Artificial intelligence (AI) can do more than just write lyrics and create songs. For example, AI algorithms can be trained to detect cancer at an early stage. But dare we blindly trust the notes of a computer that a radiologist can’t see with the naked eye?
Het werkt eigenlijk heel simpel: een computer krijgt foto’s van CT-scans te zien. Voor elk plaatje waarop hij bepaalde afwijkingen detecteert, wordt de computer ‘beloond’. Na dit tienduizenden keren te hebben herhaald, heeft de computer geleerd wanneer een mogelijke tumor op de scan te zien is. Hij is zó goed getraind, dat hij er zelfs beter in is dan de mens.
Dit is slechts een van de weinige toepassingen van AI die er op dit moment in de zorg zijn. Maar deze techniek is veelbelovend en kan straks mogelijk veel sneller en nauwkeuriger dan radiologen vaststellen of iemand een kwaadaardige tumor in zijn lichaam heeft. En hoe sneller potentiële kanker wordt ontdekt, hoe beter het vaak te behandelen is.
Deze week werd een nieuwe studie naar zo’n AI-toepassing gepubliceerd in eBioMedicine, de medische tak van het wetenschappelijke tijdschrift The Lancet. De onderzoekers bouwden een AI-algoritme dat in staat is om in een vroeg stadium ‘kankerknobbeltjes’ op longen te detecteren.
“In feite kun je deze techniek voor elke vorm van kanker toepassen”, zegt Mireille Broeders. Zij is als hoogleraar Pesonalized Cancer Screening verbonden aan het Radboudumc. “Dat komt doordat zo’n algoritme informatie uit zo’n beeld weet te halen wat wij als mensen niet kunnen zien.”
Krijg een melding bij nieuwe berichten
AI cancer research has taken off thanks to self-learning computers
In the study eBioMedicine It is one of several studies being conducted on the applications of artificial intelligence in cancer care. According to Jonas Tywin, Holland is at the forefront of researching these types of algorithms. Teuwen is affiliated with the Netherlands Cancer Institute at Antonie van Leeuwenhoek Hospital in Amsterdam. “In the Netherlands, we do these kinds of projects on a large scale,” he says.
Broeders and Teuwen say research in AI and cancer has been around for a long time, but it has only developed strongly in recent years. Broders: “The moment deep learning started to play a role, it really took off.” Deep learning is the technique that enables computers to learn from large amounts of raw data (think of the example of a CT scan).
“It’s hard to say what stage we’re in right now, as completely new disciplines within AI are being added on a regular basis,” Tywin says. “But when we look at breast cancer screening, I would say the technology is at a point where we can deploy it.”
The radiologist may obtain information that cannot be verified
But both Broeders and Teuwen insist on the need to think carefully about the (ethical) questions that come with artificial intelligence. According to Broeders, it is entirely possible that algorithms can detect changes that cannot be seen by the human eye. “It means that you as a radiologist are given information that you have no control over.”
“Do we trust such an algorithm? Is it acceptable to make a decision based on such an algorithm alone?” Broeders wondered out loud. According to her, there are a lot of questions that we as a society have to answer. “Does an algorithm have to be perfect? Human labor is often not perfect either, but with technology we often have the idea that it has to work perfectly.”
Teuwen also cautions that most algorithms are not yet ready for widespread use. Most algorithms are trained using a bounded dataset. “For example, you could build a screening algorithm for women from the Netherlands. But if we want to apply the model in the United States, we have to carefully examine whether it works well there.”
This is also the case with the study in eBioMedicine. This algorithm performed very well on the dataset in which it was developed. Broders: “They also tested it in a new data set. It does indeed work less well there, as it does in general. It also clearly indicates that this needs further investigation.”