Implementation and Application Evaluation of a Structured Reporting System for Medical Image

Objective To implement radiological diagnostic guidelines and improve the standardization level of radiological reports.

Methods A multimodal structured reporting system was designed. An integrated strategy of "standard coding + structural items + key images" was adopted to develop report templates for different diseases or anatomical sites, covering both text-only structured reports and comprehensive text-image structured reports. Horizontal comparisons with traditional (unstructured) reports were conducted to evaluate differences across four dimensions: efficiency, acceptability, completeness of disease sign description, and accuracy of data classification.

Results The quality of comprehensive text-image structured reports was significantly superior to that of traditional reports (P<0.01), while there was no statistically significant difference between text-only structured reports and traditional reports (P>0.01). The information completeness and compliance with diagnostic guidelines of text-image reports were significantly higher than those of both traditional reports and text-only structured reports. The acceptability of text-image reports among senior radiologists (4.04±0.55) and clinicians (4.19±0.58) was higher than that among junior radiologists (3.04±1.55). In terms of data classification accuracy, the retrieval accuracy of structured reports based on natural language processing (NLP) (F1-Score: 0.85–1.00) was significantly better than the keyword retrieval method used for traditional reports.

Conclusion Image-text-integrated structured reporting reduces heterogeneity in traditional reports and aids competency development among junior radiologists in primary care.