Although artificial intelligence (AI) shows great potential to help radiologists in their daily clinical routine, integrating AI into the radiology workflow is often lacking, underutilizing its full potential. Therefore, this study aimed to develop a new reporting pipeline enabling automated pre-population of structured reports with results provided by commercially available AI tools.
The authors successfully demonstrated that the AI to structured reporting pipeline helps to offer a standardized, time-efficient, and high-quality way to integrate AI-generated findings into the reporting workflow, with the potential to improve AI integration into daily clinical routine and create a more synergistic relationship between AI and structured reporting.
Key points:
- A pipeline was developed for automated transfer of AI results into structured reports.
- Pipeline chest X-ray reporting is faster than free-text or conventional structured reports.
- Report quality was also rated higher for reports created with the pipeline.
- The pipeline offers efficient, standardized AI integration into the clinical workflow.
Authors: Tobias Jorg, Moritz C. Halfmann, Fabian Stoehr, Gordon Arnhold, Annabell Theobald, Peter Mildenberger & Lukas Müller
