Erschienen in:Journal of Magnetic Resonance Imaging
Sprache:
Englisch
DOI:
10.1002/jmri.28602
ISSN:
1053-1807;
1522-2586
Entstehung:
Anmerkungen:
Beschreibung:
<jats:sec><jats:title>Background</jats:title><jats:p>Demand for prostate MRI is increasing, but scan times remain long even in abbreviated biparametric MRIs (bpMRI). Deep learning can be leveraged to accelerate T2‐weighted imaging (T2WI).</jats:p></jats:sec><jats:sec><jats:title>Purpose</jats:title><jats:p>To compare conventional bpMRIs (CL‐bpMRI) with bpMRIs including a deep learning‐accelerated T2WI (DL‐bpMRI) in diagnosing prostate cancer.</jats:p></jats:sec><jats:sec><jats:title>Study Type</jats:title><jats:p>Retrospective.</jats:p></jats:sec><jats:sec><jats:title>Population</jats:title><jats:p>Eighty consecutive men, mean age 66 years (47–84) with suspected prostate cancer or prostate cancer on active surveillance who had a prostate MRI from December 28, 2020 to April 28, 2021 were included. Follow‐up included prostate biopsy or stability of prostate‐specific antigen (PSA) for 1 year.</jats:p></jats:sec><jats:sec><jats:title>Field Strength and Sequences</jats:title><jats:p>A 3 T MRI. Conventional axial and coronal T2 turbo spin echo (CL‐T2), 3‐fold deep learning‐accelerated axial and coronal T2‐weighted sequence (DL‐T2), diffusion weighted imaging (DWI) with <jats:italic>b</jats:italic> = 50 sec/mm<jats:sup>2</jats:sup>, 1000 sec/mm<jats:sup>2</jats:sup>, calculated <jats:italic>b</jats:italic> = 1500 sec/mm<jats:sup>2</jats:sup>.</jats:p></jats:sec><jats:sec><jats:title>Assessment</jats:title><jats:p>CL‐bpMRI and DL‐bpMRI including the same conventional diffusion‐weighted imaging (DWI) were presented to three radiologists (blinded to acquisition method) and to a deep learning computer‐assisted detection algorithm (DL‐CAD). The readers evaluated image quality using a 4‐point Likert scale (1 = nondiagnostic, 4 = excellent) and graded lesions using Prostate Imaging Reporting and Data System (PI‐RADS) v2.1. DL‐CAD identified and assigned lesions of PI‐RADS 3 or greater.</jats:p></jats:sec><jats:sec><jats:title>Statistical Tests</jats:title><jats:p>Quality metrics were compared using Wilcoxon signed rank test, and area under the receiver operating characteristic curve (AUC) were compared using Delong's test. Significance: <jats:italic>P</jats:italic> = 0.05.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>Eighty men were included (age: 66 ± 9 years; 17/80 clinically significant prostate cancer). Overall image quality results by the three readers (CL‐T2, DL‐T2) are reader 1: 3.72 ± 0.53, 3.89 ± 0.39 (<jats:italic>P</jats:italic> = 0.99); reader 2: 3.33 ± 0.82, 3.31 ± 0.74 (<jats:italic>P</jats:italic> = 0.49); reader 3: 3.67 ± 0.63, 3.51 ± 0.62. In the patient‐based analysis, the reader results of AUC are (CL‐bpMRI, DL‐bpMRI): reader 1: 0.77, 0.78 (<jats:italic>P</jats:italic> = 0.98), reader 2: 0.65, 0.66 (<jats:italic>P</jats:italic> = 0.99), reader 3: 0.57, 0.60 (<jats:italic>P</jats:italic> = 0.52). Diagnostic statistics from DL‐CAD (CL‐bpMRI, DL‐bpMRI) are sensitivity (0.71, 0.71, <jats:italic>P</jats:italic> = 1.00), specificity (0.59, 0.44, <jats:italic>P</jats:italic> = 0.05), positive predictive value (0.23, 0.24, <jats:italic>P</jats:italic> = 0.25), negative predictive value (0.88, 0.88, <jats:italic>P</jats:italic> = 0.48).</jats:p></jats:sec><jats:sec><jats:title>Conclusion</jats:title><jats:p>Deep learning‐accelerated T2‐weighted imaging may potentially be used to decrease acquisition time for bpMRI.</jats:p></jats:sec><jats:sec><jats:title>Evidence Level</jats:title><jats:p>3.</jats:p></jats:sec><jats:sec><jats:title>Technical Efficacy</jats:title><jats:p>Stage 2.</jats:p></jats:sec>