A new artificial intelligence (AI) model developed by an international team of researchers, including scientists from McGill University, offers a groundbreaking approach to detecting metastatic brain cancer.
The AI system analyzes MRI scans to identify the spread of cancer cells into surrounding brain tissue, achieving 85% accuracy without the need for invasive surgery. These findings were published in Neuro-Oncology Advances.
The study, co-led by Dr. Matthew Dankner and Dr. Reza Forghani, involved MRI scans from over 130 patients treated at The Neuro (Montreal Neurological Institute-Hospital). All participants had undergone surgery to remove metastatic brain tumors.
To validate the AI’s results, the researchers compared its findings to what pathologists observed under the microscope. The AI demonstrated impressive precision in detecting invasive cancer cells in tissue that often appears normal with traditional imaging techniques.
Metastatic Brain Cancer and Its Challenges
Metastatic brain cancer, the most common type of brain tumor, occurs when cancer cells from other parts of the body spread to the brain. These tumors are particularly dangerous when cancer cells invade healthy brain tissue, as this makes them harder to treat and increases the likelihood of recurrence.
Current methods to determine the extent of tumor spread often require surgery, which can be risky for certain patients or impossible in cases where tumors are located deep within the brain.
The researchers emphasized the clinical importance of detecting these invasive cells. “Our previous work showed that invasive brain metastases are associated with shorter survival and higher risks of tumor regrowth,” explained Dr. Dankner. “This highlights the potential of machine learning to improve how we understand and treat cancer.”
How AI Detects Subtle Cancer Patterns
Traditional imaging methods, such as standard MRI scans, rely on radiologists to interpret visual patterns of abnormal tissue. However, these methods can miss subtle changes that indicate cancer has spread.
The new AI model identifies faint, complex patterns in the surrounding brain tissue that are often invisible to the human eye. These patterns, detected through advanced machine learning, suggest the presence of invasive cancer cells.
Dr. Forghani, who developed the AI model during his tenure at McGill and the University of Florida, noted that the technology goes beyond standard imaging capabilities. “The AI identifies changes that even experienced clinicians might overlook, giving us a new tool to evaluate the spread of cancer with remarkable accuracy.”
Potential Impact on Cancer Treatment
In addition to offering earlier and more precise detection, the AI model could pave the way for more personalized treatments.
Earlier this year, the same team identified potential drugs for treating brain metastases, but determining which patients would benefit from these treatments requires knowing whether the cancer has spread into surrounding tissue. The AI model could help doctors make such decisions without requiring invasive procedures.
Surgery remains the primary method for assessing and treating brain metastases. However, surgery is not always feasible for patients with tumors in hard-to-reach areas or for those with poor overall health.
The AI model could serve as a valuable alternative in these cases, enabling more patients to receive timely and effective treatment.
Looking Ahead
While the research is still in its early stages, the team plans to expand their work by using larger datasets and refining the AI model to make it suitable for clinical use.
“With further development, this technology could be integrated into routine clinical practice, helping us catch the spread of cancer within the brain earlier and more accurately,” said Dr. Benjamin Rehany, a Radiology Resident at the University of Toronto and a lead author of the study.
The researchers are optimistic that this AI-driven approach could transform cancer diagnosis and treatment, reducing the reliance on invasive procedures and improving outcomes for patients with metastatic brain cancer.
As the technology evolves, it has the potential to become a powerful tool in the fight against one of the most challenging forms of cancer.
For more information about cancer, please see recent studies that plant-based diets may reduce risk of colorectal cancer in men, and Low-fat diet may help stop cancer growth.
For more information about cancer, please see recent studies about How to harness the power of anti-cancer foods and supplements and results showing that Empower your plate: cancer-fighting foods and recipes.
The research findings can be found in Neuro-Oncology Advances.
Copyright © 2025 Knowridge Science Report. All rights reserved.
