EPFL researchers created an AI-driven microscopy system that predicts and analyzes misfolded protein aggregation in real time.
Key Details
- 1Developed a self-driving imaging system combining multiple microscopy methods and deep learning.
- 2System predicts and detects protein aggregation—a hallmark of neurodegenerative diseases—in living cells.
- 3Uses label-free microscopy to minimize sample alteration and maximize imaging efficiency.
- 4Upon aggregation detection, system triggers Brillouin microscope to analyze biomechanical properties of aggregates.
- 5Aggregation onset detection achieved 91% accuracy using a specialized deep learning algorithm.
- 6Published in Nature Communications, with potential impact on drug discovery and precision medicine.
Why It Matters
This work showcases how AI-driven, label-free imaging can reveal dynamic, disease-relevant cellular processes in unprecedented detail, opening new pathways for diagnostic research and drug development in neurodegenerative diseases.
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
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.
•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.