The use of AI in brain cancer diagnosis, monitoring and treatment

The recommendations aim to modernize clinical practices and ensure reliable clinical trial results, as well as patient safety, by utilizing artificial intelligence (AI) to diagnose, monitor, and treat brain cancer patients. 

These guidelines were crafted by an international, multidisciplinary team of researchers and clinicians and represent an update to current diagnostic standards. At present, tumor size is typically measured by individual radiologists, which directly informs treatment decisions. However, this subjective approach can lead to inconsistent results and varying treatment strategies depending on the radiologist interpreting the scans. 

Spyridon Bakas, lead author of the second policy review and professor at Indiana University School of Medicine, explains: "We can use AI to look at images of the tumors more objectively." AI programs can quickly determine the type of tumor, its subtype, and its grade, as well as track the tumor’s progression during treatment. This could lead to more accurate diagnoses and consistent treatment plans. 

The guidelines provided by the expert team include several key recommendations: 

• Use AI software developed with large, diverse patient datasets. 

• Ensure that AI models for tumor definition follow World Health Organization (WHO) criteria. 

• Consider how tumor images are acquired, processed, and segmented before analysis. 

Thomas Booth, co-author from King’s College London, states, "These guidelines are critical for ensuring that AI tools developed in the U.K. and beyond meet rigorous standards and improve patient outcomes." 

While these guidelines are among the first in the world regarding AI's use in cancer care, further research is needed. Bakas underscores: “It is important that we continue our study of these AI models on large, diverse patient populations to continue extending our understanding of disease and improving the way we use them.” 

MEDICA-tradefair.com; Source: Indiana University