Skip to content
JournalsWorldThe Global Research Discovery Platform
Featured Dataset

COVID-19 CT Pulmonary Parenchyma Image Database

This repository contains computed tomography (CT) images, segmentation masks, and classification results developed for automatic pulmonary parenchyma identification and ground-glass opacity (GGO) and pulmonary infiltrate (PI) segmentation in patients diagnosed with COVID-1

👤
CreatorTello Mijares, Santiago
📅
Published2026-05-13
🔗
DOI10.5281/zenodo.20149877
📊
Downloads14
⚖️
Licensecc-by-4.0
File Size44.9 MB
Data TypeDataset
Published2026
Licensecc-by-4.0
Total Views37
Total Downloads14

This repository contains computed tomography (CT) images, segmentation masks, and classification results developed for automatic pulmonary parenchyma identification and ground-glass opacity (GGO) and pulmonary infiltrate (PI) segmentation in patients diagnosed with COVID-19.

 

Repository Contents

Contains:

  • pulmonary parenchyma segmentation images,
  • ground-glass opacity (GGO) segmentation images,
  • pulmonary infiltrate (PI) segmentation images,
  • quantitative classification results.

All segmentation images are provided in BMP format.

 

Dataset Characteristics

  • Imaging modality: Computed Tomography (CT)
  • Disease: COVID-19
  • Targets:
    • Pulmonary parenchyma
    • Ground-glass opacity (GGO)
    • Pulmonary infiltrates (PI)
  • Image format: BMP

 

The images provided in this dataset were generated in:

TELLO-MIJARES, Santiago; WOO, Luisa. Computed Tomography Image Processing Analysis in COVID‐19 Patient Follow‐Up Assessment. Journal of Healthcare Engineering, 2021, vol. 2021, no 1, p. 8869372.

📤 Share this page

Found this useful? Share it with your network.

✓ Link copied! Paste it on ResearchGate / Academia.edu
📦
COVID-19 CT Pulmonary Parenchyma Image Database (Full Dataset)44.9 MB
⬇
📄
ReadmeVia DOI record
↗

Files are hosted on the source repository. Click download to access the full dataset.

Tello Mijares, Santiago (2026). COVID-19 CT Pulmonary Parenchyma Image Database. https://doi.org/10.5281/zenodo.20149877