The RETA Benchmark for Retinal Vascular Tree Analysis

Topological and geometrical analysis of retinal blood vessels could be a cost-effective way to detect various common diseases. Automated vessel segmentation and vascular tree analysis models require powerful generalization capability in clinical applications. In this work, we constructed a novel ben...

Full description

Saved in:
Bibliographic Details
Published in:Scientific data 2022-07, Vol.9 (1), p.397-15, Article 397
Main Authors: Lyu, Xingzheng, Cheng, Li, Zhang, Sanyuan
Format: Article
Language:English
Subjects:
631/114/1305
692/1807/1482
692/699/3161/3164
692/700/1421
Algorithms
Automation
Benchmarking
Blood vessels
Data Descriptor
Databases, Factual
Datasets
Humanities and Social Sciences
Image processing
Image Processing, Computer-Assisted
Information processing
Medical imaging
multidisciplinary
Neural networks
Retina
Retinal Vessels
Science
Science (multidisciplinary)
Segmentation
Software
Veins & arteries
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Topological and geometrical analysis of retinal blood vessels could be a cost-effective way to detect various common diseases. Automated vessel segmentation and vascular tree analysis models require powerful generalization capability in clinical applications. In this work, we constructed a novel benchmark RETA with 81 labelled vessel masks aiming to facilitate retinal vessel analysis. A semi-automated coarse-to-fine workflow was proposed for vessel annotation task. During database construction, we strived to control inter-annotator and intra-annotator variability by means of multi-stage annotation and label disambiguation on self-developed dedicated software. In addition to binary vessel masks, we obtained other types of annotations including artery/vein masks, vascular skeletons, bifurcations, trees and abnormalities. Subjective and objective quality validations of the annotated vessel masks demonstrated significantly improved quality over the existing open datasets. Our annotation software is also made publicly available serving the purpose of pixel-level vessel visualization. Researchers could develop vessel segmentation algorithms and evaluate segmentation performance using RETA. Moreover, it might promote the study of cross-modality tubular structure segmentation and analysis. Measurement(s) Retina blood vessel • Abnormal Retinal vascular morphology • Retinal vascular tree Technology Type(s) Image Segmentation • Digital Image Analysis • Supervised Machine Learning • Computer Application • Computer-Aided Diagnosis • Image Processing • Graph-based Analysis • Neural Network
ISSN:2052-4463
2052-4463
DOI:10.1038/s41597-022-01507-y