Back to all news
AI-Enhanced Microfluidic Chip Enables Label-Free Detection of Circulating Tumor Cells
Researchers developed a microfluidic chip and AI system that accurately isolates and identifies rare circulating tumor cells (CTCs) from blood without fluorescent labeling.
Key Details
- 1The platform uses contraction-expansion inertial microfluidics to separate CTCs based on size differences from blood cells.
- 2Identification of enriched tumor cells is performed with the YOLOv8 deep learning model using standard bright-field microscope images.
- 3The system achieved an MCF-7 cell recovery rate of 89.2±3.1% and a white blood cell removal rate of 86.9±1.4%.
- 4YOLOv8 attained 96% accuracy, 94.6% precision and recall, and 95.4% specificity in recognizing tumor cells.
- 5The method eliminates the need for cell-surface marker labeling or fluorescent staining.
- 6Validation was conducted on artificial blood samples, with future studies planned for patient samples.
Why It Matters
This research exemplifies how combining microfluidics with deep learning can significantly improve rare cell detection workflows without needing complex labeling, which could translate into simpler, more robust pathology and liquid biopsy diagnostics for oncology and beyond.
Source
EurekAlert
Related News
•EurekAlert
Metasurface Device Enables Real-Time Optical Differentiation and High-Resolution Imaging
Researchers introduced a metasurface optical differentiator that performs real-time, high-resolution imaging and differentiation in a single-layer device.
•EurekAlert
AI Model Predicts Glioblastoma Recurrence Sites Using Imaging
An AI tool using stimulated Raman histology can predict sites of glioblastoma recurrence before they appear on MRI.
•EurekAlert
Mayo Clinic AI Model Predicts Pancreatic Cancer Risk Years Before Diagnosis
An AI model developed at Mayo Clinic accurately predicts pancreatic cancer risk up to three years before diagnosis using longitudinal health data.