A research team from the Netherlands Cancer Institute, in collaboration with Robovision Healthcare, has introduced an innovative platform called BrainMets.ai, which utilizes artificial intelligence to detect brain metastases. According to findings published in the journal Radiology, this technology has demonstrated impressive accuracy, particularly in the case of microtumors that often go unnoticed during standard MRI scans.

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

BrainMets.ai achieved an overall sensitivity of 97.4% in detecting lesions. For tumors larger than 12 mm, accuracy reached 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 represents a significant advancement. It increases confidence in identifying even the smallest lesions, helping physicians make more timely and accurate treatment decisions,” said Dr. Lawrence Topp, a neuroradiologist at the Netherlands Cancer Institute and clinical lead of the project.

It is important to note that 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 training data on which the AI is trained plays a crucial role in accuracy. Thanks to carefully selected data, precise annotations, and optimized neural network architecture, such high performance results have been achieved.