🚀 We're looking for ML Engineers and Medical Reviewers! Join the OpenPHR Mission →
Back to Marketplace
Dataset

LIDC-IDRI

Radiology / CT Scan Oncology / Pulmonology Creative Commons Attribution 3.0 (CC BY 3.0) De-identified / TCIA Hosted
N/A GitHub Stars
N/A Open Issues
N/A Docker Support
N/A Last Updated

Technical Summary

The Lung Image Database Consortium image collection (LIDC-IDRI) consists of diagnostic and lung cancer screening thoracic computed tomography (CT) scans with marked-up annotated lesions.

Key Capabilities

  • Comprehensive Imaging: Includes 1,018 clinical thoracic CT scans from 1,010 patients, acquired from seven distinct academic centers to ensure vendor and scanner variability.
  • Multi-Reader Annotations: Each scan was reviewed by four experienced thoracic radiologists in a blinded and unblinded reading process. The resulting XML files include precise spatial coordinates for lung nodules.
  • Standardized Diagnostic Criteria: Nodule characteristics (e.g., subtlety, internal structure, calcification, spiculation) are graded by each radiologist, providing rich metadata for advanced predictive modeling.

Usage in Healthcare

LIDC-IDRI is considered the international gold standard dataset for lung nodule detection and classification. Machine learning researchers use this dataset to train models that can assist radiologists in identifying malignant pulmonary nodules early, reducing diagnostic oversight in screening programs.

Model Card Details

Architecture

N/A

Intended Use Cases

Training, testing, and validation of computer-aided diagnosis (CAD) methods for lung cancer detection.