An Interpretable Fundus Diseases Report Generating System Based On Weakly Labelings

Launched by ZHONGSHAN OPHTHALMIC CENTER, SUN YAT-SEN UNIVERSITY · Apr 5, 2025

Keywords

ClinConnect Summary

This clinical trial is focused on developing a new system to help doctors better understand and report on various eye diseases, especially those affecting the retina, like diabetic retinopathy and age-related macular degeneration. The goal is to create a program that can analyze different types of eye images and automatically generate reports that highlight important features of these diseases. By doing this, researchers hope to find new ways to predict how these conditions progress and improve treatment options for patients.

To participate in this trial, individuals will need to have undergone certain eye examinations between January 2011 and December 2023. This includes images and reports from various tests, regardless of their clarity or completeness. People with clear imaging and reports, as well as those with some quality issues, may also be included. However, images with major quality problems or missing key information will be excluded. While the trial isn't currently recruiting participants, it's an exciting step towards improving care for those with retinal diseases by using advanced technology to enhance diagnosis and treatment planning.

Gender

ALL

Eligibility criteria

• Inclusion Criteria:
• • Disease group: All multimodal fundus examination images containing fundus lesions, examined from January 2011 to December 2023, including fundus photography, as well as OCT, OCTA, FFA, ICGA, B-ultrasound and corresponding imaging reports. Images could be either clear or unclear, reports are either complete or incomplete.
• • Normal group: All multimodal fundus examination images without fundus lesions, examined from January 2011 to December 2023, including fundus photography, as well as OCT, OCTA, FFA, ICGA, B-ultrasound and corresponding imaging reports. Images could be either clear or unclear, reports are either complete or incomplete.
• Exclusion Criteria:
• • Disease group: 1. The image has serious quality problems; 2. The diagnostic report lacks key information.
• • Normal group: 1. The image has serious quality problems; 2. The diagnostic report lacks key information.