An international team developed M-PACT, an AI-powered tool, to classify pediatric brain tumors using liquid biopsy samples with high accuracy.
Key Details
- 1M-PACT uses AI to classify brain tumors from small amounts of circulating tumor DNA in cerebrospinal fluid.
- 2Achieved 92% accuracy in benchmarking tests for classifying brain tumors.
- 3Applicable for diagnosis, monitoring treatment response, and identifying recurrences or secondary malignancies.
- 4Utilizes deep neural network trained on over 5,000 DNA methylation profiles across ~100 tumor types.
- 5Provides new insights into tumor microenvironment by analyzing cell-type contributions.
- 6Published in Nature Cancer by a collaboration led by St. Jude Children's Research Hospital.
Why It Matters
This advance enables less invasive, highly accurate classification of pediatric brain tumors, helping personalize and improve treatment while lowering the need for surgical biopsies. The AI framework could extend to other cancers, signaling a major shift in molecular cancer diagnostics.
Source
EurekAlert
Related News
•EurekAlert
AI Framework Accelerates Aortic Aneurysm Risk Prediction from Imaging
Researchers developed BioPINN-LM, combining physics-informed neural networks and multimodal large language models to deliver fast, interpretable risk assessments for ascending thoracic aortic aneurysms.
•EurekAlert
Study Finds Patient Voices Missing in Generative AI Design for Oncology
A Flinders University-led review found patients and carers are rarely involved in shaping generative AI tools used in oncology.
•EurekAlert
Scripps Researchers Develop AI Foundation Model for ECG-Based Heart Disease Prediction
A new AI foundation model, ECG-CLIP, improves detection and prediction of multiple heart diseases using large-scale ECG and clinician note data.