AI-Powered Liquid Biopsy Shows Promise for Early Brain Cancer Detection

A new generation of liquid biopsy technology, fueled by artificial intelligence (AI) and nanosensors, is offering a potential breakthrough in the early detection and classification of brain tumors. These advancements promise to overcome the challenges of traditional diagnostic methods, which often require invasive procedures and may not detect subtle changes indicative of early-stage cancer.

The Challenge of Brain Cancer Diagnosis

Diagnosing brain cancer is notoriously difficult. The blood-brain barrier, a protective mechanism that prevents harmful substances from entering the brain, also hinders the passage of cancer cells and genetic material into the bloodstream. This makes traditional liquid biopsies – which analyze circulating tumor DNA (ctDNA) in blood – less effective for brain tumors compared to other cancers. Conventional diagnosis often relies on invasive biopsy procedures, which carry risks and may not always be representative of the entire tumor.

How AI and Nanosensors are Changing the Game

Researchers at Memorial Sloan Kettering Cancer Center (MSK) have developed an ultrasensitive diagnostic test that combines artificial intelligence (AI) with sensors made of carbon nanotubes to potentially detect and classify different types of brain tumors with 98% accuracy . The technology focuses on detecting alterations in proteins and other molecules in the blood that change in response to the presence of a brain tumor.

“The nanosensors detected changes in molecules in the blood, not just from the brain tumor cells, but also from the surrounding tissues and from the immune system throughout the body — the combination known as the tumor ecosystem,” explains Dr. Daniel Heller, head of the Cancer Nanomedicine Laboratory at MSK .

This approach differs from many existing liquid biopsies that primarily focus on detecting DNA from tumor cells. By analyzing the “tumor ecosystem” – including the tumor itself, surrounding tissues and the immune system – the new technology can provide a more comprehensive picture of the cancer.

New Biomarker Discovery

The research, published in Nature Nanotechnology , has also led to the identification of previously unknown cancer-associated protein biomarkers. These newly discovered factors, along with previously known biomarkers, are detected by the nanosensors and contribute to the AI’s ability to accurately identify and classify tumors.

AI Advances in Pediatric Brain Tumor Classification

Beyond adult brain cancers, AI is also making strides in pediatric oncology. Scientists at St. Jude Children’s Research Hospital, in collaboration with international partners, have created Methylation-based Predictive Algorithm for CNS Tumors (M-PACT) . This AI-powered resource analyzes ctDNA in cerebrospinal fluid to molecularly classify pediatric brain tumors based on their DNA methylation patterns.

M-PACT demonstrated 92% accuracy in identifying brain tumors in a benchmarking test and can also differentiate between tumor relapse and secondary tumors, as well as track a cancer’s response to treatment .

Broader Implications and Future Directions

These advancements in AI-powered liquid biopsies hold significant promise for improving brain cancer diagnosis, treatment, and monitoring. The non-invasive nature of these tests could reduce the need for risky surgical biopsies, although the ability to detect tumors earlier and classify them more accurately could lead to more personalized and effective treatment strategies.

Researchers are also exploring the potential of these technologies to monitor treatment response and detect early signs of recurrence, ultimately improving outcomes for patients with brain cancer. A similar AI-based liquid biopsy approach is also showing promise in detecting brain cancer in general .