A new study out of Austria provided solid evidence that content-based image retrieval systems (CBIRS) enhance radiologists’ reading efficiency, while potentially improving their diagnostic accuracy.
Eight radiologists reviewed chest CTs from 108 patients with suspected diffuse parenchymal lung disease (DPLD), leveraging contextflow’s AI-based SEARCH Lung CT CBIRS with half of the exams.
Using the radiologists’ CT image regions of interest, the CBIRS would search a database of 6,542 chest CTs to identify similar scans, providing the rads with the three most likely disease patterns and supporting information (e.g. a list of potential differential diagnoses). The CBIRS’ added “context” had a notable impact on the radiologists:
- Reducing their average reading time by 31.3% (197 vs. 287 seconds)
- Reducing resident and attending radiologists’ reading time by 27% and 35%
- Improving overall diagnostic accuracy by over 7pts (42.2% vs. 34.7%; not statistically significant)
These reading time reductions came despite the fact that radiologists were more likely to search for additional information when using the CBIRS (72% vs. 43% of cases). That’s partially because CBIRS allowed greater speed improvements when radiologists searched for more information (110 seconds faster vs. without CBIRS) than when rads didn’t search for more info (39 seconds faster).
The Takeaway
This study presents a rare example of how imaging AI can significantly improve radiologists’ efficiency, while amplifying their current workflows and diagnostic decision-making processes. It’s also the second study in the last year suggesting that CBIRS might improve diagnostic accuracy, although the authors encourage more research into CBIRS’ accuracy impact to know for sure.
