A Dataset of Widefield Fundus Images From Patients With Birdshot Chorioretinitis and Matched Control
Clinical Snapshot
PICO Framework
| P — Population | 742 eyes with birdshot chorioretinitis and 742 age- and sex-matched healthy control eyes |
| I — Intervention | Widefield fundus photography imaging |
| C — Comparator | Healthy control eyes matched for age and sex |
| O — Outcomes | Classification accuracy for distinguishing birdshot chorioretinitis from normal eyes using deep learning models (AUC up to 0.96) |
Bottom Line
This study presents a large, standardized dataset of widefield fundus images from 742 eyes with birdshot chorioretinitis and matched controls, demonstrating high diagnostic accuracy (AUC 0.96) using deep learning classification. While the dataset size and longitudinal design are impressive strengths, the abstract lacks crucial methodological details including specific reference standard criteria, blinding procedures, and traditional diagnostic accuracy metrics. The clinical utility appears promising for supporting diagnosis of this rare inflammatory condition, particularly in tertiary centres with appropriate imaging capabilities. However, validation in independent populations and comparison with current diagnostic standards would strengthen the evidence base. Australian ophthalmologists should await full publication details and external validation before considering clinical implementation, though the approach shows potential for improving diagnostic accuracy in posterior uveitis evaluation.
Key Findings
P Value: Not reported
Effect Size: Area under ROC curve up to 0.96
Primary Outcome: Classification accuracy for distinguishing birdshot chorioretinitis from normal eyes
Nnt Or Sensitivity: Sensitivity and specificity not reported - only AUC provided
Confidence Interval: Not reported
Clinical Application
Requires widefield fundus photography capability and deep learning infrastructure - feasible in tertiary ophthalmology centres Relevant to Australian ophthalmology practice where birdshot chorioretinitis diagnosis can be challenging. Could support PBS applications for immunosuppressive therapy by providing objective diagnostic evidence. Aligns with RANZCO guidelines for posterior uveitis investigation. Patients presenting with posterior uveitis or suspected inflammatory chorioretinopathy requiring differential diagnosis
Abstract
Birdshot chorioretinitis is a rare uveitis where research is limited by the lack of large, publicly available imaging datasets. To address this gap, we present Birdshot-Wide, a standardized retinal imaging dataset comprising 5,042 widefield fundus photographs from 742 eyes with birdshot chorioretinitis (BSCR) and 1,310 images from 742 age-and sex- matched healthy eyes controls. The BSCR cohort is longitudinal, with a median follow-up of 4.31 years. Each image in the BSCR cohort was manually reviewed for quality and classified by dominant lesion subtype. To demonstrate its utility, the dataset was benchmarked on a classification task, where deep learning models trained to differentiate BSCR from control images achieved an area under the receiver operating characteristic curve of up to 0.96. This dataset, with its detailed metadata, provides a valuable resource for biomarker discovery, the development of automated diagnostic tools, and disease progression modeling.
References
- 1.Foulonneau, T., Memmi, C., Monnet, D., Brézin, A. P., & Vienne-Jumeau, A. (2026). A dataset of widefield fundus images from patients with birdshot chorioretinitis and matched control. Scientific Data. https://doi.org/10.1016/j.ajo.2021.03.059
Related Research
Indian journal of ophthalmology
Internet of things in assistive technology for people with visual impairment: A scoping review
1 Aug 2026
BMJ open ophthalmology
Screening for diabetic retinopathy with artificial intelligence in a primary care setting: a comparative cost analysis
1 Aug 2026
Science advances
Multispectral infrared-to-full-color upconversion expanding human vision
1 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service