As reported by BGR, researchers from the Netherlands Cancer Institute, in collaboration with Robovision Healthcare, have unveiled a new system called BrainMets.ai. This system employs artificial intelligence (AI) to detect metastases in the brain. A study published in the journal Radiology revealed that this technology exhibits impressive accuracy, particularly for microtumors that often evade detection during standard MRI scans.

Brain metastases are the most common type of central nervous system tumors, occurring in approximately 17% of adult cancer patients. The challenge lies in the fact that these tumors typically have a diameter of less than 3 mm, making them difficult to identify even with multiple MRI images.

BrainMets.ai achieved a sensitivity of 97.4% for detecting lesions overall. For tumors larger than 12 mm, the accuracy was 100%, for sizes 6–12 mm it was 98%, 3–6 mm was 97.9%, and for tumors smaller than 3 mm, it was 93%.

“This technology represents a significant advancement. It enhances confidence in detecting even the smallest lesions, allowing doctors to make more timely and accurate treatment decisions,” stated Dr. Lawrence Topff, a neuroradiologist at the Netherlands Cancer Institute and clinical lead of the project.

It should be noted that this technology is not intended to replace medical professionals but aims to expedite the diagnostic process and reduce the risk of missed cases. The developers emphasize that the quality of training data used for AI was a crucial factor in achieving accuracy. Thanks to carefully selected data, precise annotations, and an optimized neural network architecture, such remarkable results were obtained.