Application of the ILO International Classification of Radiographs of Pneumoconioses to Digital Chest Radiographic Images

A NIOSH Scientific Workshop

The following content has been adapted from a presentation given at the NIOSH Scientific Workshop: Application of the ILO International Classification of Radiographs of Pneumoconioses to Digital Chest Radiographic Images.

DISCLAIMER: The findings and conclusions in these proceedings are those of the authors and do not necessarily represent the official position of the National Institute for Occupational Safety and Health (NIOSH). Mention of any company or product does not constitute endorsement by NIOSH. In addition, citations to Web sites external to NIOSH do not constitute NIOSH endorsement of the sponsoring organizations or their programs or products. Furthermore, NIOSH is not responsible for the content of these Web sites.

Acquisition and QC for classification of digital chest radiographs Group discussion and outcome

3 phase approach

• Immediate terms (<1 yr)
• Medium term (1-3 yrs)
• Long term (3-6 yrs)

Immediate term (<1 yr) Approval elements

• Acceptance criteria for equipment/facility
• IQ consistency as the key goal
• ACR guidelines as a starting point
• Equipment attributes (eg, pixel size, bit- depth, baseline performance, resolution, MTF/NPS/DQE/eDQE, speed, QC utilities, DICOM compliance, …)

Immediate term (<1 yr) Approval elements

• QA process in the facility incorporating specific attributes
• QA process oversight (physicist oversight?)
• Documentation of IQ in an standardized fashion (via phantoms) –recommended but required within a longer period of time
• TG10 type testing performance

Immediate term (<1 yr) Approval elements

• Acqusition protocol requirements
  • Scatter reduction: Grid (moving/stat), air gap, slot-scan, photon-counting
  • Beam quality (kVp, filter)
  • kW rating of generators
  • Providing an exposure index (TG116)
  • Exposure monitoring over time
  • AEC and/or exposure chart
  • AEC testing

Immediate term (<1 yr) Approval elements

• Specific file format (processed and “for processing” as available, required for new equipment)
• QC guidelines
• Ongoing demonstration of quality
• Beta testing of the approach

Medium term (1-3 yrs)

• A more representative phantom with automated analysis and objective measures (MTF, NPS, eDQE, processing artifacts, imaging chain issues)
• Exposure requirements (based on eDQE)
• Integrated QC utility per image

Long term (3-6 yrs)

• Automated disease classification
• Automated IQ assessment based on image data