Fraunhofer MEVIS Delivers Digital Infrastructure for Germany's Largest Health Study

FraunhoferJune marks the beginning of the National Cohort (NAKO), a long-term study of 200,000 subjects, the broadest of its kind in Germany to date. Gathering MRI data of up to 30,000 subjects is central to the study. These images help scientists gain valuable insight into the formation and development of diseases. As a partner in this research project, the Fraunhofer Institute for Medical Image Computing MEVIS in Bremen is responsible for making images directly available in reliably high quality - a significant prerequisite for the success of the study. The software system from MEVIS facilitates the participating radiologists’ access to the image data. This allows experts to notice abnormalities in the scans quickly and reliably and notify test subjects of serious problems promptly.

How do diseases such as diabetes, cancer, or dementia arise? What are the effects of genetics, environment, and lifestyle? The National Cohort will tackle these questions. The results of the study, which is planned to run for the next ten years, should improve both disease prevention and therapy. Since May 2014, 200,000 randomly selected men and women between the ages of 20 and 69 have been invited to undergo a comprehensive examination. During the examination, which lasts up to four hours, medical personnel check the subject's weight, blood pressure, and heart rate and inquire about the subject’s lifestyle and social environment. 40,000 subjects will be surveyed in more detail, undergoing a 24-hour sleep analysis, a smell test, and 3D echocardiography.

Another central element of the longitudinal study is the examination of 30,000 subjects with magnetic resonance imaging (MRI), which produces 3D images of the inside of the body without using harmful x-rays. Thereafter, a whole-body scan is produced at relatively low resolution. "To do this, MR scanners will be procured for five locations," says MEVIS project director Prof. Matthias Günther. "To ensure that the data from these five locations can be compared, we will use the same type of device at each location, and examinations will follow the same procedure."

After one of the five MRI centers produces a scan, the data will be uploaded directly to the server in Bremen. Data privacy is of utmost importance and is respected throughout the project: all data is 'pseudonymized', meaning that names of subjects are replaced with reference numbers. In addition, the images are transferred to Bremen over secure connections. For each subject, 6,000 images are taken, creating a data volume of approximately three gigabytes.

This is where MEVIS experts will apply their expertise: the Fraunhofer institute will serve as the collection center to preprocess medical image data and ensure its consistency. The data processed in Bremen will be inspected for incidental results by participating radiologists across Germany and stored in a long-term archive at the University of Greifswald and the German Cancer Research Center (DKFZ) in Heidelberg.

Next, quality assurance software is employed. "This software automatically analyzes the quality of image data and ensures that it can be compared with other data," says Günther. The software checks whether all data is available or if some is missing. If images are produced twice, the software decides which should be used for the radiologists' reading. In addition, the software checks all relevant measurement parameters and recognizes when the MR scanner produces an error or when a scan is blurry due to patient movement. "We notify the centers of deviations immediately, so that the personnel know when something goes wrong," says Günther. "This minimizes the chance that the same error occurs during the next scan."

Because up to 30,000 subjects will undergo MRI scans in the upcoming years, signs of disease may be discovered in some, such as early-stage tumors that are not yet felt by the patient but that could soon become dangerous. For this reason, radiologists at all five MRI centers review the images. They aim to inform subjects of potential problems within days, a requirement for timely diagnosis or treatment.

To achieve this, Fraunhofer MEVIS uses a browser-based implementation for remote inspection. Instead of sending complete, quality-assured image data via internet from Bremen to the five MRI centers and the reading center in Heidelberg, radiologists can easily review the scans in a web browser without needing to download the original data. This solution is integrated in a web-based platform developed and employed at the Greifswald University Hospital and the DKFZ in Heidelberg and functions as the central point for standardized input of all NAKO examination data. "This web-based implementation alleviates and accelerates quick access to information, so that clinicians can find possible abnormalities without delay," explains Günther. "In addition, our software informs whether a radiologist at the MRI center has noticed something."

The MR scanners will deliver images for the National Cohort for four years; the longitudinal study is financed for this time span. "It makes sense to examine the subjects again afterwards," says Günther. Before-and-after comparisons could generate valuable insight into the formation of diseases. According to Günther, "This is our goal, but the funding for the second phase is still pending."

About the National Cohort (NAKO)
Researching together for a healthier future is the goal of the National Cohort, currently the largest population study in Germany. In the upcoming years, 200,000 men and women across the country between the ages of 20 and 69 will be medically examined in 18 study centers and surveyed about their lifestyles. With the help of medical data, biosamples, and questionnaires about the participants, chronic illnesses will be more thoroughly researched. NAKO researchers hope to answer the following questions: How do diseases form? Are there factors that promote diseases formation? What roles do genetics, exposure to environmental factors, social contact, or lifestyle play? Can we protect ourselves from these diseases? How can these diseases be detected early? The project is financed by the Federal Ministry of Education and Research, 14 German states, and the Helmholtz Association of German Research Centers.

Most Popular Now

Unlocking the 10 Year Health Plan

The government's plan for the NHS is a huge document. Jane Stephenson, chief executive of SPARK TSL, argues the key to unlocking its digital ambitions is to consider what it...

Alcidion Grows Top Talent in the UK, wit…

Alcidion has today announced the addition of three new appointments to their UK-based team, with one internal promotion and two external recruits. Dr Paul Deffley has been announced as the...

AI can Find Cancer Pathologists Miss

Men assessed as healthy after a pathologist analyses their tissue sample may still have an early form of prostate cancer. Using AI, researchers at Uppsala University have been able to...

New Training Year Starts at Siemens Heal…

In September, 197 school graduates will start their vocational training or dual studies in Germany at Siemens Healthineers. 117 apprentices and 80 dual students will begin their careers at Siemens...

AI, Full Automation could Expand Artific…

Automated insulin delivery (AID) systems such as the UVA Health-developed artificial pancreas could help more type 1 diabetes patients if the devices become fully automated, according to a new review...

How AI could Speed the Development of RN…

Using artificial intelligence (AI), MIT researchers have come up with a new way to design nanoparticles that can more efficiently deliver RNA vaccines and other types of RNA therapies. After training...

MIT Researchers Use Generative AI to Des…

With help from artificial intelligence, MIT researchers have designed novel antibiotics that can combat two hard-to-treat infections: drug-resistant Neisseria gonorrhoeae and multi-drug-resistant Staphylococcus aureus (MRSA). Using generative AI algorithms, the research...

AI Hybrid Strategy Improves Mammogram In…

A hybrid reading strategy for screening mammography, developed by Dutch researchers and deployed retrospectively to more than 40,000 exams, reduced radiologist workload by 38% without changing recall or cancer detection...

Penn Developed AI Tools and Datasets Hel…

Doctors treating kidney disease have long depended on trial-and-error to find the best therapies for individual patients. Now, new artificial intelligence (AI) tools developed by researchers in the Perelman School...

Are You Eligible for a Clinical Trial? C…

A new study in the academic journal Machine Learning: Health discovers that ChatGPT can accelerate patient screening for clinical trials, showing promise in reducing delays and improving trial success rates. Researchers...

Global Study Reveals How Patients View M…

How physicians feel about artificial intelligence (AI) in medicine has been studied many times. But what do patients think? A team led by researchers at the Technical University of Munich...

New AI Tool Addresses Accuracy and Fairn…

A team of researchers at the Icahn School of Medicine at Mount Sinai has developed a new method to identify and reduce biases in datasets used to train machine-learning algorithms...