What question did this study set out to answer?

To assess the impact of deep learning reconstruction on MRI acceleration without compromising prostate cancer detection by radiologists.

April 4, 2026Open Access

Diagnostic assessment of artificial intelligence reconstruction on accelerated prostate MRI: a retrospective, paired, multi-reader multi-case study

Key Points

To assess the impact of deep learning reconstruction on MRI acceleration without compromising prostate cancer detection by radiologists.
Retrospective, paired multi-reader multi-case study design
Involvement of eight radiologists to evaluate diagnostic performance
Comparison of three- and sixfold acceleration using deep learning reconstruction
No significant change in detection rates of prostate cancer observed
Deep learning reconstruction maintains image quality even at sixfold acceleration
T2-weighted acquisition times reduced significantly with acceleration methods

Abstract

Question This study investigated whether deep learning reconstruction enables three- to sixfold acceleration without reducing radiologists' detection of clinically significant prostate cancer. Findings In a multi-reader multi-case study with eight radiologists, three- and sixfold acceleration showed no significant change in area under the receiver operating characteristic curve. Clinical relevance Deep learning reconstruction shortened T2-weighted acquisition times at sixfold acceleration while preserving perceived image quality and diagnostic performance across acceleration factors.

Bookmark

View Full Paper