ͯÑÕÊÓƵ

Magnetic resonance imaging (MRI) offers great opportunities when it comes to diagnosing cancer. However, the scanning procedure is extremely sensitive. One of the many problems can be that if the patient moves ever so slightly during the scan, the images will be blurry. This makes it more difficult to accurately determine the size and position of the cancer tumour. This is important to be able to plan the treatment with precision, for example to direct radiation so that it attacks the tumour but not the healthy tissue around the tumour.

On the other hand, as medical technology improves, the amount of available data increases to help the treatment of the patient, however it also significantly increases the workload of the already overworked medical staff. It can create information stress that can cause delays and errors. More efficient processes for image processing would therefore be a much-needed improvement.

Attila Simko, doctoral student at Department of Diagnostics and Intervention.

In his dissertation at the Department of Diagnostics and Intervention, Attila Simko shows how to optimize the quality and the efficient processing of MRI images by using machine learning. In the presented studies, Attila and his colleagues have developed machine learning models trained to eliminate common artefacts in MRI images, including noise and movement. They have also developed a robust model to create synthetic CT scans from MRI. To further promote their methods, they are all publicly available for researchers for further use and comparisons.

Attila Simko has created a web-based version of his thesis with several interactive figures to help with the understanding of the field. More about it is available on .