Structured templates paired with CAD improves prostate MRI reporting

Implementation of structured reporting templates and computer-aided diagnosis (CAD) tools can significantly elevate the quality of reporting for multiparametric MRI (mp-MRI), according to study results published online April 8 in Academic Radiology.

The use of mp-MRI is well-established as an effective, noninvasive method of diagnosing and determining treatment for prostate cancer, but inconsistencies and widespread variations in reporting continues to be an impediment to large-scale adoption of the modality. Structured reporting templates and CAD tools can help solve this problem, according to lead author Patricia Silveira, MD, and her colleagues at Brigham and Women’s Hospital in Boston. “Compared to conventional, free-text reports, in addition to improving communication of test results, structured reports allow information to be retrieved and reused more easily,” wrote Silveira and colleagues. “CAD tools aim to provide a fast, reproducible, quantitative, and standardized computer analysis of image data, and have been used in the assessment of various diseases across a wide range of imaging modalities.”

The research team set out to determine whether combining structured templates with CAD as part of an IT-enabled quality improvement strategy could improve the consistency and effectiveness of mp-MRI reporting. To do so, they analyzed all mp-MRI reports from their medical facility over a 12-month period­—six months before the installation of the structured template-CAD reporting method, and the six month immediately following implementation. The reports were evaluated by a panel of abdominal radiologists to determine the quality of reporting stemming from the newly implemented reporting method.

Their results showed that reports deemed “optimal” or “satisfactory” by the panel increased from 30 percent to 53 percent following the switch to structured templates and CAD. Despite this, clinicians were slow and somewhat reluctant to adopt to the new reporting tools. “These results suggest that voluntary adoption of IT tools to improve report quality, even when supported by departmental leadership and embedded in radiologists’ workflow, may be inconsistent and may take months,” wrote Silveira et al. “Potential explanations include a gradual learning curve, resistance to behavior change, or lack of evidence regarding benefits of adopting the IT tool.”

The researcher remains optimistic about their findings, however, and believe more studies should be conducted to better evaluate the benefits to structured reporting and CAD, as well as the variables impeding widespread adoption. “Future studies are needed to assess the impact of various quality improvement strategies for accelerated and consistent adoption and use of IT tools on report quality,” the authors wrote. “Such strategies may include automated monitoring of report content through the use of natural language processing tools, feedback to radiologists using quality dashboards, education targeting quality variables awareness, financial incentives, and mandatory use of the IT tools.”