Evaluation of a content-based image retrieval system for radiologists in high-resolution CT of interstitial lung diseases.

Eur Radiol Exp · 2025 · PMC11729592 · PMID 39804425

Europe PMC DOI

hedged sentences

0.1250

closest p · 2.5× alpha

0.1250

boldest claim

The sentences

a decreasing trendp = 0.125not close (p > 0.1)

Per-reader analysis showed that CBIR software use of reader 1 slightly increased from session B (6/14, 42.9%) to D (7/14, 50%), whereas software use of reader 2 showed a decreasing trend (12/14, 85.7% versus 8/14, 57.1%, p = 0.125).

also in 29,876 other papers

a positive trendno p-value reported

Choe et al [ 19 ] reported a positive trend of diagnostic accuracy using an in-house developed CBIR (46.1% versus 60.9%), including radiology and non-radiology residents, whereas our study focused on radiology residents.

also in 6,846 other papers

an increasing trendno p-value reported

Results Diagnostic accuracy and confidence of readers showed an increasing trend with CBIR use compared to no CBIR use (53.6% versus 35.7% and 50.0% versus 32.2%, respectively).

also in 38,133 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.