Researchers from the Netherlands Cancer Institute, in collaboration with Robovision Healthcare, have unveiled a groundbreaking tool — BrainMets.ai. This system utilizes artificial intelligence to detect metastases in the brain. Findings published in the journal Radiology indicate a high level of accuracy for the technology, especially in cases of microtumors that often go unnoticed during standard MRI scans.

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

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

"This technology is a significant advancement. It enhances confidence in detecting even the smallest lesions, enabling physicians to make more timely and accurate treatment decisions," stated Dr. Lawrence Topp, a neuroradiologist at the Netherlands Cancer Institute and clinical lead of the project.

Notably, this technology is not intended to replace healthcare professionals but aims to expedite the diagnostic process and reduce the risk of missed cases. According to the developers, the quality of the training data used to train the AI was a crucial factor in achieving accuracy. Through carefully selected data, precise annotations, and optimized neural network architecture, such high-performance results were attained.