OtherJournal of neuroengineering and rehabilitation2026

Simulation of prosthetic vision with the PRIMA system and enhancement of face representation.

Anna Kochnev Goldstein, Jungyeon Park, Yueming Zhuo and 2 others

PMID 41896965

WHAT IT FOUND

Sighted users identified emotions 48.4% accurately with image enhancements versus 25.5% without.

This software update helps prosthetic vision patients see faces by thickening features and correcting contrast, but requires testing in actual patients.

Key findings

01Enhancing images with facial landmarking and contrast correction increased emotion recognition accuracy from 25.5% to 48.4% in sighted participants.

02Response times for identifying emotions dropped from 8.17 to 6.45 seconds when using the enhanced simulation.

03The enhancements are computational and can be delivered as a software update without changing the implanted hardware.

STILL TO COME

How it was doneWhat they found

Read the rest of this summary

You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.

Already have one?

What it does not show

The study was conducted on 16 sighted individuals, not actual PRIMA patients, so it measures how well the simulation communicates information to people with normal vision, not the subjective experience of the patients. The simulator is an approximation and does not represent actual neural signal processing in the retina or brain. The exact function of contrast sensitivity loss in individual patients is unknown, requiring personalized calibration before clinical use. The hardware currently limits the fidelity of contrast adjustments to 14 discrete levels.

Declared interests

Funding was provided by the National Institutes of Health, Department of Defense, Air Force Office of Scientific Research, and The Research to Prevent Blindness.

The easy way to misread this

Do not assume these accuracy improvements reflect how well actual PRIMA patients will see faces. The study tested sighted users viewing a simulation, not the patients themselves, and the enhancements require personalized calibration to work in clinical practice.

Summarised by AI from the full paper, without a clinician reviewing it. Check it against the source before it changes what you do. Read it on PubMed →


The study

Participants
16 sighted individuals
Certainty of evidence
Low

Browse

    Cite

    Anna Kochnev Goldstein, Jungyeon Park, Yueming Zhuo, et al. Simulation of prosthetic vision with the PRIMA system and enhancement of face representation. Journal of neuroengineering and rehabilitation. 2026.

    Read the original — we summarise, we never replace the paper.