Deep Learning Reconstruction Enables Highly Accelerated Biparametric MR Imaging of the Prostate

Background Early diagnosis and treatment of prostate cancer (PCa) can be curative; however, prostate-specific antigen is a suboptimal screening test for clinically significant PCa. While prostate magnetic resonance imaging (MRI) has demonstrated value for the diagnosis of PCa, the acquisition time is too long for a first-line screening modality. Purpose To accelerate prostate MRI exams, utilizing a variational network (VN) for image reconstruction. Study Type Retrospective. Subjects One hundred and thirteen subjects (train/val/test: 70/13/30) undergoing prostate MRI. Field Strength/Sequence 3.0 T; a T2 turbo spin echo (TSE) T2-weighted image (T2WI) sequence in axial and coronal planes, and axial echo-planar diffusion-weighted imaging (DWI). Assessment Four abdominal radiologists evaluated the image quality of VN reconstructions of retrospectively under-sampled biparametric MRIs (bp-MRI), and standard bp-MRI reconstructions for 20 test subjects (studies). The studies included axial and coronal T2WI, DWI B50 seconds/mm(2) and B1000 seconds/mm (4-fold T2WI, 3-fold DWI), all of which were evaluated separately for image quality on a Likert scale (1: non-diagnostic to 5: excellent quality). In another 10 test subjects, three readers graded lesions on bp-MRI-which additionally included calculated B1500 seconds/mm(2), and apparent diffusion coefficient map-according to the Prostate Imaging Reporting and Data System (PI-RADS v2.1), for both VN and standard reconstructions. Accuracy of PI-RADS >= 3 for clinically significant cancer was computed. Projected scan time of the retrospectively under-sampled biparametric exam was also computed. Statistical Tests One-sided Wilcoxon signed-rank test was used for comparison of image quality. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated for lesion detection and grading. Generalized estimating equation with cluster effect was used to compare differences between standard and VN bp-MRI. A P-value of Three of four readers rated no significant difference for overall quality between the standard and VN axial T2WI (Reader 1: 4.00 +/- 0.56 (Standard), 3.90 +/- 0.64 (VN) P = 0.33; Reader 2: 4.35 +/- 0.74 (Standard), 3.80 +/- 0.89 (VN) P = 0.003; Reader 3: 4.60 +/- 0.50 (Standard), 4.55 +/- 0.60 (VN) P = 0.39; Reader 4: 3.65 +/- 0.99 (Standard), 3.60 +/- 1.00 (VN) P = 0.38). All four readers rated no significant difference for overall quality between standard and VN DWI B1000 seconds/mm(2) (Reader 1: 2.25 +/- 0.62 (Standard), 2.45 +/- 0.75 (VN) P = 0.96; Reader 2: 3.60 +/- 0.92 (Standard), 3.55 +/- 0.82 (VN) P = 0.40; Reader 3: 3.85 +/- 0.72 (Standard), 3.55 +/- 0.89 (VN) P = 0.07; Reader 4: 4.70 +/- 0.76 (Standard); 4.60 +/- 0.73 (VN) P = 0.17) and three of four readers rated no significant difference for overall quality between standard and VN DWI B50 seconds/mm(2) (Reader 1: 3.20 +/- 0.70 (Standard), 3.40 +/- 0.75 (VN) P = 0.98; Reader 2: 2.85 +/- 0.81 (Standard), 3.00 +/- 0.79 (VN) P = 0.93; Reader 3: 4.45 +/- 0.72 (Standard), 4.05 +/- 0.69 (VN) P = 0.02; Reader 4: 4.50 +/- 0.69 (Standard), 4.45 +/- 0.76 (VN) P = 0.50). In the lesion evaluation study, there was no significant difference in the number of PI-RADS >= 3 lesions identified on standard vs. VN bp-MRI (P = 0.92, 0.59, 0.87) with similar sensitivity and specificity for clinically significant cancer. The average scan time of the standard clinical biparametric exam was 11.8 minutes, and this was projected to be 3.2 minutes for the accelerated exam. Data Conclusion Diagnostic accelerated biparametric prostate MRI exams can be performed using deep learning methods in <4 minutes, potentially enabling rapid screening prostate MRI. Level of Evidence 3 Technical Efficacy Stage 5

Automated summary

The study utilized a variational network (VN) for image reconstruction to accelerate prostate MRI exams, showing that diagnostic biparametric prostate MRI exams can be performed in less than 4 minutes using deep learning methods, potentially enabling rapid screening prostate MRI.