Structure-preserving super-resolution of retinal fundus images via a dual-transformer residual network.

Front Med (Lausanne) · 2025 · PMC12900677 · PMID 41694677

Europe PMC DOI

hedged sentence

—

closest p

—

boldest claim

The sentences

highly significantno p-value reported

Notably, the improvements over state-of the-art methods including HAT ( p = 0.0034), ResShift ( p = 0.0041), and SwinIR ( p < 0.001) are highly significant, establishing that DTRSRN's superior performance is statistically meaningful rather than arising from dataset-specific fluctuations.

also in 132,142 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.