Download Your Application Note
"*" indicates required fields
We respect your inbox. You can unsubscribe at any time. View our privacy policy.
Inside this application note
See how episcopic brightfield microscopy paired with NIS-Elements AI learning enables label-free prediction of Quick-Neuron™ iPSC-derived neuron distribution on MaxOne HD-MEA chips, eliminating the need for fixation or staining prior to electrophysiology testing.
- An AI model trained on just 10 episcopic brightfield images — using calcein fluorescence as ground truth — achieved a training loss of 0.129 after 1,000 iterations, successfully predicting cell regions in a held-out test image.
- The AI-predicted image identified 73% of the 2,067 calcein-stained cells, corresponding to 80% of the 1,886 cells the model itself detected, demonstrating close agreement between predicted and fluorescence-confirmed cell distributions.
- Because HD-MEA chips block transmitted light and prevent phase contrast imaging, this episcopic brightfield plus AI approach enables noninvasive assessment of viable cell seeding density before electrophysiology experiments begin.
Related Resources
Explore related cell models, services, and protocols connected to this application.
Contact Us
Have a question about our products, services, or custom projects? Our team is here to help—reach out and we’ll get back to you as soon as possible.
Subscribe
Sign up to our eNewsletter to stay up to date with the latest product launches, promotions, and receive expert tips.
By signing up you are agreeing to our Privacy Policy