Every year, more than 13,000 men in the Netherlands fall ill with prostate cancer. This makes it one of the most common types of cancer in our country. Thanks to the MR-Linac, a combination of an MRI scanner and a radiation device, it is possible to irradiate prostate cancer very precisely. This leads to fewer erection problems later. Scientists from UMC Utrecht are now looking to improve the technology even further, for example by using artificial intelligence (AI).
Prostate cancer is increasingly being treated with targeted radiation of the prostate. In many cases, this means that major surgery is no longer needed. With radiation therapy, it’s important that enough radiation reaches the prostate to fully fight the cancer. But surrounding tissues and organs should be spared as much as possible. These include the bladder, rectum, and the nerve and vascular structures responsible for erections.
‘Live’ image of the radiation area
Targeted irradiation is already gaining more and more success, partly thanks to the MR-Linac – an invention from Utrecht that is now used worldwide. It is an innovative combination of an MRI scanner and a radiation device, a so-called linear accelerator. This allows doctors to view the entire area “live” with MRI images during treatment. This allows you to direct the radiation very precisely. Doctors can also immediately correct the direction of the radiation if the prostate moves slightly, for example due to filling of the bladder or bowel movements.
After performing an MRI scan, a radiation oncologist still manually draws the relevant structures. PhD student Inge van den Berg is a medical technician at the UMC Utrecht Department of Radiotherapy. She is researching the application of artificial intelligence to speed up and improve image drawing.
Draw structures
“Tracing all the structures on the MRI images is very important, because then it becomes clear where the radiation should be concentrated and where the amount of radiation should stay below a certain dose. The doctor now does it manually and this takes a lot of time. Together with computer scientist Mark Savenije, I’m experimenting with algorithms that can draw all the important structures very quickly in advance. Ultimately, we want to use these types of AI techniques during the MR-Linac treatment as well, so that the direction of the radiation is automatically corrected as well. With this we want to shorten the treatment time and more treatments can be performed per day with MR-Linac.”
Faster and more accurate irradiation
“My research focuses in particular on the nervous and vascular structures responsible for erection. It is obviously important for many patients to spare these facilities as much as possible. You see now – besides the fact that exactly drawing those structures takes a long time – that every radiation oncologist does it a little differently. We think this can be done faster and more consistently. After all, the computer learns from many voices and we pass deep learning please. Then, if it’s consistent, we can further optimize the logging so that it’s ultimately faster and more accurate. Because the better the recording, the better and more targeted the radiation will be and hopefully fewer erection problems afterwards.
