All algorithms
Particle picking
Stage
1
of 8
Included on all plans
Contamination Segmentation
Ice contamination and carbon edges detected and masked during picking, so junk never enters the particle stack.
Automatic
No regions drawn by hand
Ice and carbon
Contamination and foil edges, per micrograph
What it does
Real grids are not clean. Crystalline ice, aggregates and the edges of the foil all produce high contrast, and high contrast is exactly what a picker is drawn to. Left alone these become false picks that carry through classification and cost time at every later stage.
CryoCloud detects those regions during picking and masks them out, so no picks are made inside them.
How it works
Detection works by region rather than by particle: instead of asking where the particles are, it asks which parts of this micrograph are not usable specimen. The Picker automatically detects both ice contamination and foil hole edges, and excludes particles from those areas.
This way, less junk ends up in particle stack making downstream processing more efficient.
Measured data examples. Regions of ice contamination or foilhole are outlined and filled by the mask. Particles outside them are picked, particle inside are excluded.
Where it sits
It runs as part of the Picker, near the start of the workflow, where removing bad data is cheapest. In the interface it is the option to exclude contaminated regions.
Junk that still gets through is caught downstream by 2D and/or 3D classification.
At a glance
Stage
Particle picking
Runs
Automatically, with picking
Hardware
GPU
Inputs
Motion-corrected micrographs
Outputs
Masked regions per micrograph
Areas the picker treats as out of bounds, with contamination area available as a filter.
Replaces
Availability
Included
Contamination is masked on every dataset you process.
Put this algorithm to work
See the full system around the workflow step, then choose the right way to get started.
TECHNOLOGY OVERVIEW
Explore all algorithms
Browse the complete analysis workflow, from pre-processing to refinement.
View algorithm overview
PLAN WITH CONFIDENCE
See what’s included
Compare plans, compute, and storage with transparent costs for every workflow.
Explore pricing
SEE YOUR DATA FLOW
Book a guided demo
Talk through your data, workflows, and deployment needs with a CryoCloud specialist.
Book a demo
Next in the workflow
Particle picking
CryoCloud Picker
Generalised ML particle picker with higher accuracy, no per-dataset training.
2D classification
AutoClass2D
Automated reference-based 2D class selection, no manual class picking.
Pre-processing
Patch-based CTF Estimation
Patch-based estimation with local defocus per micrograph.