Uterine cancer is the most common tumor of the female genital tract. A lot of research is being done at the LUMC into this type of tumour. According to the researchers, the study into the use of AI contributes to the further improvement of the diagnosis and treatment of uterine cancer.
2,000 images of uterine cancer
To achieve this, the software must first be fed with artificial intelligence with a lot of images. The LUMC researchers used microscopy images of uterine cancer from more than 2,000 women who participated in the clinical PORTEC studies, coordinated from the LUMC by Professor Carien Creutzberg. With those unique images, the AI system was able to quickly learn to distinguish different types of uterine cancer. Importantly, the developed model shows the researchers where the visual information for the predictions is hidden in the tissue. The developed AI model is therefore not a black box like many other AI-driven systems.
AI helps with diagnosis and treatment
AI is increasingly being used, just like at LUMC, to support specialists in diagnosing and treating cancer. For example, a new automated system, developed by researchers at UMC Utrecht, is able to quickly and accurately inspect MRI images of breasts with dense mammary gland tissue using AI. The system ensures that the radiologist only sees images on which abnormalities have been detected and which may indicate breast cancer. But AI is also gratefully used in colon cancer, for example to indicate tumors that have started during surgery by placing a square around them.
DNA changes
At the LUMC, AI now helps to identify different types of uterine cancer, because no DNA changes can be seen with the naked eye. The researchers explain this on the LUMC website: ‘DNA changes in a tumor determine the behavior of the tumor and the course of the disease, that much has become clear in recent years, partly due to work at the LUMC. There are four types of uterine cancer, each with a different disease course. It is important for patient and doctor to know what type of tumor it is, but this currently requires costly, additional DNA tests. With AI, that situation can change dramatically.’
Sarah Fremond, PhD student in Pathology at LUMC explains: “Through this study we wanted to learn more about the relationship between the appearance of the tumor and the underlying DNA changes. With this work, we have learned which areas in the tumors contain the most important visual information for diagnosis and, therefore, what pathologists should focus on.”
ICT&health congres 2023
On January 30, 2023, ICT&health kicks off the new healthcare year with the annual major and influential healthcare conference on healthcare transformation.
Also be present? Book your entrance ticket quickly