Machine learning-based multi-class classification of bladder pathologies using fused 3D CT radiomic and 3D auto-encoder deep features.

Eur J Radiol Open · 2026 · PMC12818980 · PMID 41568074

Europe PMC DOI

hedged sentence

0.0700

closest p · 1.4× alpha

0.0700

boldest claim

The sentences

showed a trendP = 0.07so close (0.05 < p ≤ 0.1)

DeLong’s test indicated that the hybrid model’s performance was significantly superior to that of the deep learning-only model ( P < 1 ×10−5) and showed a trend towards superiority over the radiomics-only model ( P = 0.07).

also in 53,322 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.