Related Experiment Video
Updated: Jan 2, 2026
05:33
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
721
Augmented Radiologist Workflow Improves Report Value and Saves Time: A Potential Model for Implementation of
Huy M Do1, Lillian G Spear2, Moozhan Nikpanah1
1Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Building 10, 9000 Rockville Pike, Bethesda, MD 20892, USA.
Academic Radiology
|December 11, 2019
Summary
Radiology preprocessors (RPs) significantly improved target lesion measurement concordance by threefold and decreased radiologist interpretation times by 37%. RPs also enabled earlier detection and faster notification of incidental findings, enhancing patient care.
Area of Science:
- Radiology
- Medical Imaging
- Health Informatics
Background:
- Improving the accuracy and efficiency of radiology reports is crucial for timely patient care.
- Radiology reports often face challenges with target lesion measurement concordance and timely communication of incidental findings.
- Reducing radiologist interpretation time can alleviate workflow burdens and improve throughput.
Purpose of the Study:
- To enhance radiology report accuracy by improving target lesion measurement concordance with oncology records using radiology preprocessors (RPs).
- To assess the impact of RPs on the speed of notification for incidental actionable findings to referring clinicians.
- To evaluate the time savings for clinical radiologists in exam interpretation through RPs that quantify tumor burden.
Main Methods:
- A prospective quality improvement initiative involving RPs annotating lesions before radiologist interpretation of CT exams.
- Clinical radiologists hyperlinked approved measurements into interactive reports.
- RPs evaluated concordance with tumor measurement radiologists, and actionable finding detection/notification times were recorded.
Main Results:
- Improved target lesion measurement concordance from 22.5% to 67.8% (three-fold increase).
- RPs detected 93.1% of incidental actionable findings, with a median notification time reduction of 1 hour.
- Clinical radiologist exam interpretation times decreased by 37%.
Conclusions:
- The implemented workflow significantly improved target lesion measurement concordance and accelerated the detection and notification of incidental findings.
- Radiology preprocessors demonstrated potential for automation, including AI, to enhance report value, prioritize worklists, and improve patient care.
- This approach offers a valuable model for optimizing radiology workflows and clinical decision-making.
