DGIST researchers developed a deep learning model that classifies lung cancer exosomes based on physical properties measured by atomic force microscopy.
Key Details
- 1DGIST team used AFM to measure nanomechanical properties (stiffness, height-to-radius) of exosomes from NSCLC cell lines with different genetic mutations.
- 2AI model (DenseNet-121) classified exosomes by origin, achieving 96% accuracy and AUC of 0.92.
- 3Exosome stiffness reflected KRAS and EGFR mutations in their respective lung cancer cell lines.
- 4The method enables high-precision, label-free, liquid biopsy-based lung cancer diagnosis.
- 5Study published July 8, 2025, in Analytical Chemistry.
Why It Matters
This approach could offer a rapid, non-invasive way to diagnose lung cancer genetic mutations, reducing the need for tissue biopsies. Leveraging AI with nanomechanical imaging pushes boundaries in early cancer detection and personalized medicine.
Source
EurekAlert
Related News
•EurekAlert
MD Anderson Unveils New AI Genomics Insights and Therapeutic Advances
MD Anderson reports breakthroughs in cancer therapeutics and provides critical insights into AI models for genomic analysis.
•EurekAlert
UCLA Researchers Present AI, Blood Biomarker Advances at SABCS 2025
UCLA Health researchers unveil major advances in breast cancer AI pathology, liquid biopsy, and biomarker strategies at the 2025 SABCS.
•EurekAlert
SH17 Dataset Boosts AI Detection of PPE for Worker Safety
University of Windsor researchers released SH17, a 8,099-image open dataset for AI-driven detection of personal protective equipment (PPE) in manufacturing settings.