Artificial intelligence is already present in many imaging devices and will be even more so in the very near future. It presents two major applications in medical imaging, including that of automating, making reliable and accelerating the analysis of images (MRI, mammograms, PET scanner, etc.). This can be done in several ways, starting with “the use of AI algorithms which makes it possible to automatically detect anomalies in the images obtained,” explains Dr Irène Buvat. This facilitates rapid sorting between normal images and pathological images that require urgent radiological expertise to determine whether the patient has cancer.”
The use of AI algorithms also consists of automatically carrying out measurements on tumor images (volume or characterization of shape). Currently, radiologists or nuclear physicians perform these measurements manually, which is time-consuming and sometimes practitioners do not agree. AI helps automate and accelerate these processes. “This reduces variability between medical centers and observers,” adds the specialist. This is particularly useful in centers with limited resources and seeing few patients. »
And even, in the near future, algorithms could generate an initial imaging report, facilitating the work of radiologists or nuclear doctors who will then only have to verify and complete it. This automation process is underway and is gradually becoming widespread in French medical services.
AI makes images “speak”
The second part of progress using AI is to better exploit the information contained in images. “Currently, we mainly measure the volume, the largest dimension of the tumors, as well as the signal level (contrast), which allows us to roughly characterize the anomalies,” explains Irène Buvat. However, AI algorithms offer the possibility of measuring a multitude of information, up to hundreds of indices extracted from radiological images, called “radiomics”. »
But the issue is not limited to the simple measurement of these indices. They still need to be exploited. And here again, the machine can do better than the human brain. Indeed, the latter has difficulty analyzing more than four parameters simultaneously. So what about twenty, or even several dozen! This is where AI algorithms come into play. They can identify the best combinations of parameters, and thus be able, for example, to predict the response to treatment and the way in which they influence the prognosis of patients, or even predict cardiotoxicity linked to breast irradiation. For more personalized treatment strategies for each patient.
In addition, these algorithms are used to better understand tumors, for example based on their molecular characteristics. The objective for researchers in the coming years is to identify the phenotypes of tumors (set of characteristics) from precise images, particularly in 3 D (MRI, scanner) which complement the anatomopathological analyzes (tissue analysis). And thus, example among others, to understand resistance to treatment by immunotherapy.
To find out more: The IHU Women’s Cancer Institute is a project which brings together the Institut Curie, the University of Paris Sciences et Lettres and Inserm, for comprehensive care for women affected by breast and breast cancer. gynecological.
LED in toys: why do we need to review European standards?
Source: Destination Santé
