to automate the safety standards for the application of artificial intelligence in medical imaging.
Artificial intelligence already facilitates the everyday lives of many doctors in medicine. For example, when X-rays or MRI scans are taken, it detects disease patterns, helps with diagnoses and recommends treatments. However, AI-based solutions require thousands of concrete examples to learn and must be verified (validated) at the same time to be approved as a medical device by the authorities. Data for the implementation of innovative AI products is often not big enough though and also not representative of the general public. In addition, medical image data are highly sensitive patient data which are subject to the strict regulations of the General Data Protection Regulation (GDPR) and cannot be used without restriction.
This is exactly where the new “NeuroTest” project at Landshut University of Applied Sciences, overseen by Prof. Dr. Stefanie Remmele, is stepping in. In collaboration with the Munich-based medical technology company deepc, the professor of Medical Technology research is researching how artificial patient data can be developed for use in AI models in medical imaging. At the same time, the project partners are working on an online platform to offer manufacturers of medical devices the opportunity to test their AI-based medical devices before applying for a license. The project is being funded by the Federal Ministry for Economic Affairs and Energy with more than 400,000 euros.
Call for standardised procedures
National, European and international medical institutions have been calling for a standardised validation option for AI applications in the field of radiology and medical imaging for a long time. In the next two years, the project team at Landshut University of Applied Sciences will be looking at the conditions under which AI models can deliver a consistent and meaningful result in imaging, in order to support doctors in the diagnosis accordingly. Unlike conventional methods, the accuracy of the AI solution not only depends on the data processing logic, but also on the data used to train the technology. “This is particularly challenging when processing MRI data, because contrast and image quality can vary greatly, there is no infinite number of images and the available training images never cover the entire range of possible variations,” Remmele explains.
Mix of artificial and real data
Landshut University of Applied Sciences is researching the influencing parameters of human brain images using existing MRI images and artificial test images. The patient’s age, gender, pre-existing illnesses or genetic and ethical information play an important role here, as do fluctuations in the recording parameters and the I hardware. “With the help of this generated and analysed data and the model knowledge about technical influences, we want to create artificial data sets which variations can be simulated from depending on the hardware, findings or patient,” Remmele explains the procedure. “With this, we can then test AI models against all these variations and detect which changes in the data a model does not react sufficiently robustly to,” says Remmele. The major challenge is to standardise the generated data in such a way that AI models can be evaluated sustainably and do not provide any incorrect information.
Support for manufacturers and doctors
At the same time, deepc’s AI and software specialists are developing software that enables manufacturers, for example PAC systems, to validate their AI-based products online and achieve the specified safety standards. “With the help of the development of methods to create synthetic reference data in combination with real patient data, which are constantly checked, added to and compared at the same time using a standardised software platform, we expect clear progress in the standardisation, application and especially in the approval process for AI solutions in the field of imaging medical technology,” explains Dr. Franz Pfister, CEO of deepc.
About the project
The “NeuroTest” project is to run until December 2022. The project manager at Landshut University of Applied Sciences is Prof. Dr. Stefanie Remmele, head of Medical Technology research. The Munich-based medical technology company deepc is an active cooperation partner for the project overseen by CEO Dr. Franz Pfister. The Technische Universität Berlin and the Physikalisch-Technische Bundesanstalt Berlin (PTB) are associated partners. The total project amount is around 630,000 euros. The Federal Ministry for Economic Affairs and Energy is funding the project with around 400,000 euros as part of the “Central Innovation Program for SMEs (ZIM)” programme. deepc is contributing 225,000 euros from its own funds.
About Landshut University of Applied Sciences
Landshut University of Applied Sciences stands for excellent teaching, further education and applied research. The six faculties of Business Administration, Electrical Engineering and Industrial Engineering and Management, Computer Science, Interdisciplinary Studies, Mechanical Engineering and Social Work offer more than 30 courses of study. The courses on offer clearly focus on the labour market’s current and future requirements. The approximately 5,000 students benefit from the practical relevance of the teaching, individual support and modern technical equipment. The university offers a wide range of project topics for research institutions and companies, which are supervised and implemented by scientific experts with the best know-how. More than 118 professors work in teaching and research.
About deepc
At WERK1 digital start-up centre in Munich’s Werksviertel district, the founders of deepc (Dr. Franz Pfister, Julia Moosbauer, Dr. Michael Meyerhoff, Paul Mayer) and their team of over 25 experienced medical technology, AI, software and healthcare experts are working on the development of medical devices with the aim of simplifying and improving the workflow in imaging diagnostics with pioneering AI and software technology.
deepc started operating the new AI platform ´deepcOS´ in Europe in March 2021. The CE-marked medical device product, which has been tested in everyday hospital life and in radiological practices, supports and improves radiological diagnostics with various AI applications from leading international partners and is easy to integrate into existing clinical systems in compliance with data protection regulations. deepc was honoured with the Start-up Award and Special Award in the health category by the Federal Ministry for Economic Affairs and Energy (BMWi). More information at www.deepc.ai
Wissenschaftliche Ansprechpartner:
Prof. Dr. Stefanie Remmele
Media Contact
All latest news from the category: Medical Engineering
The development of medical equipment, products and technical procedures is characterized by high research and development costs in a variety of fields related to the study of human medicine.
innovations-report provides informative and stimulating reports and articles on topics ranging from imaging processes, cell and tissue techniques, optical techniques, implants, orthopedic aids, clinical and medical office equipment, dialysis systems and x-ray/radiation monitoring devices to endoscopy, ultrasound, surgical techniques, and dental materials.
Newest articles
The last missing piece of silicon photonics
International research team presents first electrically pumped continuous-wave semiconductor laser suitable for seamless silicon integration. Scientists from Forschungszentrum Jülich, FZJ, the University of Stuttgart, and the Leibniz Institute for High…
Space-time crystals, an important step toward new optical materials
KIT scientists design tailored materials for optical information processing. Photonic space-time crystals are materials that could increase the performance and efficiency of wireless communication or laser technologies. They feature a…
Quasiparticle loss in extreme quantum materials
A new study by Rice University physicist Qimiao Si unravels the enigmatic behaviors of quantum critical metals — materials that defy conventional physics at low temperatures. Published in Nature Physics…