Realistic in Generation of HEp-2 Cell Images Using Latent Diffusion Models: a Multi-center Visual Turing Test

Launched by XINHUA HOSPITAL, SHANGHAI JIAO TONG UNIVERSITY SCHOOL OF MEDICINE · Aug 2, 2024

Keywords

ClinConnect Summary

This clinical trial is focused on improving the way we analyze certain images that are important for diagnosing autoimmune diseases. Specifically, it looks at how using advanced artificial intelligence techniques, called latent diffusion models, can help create clearer and more diverse images of anti-nuclear antibodies (ANA) found in a type of test called Hep-2 cell immunofluorescence. The main goal is to see if these models can make the images better, which might help doctors be more accurate and efficient in diagnosing diseases.

To participate in this trial, individuals must have relevant qualifications and at least one year of experience interpreting ANA patterns in a laboratory. Those who do not have the necessary certifications or experience, or who are not willing to follow the rules of the study, will not be eligible. While the trial is not yet recruiting participants, it is an important step toward enhancing the quality of diagnostic images, ultimately aiming to improve healthcare outcomes for patients.

Gender

ALL

Eligibility criteria

• 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