Anterior Segment Measurement Dataset Using Ultrasound Biomicroscopy Image Analysis
- Journal
- Translational vision science & technology (Q1)
- Published
- 3 August 2026
- Study design
- Case-control study
- Evidence level
- Level 3, Low (CEBM 3b)
- Authors
- Taylor Kolosky, He Eun Forbes, Moran R Levin, Camilo Martinez, William P Madigan, Janet L Alexander
- PMID
- 42635484
- DOI
- 10.1167/tvst.15.8.19
Why clinicians should know about it
- Picked for Anatomy (paper of the day, 27 August 2026): Anterior segment UBM dataset for ocular anatomy
Abstract
PURPOSE: The purpose of this study was to provide a comprehensive, quantitative dataset of anterior segment (AS) parameters obtained from ultrasound biomicroscopy (UBM) images to support research in ocular development, disease characterization, and image-based analysis. METHODS: UBM images were prospectively collected from 185 eyes of 138 participants aged 3 weeks to 26 years (median = 17 months), encompassing diagnoses such as healthy controls, primary congenital glaucoma (PCG), glaucoma following cataract surgery (GFCS), congenital cataract, traumatic cataract, Lowe syndrome, and Sturge-Weber syndrome (SWS)-associated glaucoma. Twenty-seven quantitative AS parameters were measured from deidentified images using ImageJ software following a standardized protocol. RESULTS: The resulting dataset includes demographic and diagnostic metadata paired with quantitative UBM-derived parameters for each eye. The dataset is provided in comma-separated value (CSV) format with an accompanying data dictionary. CONCLUSIONS: This dataset provides one of the most extensive collections of quantitative pediatric AS measurements obtained by UBM, enabling characterization of age- and disease-related anatomic variation and facilitating reproducible secondary analyses. TRANSLATIONAL RELEVANCE: This open-source pediatric UBM dataset establishes a foundation for studies of ocular growth, disease mechanisms, and surgical planning, and provides a valuable resource for the development and validation of automated image analysis and machine learning models in pediatric AS imaging.
Abstract as published, via PubMed.
For healthcare professionals. The summary is generated by AI from the published abstract, and the evidence level is assigned automatically from the study design on the Oxford CEBM hierarchy. Neither is medical advice. Read the full paper before changing practice.