VisionSort
Morphology based cell sorting using AI
Overview
Visionsort™ combines traditional fluorescence flow cytometry with high-dimensional morphological profiling and AI to enable label-free cell sorting and unbiased single cell profiling.
Dual Mode Sorting
- Label-Free and Fluorescence Based
- Gentle sorting mechanism
High Resolution
- High dimensional ‘cellular fingerprints’ based on scattered light profiles
- <1 um cellular resolution
High Throughput
- Cell sorting at 3,000 eps
- Fully closed system
User Driven AI
- Supervised and unsupervised machine learning
- Intuitive UI
VisionSort Powered by Ghost Cytometry
Label-free, high throughput cell characterization and isolation based on high-resolution morphology and artificial intelligence.
How Ghost Cytometry works?
A. Profile Acquisition
Cells pass through a structured illumination and morphological profiles are collected as high-dimensional temporal waveforms with a single pixel detector.
C. Sorting
The classified cells are gently isolated using fluid pressure.
B. AI-based Classification
A trained AI model predicts the cell class based on the waveform.
Applications
Cell Therapy
Label-free Monitoring and Isolation of Target Cells
- Label-free immune cell sorting
- Select therapeutically relevant cells
- C and GT manufacturing QC
Drug discovery
Phenotypic screening unleashed by morphology
- Faster, cheaper alternative to plate-based phenotypic screening
- Screen a wider range of phenotypes
- Compatible with small molecule & CRISPR-based approaches
Disease Profiling
High-resolution single cell profiling and analysis by AI to identify morphotypic changes in disease
- Disease insight.....with AI
- Novel biomarker discovery, uncover novel cell populations, ID new targets, disease characterization, MRD, patient stratification
Laser free morphological profilingCellular fingerprints reflecting morphology
Standard 3-laser fluoresence4 label-free morphometric measures and 1 high resolution spatial fluorescence measure
AL-driven cell classificationSupervised and unsupervised machine learning approaches
Gentle sorting mechanismMinimum call damage, maximize viable cell recovery
