Deep learning-accelerated T2-weighted imaging of the prostate: Reduction of acquisition time and improvement of image quality

Purpose: To introduce a novel deep learning (DL) T2-weighted TSE imaging (T2(DL)) sequence in prostate MRI and investigate its impact on examination time, image quality, diagnostic confidence, and PI-RADS classification compared to standard T2-weighted TSE imaging (T2(S)). Method: Thirty patients who underwent multiparametric MRI (mpMRI) of the prostate due to suspicion of prostatic cancer were included in this retrospective study. Standard sequences were acquired consisting of T1- and T2-weighted imaging and diffusion-weighted imaging as well as the novel T2(DL). Axial acquisition time of T2(S) was 4:37 min compared to 1:38 min of T2(DL). Two radiologists independently evaluated all imaging datasets in a blinded reading regarding image quality, lesion detectability, and diagnostic confidence using a Likert-scale ranging from 1 to 4 with 4 being the best. T2 score as well as PI-RADS score were obtained for the most malignant lesion. Results: Mean patient age was 65 +/- 11 years. Noise levels and overall image quality were rated significantly superior by both readers with a median of 4 in T2(DL) compared to a median of 3 in T2(S) (all p < 0.001). Lesion detectability was also rated higher in T2(DL) by both readers with a median of 4 versus a median of 3 in T2(S) (p = 0.005 and <0.001, respectively). There was no difference regarding PI-RADS scoring between T2(DL) and T2(S) affecting patient management. Conclusions: Deep learning axial T2w TSE imaging of the prostate is feasible with reduction of examination time of 65 % compared to standard imaging and improvement of image quality and lesion detectability.

Automated summary

Introduction of novel deep learning T2-weighted TSE imaging sequence in prostate MRI significantly reduces examination time while improving image quality and lesion detectability. Radiologists rated T2(DL) significantly higher than T2(S) in terms of noise levels, overall image quality, and lesion detectability, but there was no significant difference in PI-RADS scoring affecting patient management.