EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Refined IDRiD: An Enhanced Dataset for Diabetic Retinopathy Segmentation with Expert-Validated Annotations and Comprehensive Anatomical Context

Sakon Chankhachon, Supaporn Kansomkeat, Patama Bhurayanontachai, Sathit Intajag

Data · 01.02.2026 · 11 (2) · 30

DOI: 10.3390/data11020030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data, online erschienen am 01.02.2026. Verfasst von Sakon Chankhachon und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSRF via the Program Management Unit for Human Resources & Institutional Development, Research and Innovation, Thailand’s Education Hub for the Southern Region of ASEAN Countries for Ph.D. Students.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Indian Diabetic Retinopathy Image Dataset (IDRiD) has been widely adopted for DR lesion segmentation research. However, it contains annotation gaps for proliferative DR lesions and labeling errors that limit its utility for comprehensive automated screening systems. We present Refined IDRiD, an enhanced version that addresses these limitations through (1) expert ophthalmologist validation and correction of labeling errors in original annotations for four non-proliferative lesions (microaneurysms, hemorrhages, hard exudates, cotton-wool spots), (2) the addition of three critical proliferative DR lesion annotations (neovascularization, vitreous hemorrhage, intraretinal microvascular abnormalities), and (3) the integration of comprehensive anatomical context (optic disc, fovea, blood vessels, retinal region). A team of three ophthalmologists (one senior specialist with >10 years’ experience, two expert fundus image annotators) conducted systematic annotation refinement, achieving an inter-rater agreement F1-score of 0.9012. The enhanced dataset comprises 81 high-resolution fundus images with pixel-level annotations for seven DR lesion types and four anatomical structures. All images were cropped to the retinal region of interest and resized to 1024 × 1024 pixels, with annotations stored as unified grayscale masks containing 12 classes enabling efficient multi-task learning. Refined IDRiD enables training of comprehensive DR screening systems capable of detecting both non-proliferative and proliferative stages while reducing false positives through anatomical context awareness.

Förderung

  • NSRF via the Program Management Unit for Human Resources & Institutional Development, Research and Innovation
  • Thailand’s Education Hub for the Southern Region of ASEAN Countries for Ph.D. Students

Zitieren

APA

Chankhachon, S., Kansomkeat, S., Bhurayanontachai, P., & Intajag, S. (2026). Refined IDRiD: An Enhanced Dataset for Diabetic Retinopathy Segmentation with Expert-Validated Annotations and Comprehensive Anatomical Context. Data, 11(2), 30. https://doi.org/10.3390/data11020030

Vancouver

Chankhachon S, Kansomkeat S, Bhurayanontachai P, Intajag S. Refined IDRiD: An Enhanced Dataset for Diabetic Retinopathy Segmentation with Expert-Validated Annotations and Comprehensive Anatomical Context. Data. 2026;11(2):30. doi:10.3390/data11020030

BibTeX
@article{Chankhachon2026,
  author = {Chankhachon, Sakon and Kansomkeat, Supaporn and Bhurayanontachai, Patama and Intajag, Sathit},
  title = {Refined IDRiD: An Enhanced Dataset for Diabetic Retinopathy Segmentation with Expert-Validated Annotations and Comprehensive Anatomical Context},
  journal = {Data},
  year = {2026},
  volume = {11},
  number = {2},
  pages = {30},
  doi = {10.3390/data11020030}
}
Kostenlos starten →