Adaptive ensemble learning for prostate cancer classification on multi-modal MRI: reducing unnecessary biopsies.

BMC Med Imaging · 2026 · PMC12888165 · PMID 41526840

Europe PMC DOI

hedged sentence

0.0600

closest p · 1.2× alpha

0.0600

boldest claim

The sentences

near-significantp = 0.06so close (0.05 < p ≤ 0.1)

The consistent dominance of DCE across all architectures (41.5–41.8%) and the near-significant p-value ( p = 0.06) suggest that the model learned clinically relevant vascular patterns complementary to traditional DWI assessment.

also in 1,169 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.