This demo is for research & educational use only — not a medical device. Read full disclaimer.

AI-Based biological cells (RGC) / Materials grain size analysis

Upload a fluorescence microscopy image (e.g., RGC / nuclei / cells) or a granular / microstructure image (SEM, TEM, metallography, powders, nanocrystalline materials, stones, rice, wheat, pulses, etc.). (Last updated: 1 March 2026)

Retinal ganglion cells (RGCs) exist in all vertebrate retinas, including humans and mice. They are the output neurons that transmit visual information to the brain via the optic nerve. Quantitative analysis of RGC loss is a standard endpoint in glaucoma and optic nerve injury research.

This research demonstration supports AI-based detection, segmentation, and counting for biological cells (e.g., RGC fluorescence microscopy) and grain/particle segmentation and size statistics for materials images (e.g., SEM/TEM). Please upload only images that you are permitted to use.

0.0s
Example Input
Example retinal image for RGC analysis

Upload a retinal microscopy image containing retinal ganglion cells (RGCs).

  • Fluorescence or immunostained microscopy images of mouse retinal tissue
  • Images with visible RGC somas or nuclei
  • Sufficient contrast between labeled RGCs and background tissue

Images should be reasonably focused with adequate contrast. Severely blurred or low-contrast images may affect detection accuracy.

Example Output
Example RGC detection and counting result

The output visualization provides:

  • Detected retinal ganglion cells highlighted on the image
  • Automated RGC counting results
  • Spatial distribution of detected RGCs within the field of view

Results are provided for research and quantitative analysis only. This demonstration is not intended for clinical diagnosis or decision-making.

Materials Science / General
Materials Science

Grain/Particle size analysis.

Medical Science
Example image 2

Cell like structures.