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
NIH-Backed AI Model Predicts Cancer Survival Using Single-Cell Data
Researchers have developed scSurvival, a machine learning tool that uses single-cell tumor data to accurately predict cancer patient survival and identify high-risk cell populations.
•EurekAlert
Deep Learning Pathomics Platform Improves Immunotherapy Prediction in Lung Cancer
A deep learning pathomics platform accurately predicts immunotherapy response in metastatic NSCLC using routine pathology slides.
•EurekAlert
AI Pathology Model Outperforms PD-L1 in Predicting NSCLC Immunotherapy Response
MD Anderson's Path-IO machine learning platform accurately predicts immunotherapy responses in metastatic non-small cell lung cancer, surpassing current biomarker standards.