Deep Learning Super-Resolution Reconstruction for Fast and Motion-Robust T2-weighted Prostate MRI

Background: Deep learning (DL) reconstructions can enhance image quality while decreasing MRI acquisition time. However, DL reconstruction methods combined with compressed sensing for prostate MRI have not been well studied. Purpose: To use an industry-developed DL algorithm to reconstruct low-resolution T2-weighted turbo spin-echo (TSE) prostate MRI scans and compare these with standard sequences. Materials and Methods: In this prospective study, participants with suspected prostate cancer underwent prostate MRI with a Cartesian standard-resolution T2-weighted TSE sequence (T2 (C)) and non-Cartesian standard-resolution T2-weighted TSE sequence (T2 (NC)) between August and November 2022. Additionally, a low-resolution Cartesian DL-reconstructed T2-weighted TSE sequence (T2 (DL)) with compressed sensing DL denoising and resolution upscaling reconstruction was acquired. Image sharpness was assessed qualitatively by two readers using a five-point Likert scale (from 1 = nondiagnostic to 5 = excellent) and quantitatively by calculating edge rise distance. The Friedman test and one-way analysis of variance with post hoc Bonferroni and Tukey tests, respectively, were used for group comparisons. Prostate Imaging Reporting and Data System (PI-RADS) score agreement between sequences was compared by using Cohen kappa. Results: This study included 109 male participants (mean age, 68 years +/- 8 [SD]). Acquisition time of T2 (DL) was 36% and 29% lower compared with that of T2 (C) and T2 (NC) (mean duration, 164 seconds +/- 20 vs 257 seconds +/- 32 and 230 seconds +/- 28; P <.001 for both). T2 (DL) showed improved image sharpness compared with standard sequences using both qualitative (median score, 5 [IQR, 4-5] vs 4 [IQR, 3-4] for T2 (C) and 4 [IQR, 3-4] for T2 (NC); P <.001 for both) and quantitative (mean edge rise distance, 0.75 mm +/- 0.39 vs 1.15 mm +/- 0.68 for T2 (C) and 0.98 mm +/- 0.65 for T2 (NC); P <.001 and P =.01) methods. PI-RADS score agreement between T2 (NC) and T2 (DL) was excellent (. range, 0.92-0.94 [95% CI: 0.87, 0.98]). Conclusion: DL reconstruction of low-resolution T2-weighted TSE sequences enabled accelerated acquisition times and improved image quality compared with standard acquisitions while showing excellent agreement with conventional sequences for PI-RADS ratings.