Biparametric prostate MRI with super-resolution deep learning reconstruction: image quality assessment using PI-QUAL version 2

Motivation: Super-resolution deep learning reconstruction (SR-DLR) can simultaneously reduce noise and improve spatial resolution. Goal(s): Our goal was to evaluate the image quality of biparametric prostate MRI with SR-DLR using PI-QUAL version 2. Approach: SR-DLR was applied to both T2WI and DWI. SNR and subjective image quality were compared between SR-DLR and conventional images. Results: SR-DLR significantly improved the image quality of biparametic prostate MRI and increased PI-QUAL scores. Impact: SR-DLR improves both T2WI and DWI image quality in prostate MRI, resulting in improved PI-QUAL scores. This technique may have the potential to improve the diagnostic accuracy of prostate biparametric MRI of the prostate.