Can AI fake a cell image well enough to fool a lab expert?
NCT ID NCT06542783
First seen Sep 10, 2026 · Last updated Sep 11, 2026 · Updated 1 time
Summary
Researchers want to know whether computer-generated images of ANA Hep-2 cells look real enough to pass as genuine microscope pictures. They ask 300 experienced lab professionals from multiple medical centers to judge a mix of real and AI-made images and to identify the cell patterns. The study also checks whether seeing AI suggestions changes how accurately those professionals read the patterns.
What this could mean
Our plain-language read of the trial. This is informational only, not medical advice or a prediction.
- Active substance
- AI-generated ANA cell images used as a reading aid
- What this could lead to
- If the images pass as real, labs could use them to train staff and test diagnostic tools without needing as many patient samples. If AI help sharpens pattern reading, autoimmune test results could become more consistent across hospitals.
- What could go wrong
- This is an observational study with 300 lab professionals, so it measures perception and reading accuracy, not whether patients get better diagnoses. AI-generated images may look convincing yet still miss the biological details that matter, and AI suggestions could bias readers rather than help them.
This is an AI summary of the original study and may miss details. Read our disclaimer.
Study facts
What this study's own registry entry says, in plain language.
- Participants
-
About 300 people
The number the study aims to enrol. It can still change while the study runs.
- Started
-
May 2025
- Expected to finish
-
Jan 2029
An estimate. End dates often move.
- Lead sponsor
-
Other sponsor
The registry's catch-all category, for sponsors it does not file as a company, a government agency, or a research network.
Who can take part
This study's own entry requirements. Only the study team can say for certain whether you qualify.
Who is studied
We are recruiting cytopathologists from clinical laboratories in multiple medical institutions worldwide who specialize in interpreting anti-nuclear antibody (ANA) patterns to participate in a visual Turing test.
- Ages
-
Children (under 18), adults (18 to 64) and older adults (65 and over)
- Sex
-
Anyone
- Healthy volunteers
-
Accepted
You do not need to have the condition being studied to take part.
Show the full entry requirements Hide the full entry requirements
Copied word for word from the study's registry entry, so the wording is the study team's rather than ours.
Inclusion Criteria: * Originating from reputable medical institutions * Possessing relevant certification and qualifications * Having over one year of experience in interpreting anti-nuclear antibody (ANA) patterns within a laboratory setting Exclusion Criteria: * Lacking relevant professional certification and qualifications * Without experience in interpreting ANA patterns * Unwilling to accept the rules and informed consent of the visual Turing test
Get updates
Get notified about this study
Sign up to get updates when this study changes or when new studies for Anti-nuclear antibody are added.
By submitting, you agree to our Terms of use
Conditions
The condition(s) this trial relates to.
As listed by the trial registrant
The condition terms exactly as the trial's registrant entered them.
Contacts and locations
Locations
-
Department of Clinical Laboratory, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
Shanghai, Shanghai Municipality, 200092, China
More trials for these conditions
Other studies related to the condition(s) this trial covers.
- Can AI help doctors hear hidden heart defects in children?
- Can AI read skin biopsies as well as expert pathologists?
- Can AI match the human eye for perfect tooth shades?
- AI and ultrasound join forces to detect hidden muscle decline in the ICU
- Can an AI trained on real heart patients outsmart generic chatbots?
- Can a computer spot a gummy smile as well as a dentist?