Performance of an Automated Workflow for Magnetic Resonance Imaging of the Prostate: Comparison With a Manual Workflow

Whole-Body Magnetic Resonance Imaging in the Large Population-Based German National Cohort Study: Predictive Capability of Automated Image Quality Assessment for Protocol Repetitions

BACKGROUND

Reproducible image quality is of high relevance for large cohort studies and can be challenging for magnetic resonance imaging (MRI). Automated image quality assessment may contribute to conducting radiologic studies effectively.

PURPOSE

The aims of this study were to assess protocol repetition frequency in population-based whole-body MRI along with its effect on examination time and to examine the applicability of automated image quality assessment for predicting decision-making regarding repeated acquisitions.

MATERIALS AND METHODS

All participants enrolled in the prospective, multicenter German National Cohort (NAKO) study who underwent whole-body MRI at 1 of 5 sites from 2014 to 2016 were included in this analysis (n = 11,347). A standardized examination program of 12 protocols was used. Acquisitions were carried out by certified radiologic technologists, who were authorized to repeat protocols based on their visual perception of image quality. Eleven image quality parameters were derived fully automatically from the acquired images, and their discrimination ability regarding baseline acquisitions and repetitions was tested.

RESULTS

At least 1 protocol was repeated in 12% (n = 1359) of participants, and more than 1 protocol in 1.6% (n = 181). The repetition frequency differed across protocols (P < 0.001), imaging sites (P < 0.001), and over the study period (P < 0.001). The mean total scan time was 62.6 minutes in participants without and 67.4 minutes in participants with protocol repetitions (mean difference, 4.8 minutes; 95% confidence interval, 4.5-5.2 minutes). Ten of the automatically derived image quality parameters were individually retrospectively predictive for the repetition of particular protocols; for instance, "signal-to-noise ratio" alone provided an area under the curve of 0.65 (P < 0.001) for repetition of the Cardio Cine SSFP SAX protocol. Combinations generally improved prediction ability, as exemplified by "image sharpness" plus "foreground ratio" yielding an area under the curve of 0.89 (P < 0.001) for repetition of the Neuro T1w 3D MPRAGE protocol, versus 0.85 (P < 0.001) and 0.68 (P < 0.001) as individual parameters.

CONCLUSIONS

Magnetic resonance imaging protocol repetitions were necessary in approximately 12% of scans even in the highly standardized setting of a large cohort study. Automated image quality assessment shows predictive value for the technologists' decision to perform protocol repetitions and has the potential to improve imaging efficiency.

Fully Automatic Deep Learning in Bi-institutional Prostate Magnetic Resonance Imaging: Effects of Cohort Size and Heterogeneity

BACKGROUND

The potential of deep learning to support radiologist prostate magnetic resonance imaging (MRI) interpretation has been demonstrated.

PURPOSE

The aim of this study was to evaluate the effects of increased and diversified training data (TD) on deep learning performance for detection and segmentation of clinically significant prostate cancer-suspicious lesions.

MATERIALS AND METHODS

In this retrospective study, biparametric (T2-weighted and diffusion-weighted) prostate MRI acquired with multiple 1.5-T and 3.0-T MRI scanners in consecutive men was used for training and testing of prostate segmentation and lesion detection networks. Ground truth was the combination of targeted and extended systematic MRI-transrectal ultrasound fusion biopsies, with significant prostate cancer defined as International Society of Urological Pathology grade group greater than or equal to 2. U-Nets were internally validated on full, reduced, and PROSTATEx-enhanced training sets and subsequently externally validated on the institutional test set and the PROSTATEx test set. U-Net segmentation was calibrated to clinically desired levels in cross-validation, and test performance was subsequently compared using sensitivities, specificities, predictive values, and Dice coefficient.

RESULTS

One thousand four hundred eighty-eight institutional examinations (median age, 64 years; interquartile range, 58-70 years) were temporally split into training (2014-2017, 806 examinations, supplemented by 204 PROSTATEx examinations) and test (2018-2020, 682 examinations) sets. In the test set, Prostate Imaging-Reporting and Data System (PI-RADS) cutoffs greater than or equal to 3 and greater than or equal to 4 on a per-patient basis had sensitivity of 97% (241/249) and 90% (223/249) at specificity of 19% (82/433) and 56% (242/433), respectively. The full U-Net had corresponding sensitivity of 97% (241/249) and 88% (219/249) with specificity of 20% (86/433) and 59% (254/433), not statistically different from PI-RADS (P > 0.3 for all comparisons). U-Net trained using a reduced set of 171 consecutive examinations achieved inferior performance (P < 0.001). PROSTATEx training enhancement did not improve performance. Dice coefficients were 0.90 for prostate and 0.42/0.53 for MRI lesion segmentation at PI-RADS category 3/4 equivalents.

CONCLUSIONS

In a large institutional test set, U-Net confirms similar performance to clinical PI-RADS assessment and benefits from more TD, with neither institutional nor PROSTATEx performance improved by adding multiscanner or bi-institutional TD.

Multiparametric prostate MRI quality assessment using a semi-automated PI-QUAL software program

The technical requirements for the acquisition of multiparametric magnetic resonance imaging (mpMRI) of the prostate have been clearly outlined in the Prostate Imaging Reporting and Data System (PI-RADS) guidelines, but there is still huge variability in image quality among centres across the world. It has been difficult to quantify what constitutes a good-quality image, and a first attempt to address this matter has been the publication of the Prostate Imaging Quality (PI-QUAL) score and its dedicated scoring sheet. This score includes the assessment of technical parameters that can be obtained from the DICOM files along with a visual evaluation of certain features on prostate MRI (e.g., anatomical structures). We retrospectively analysed the image quality of 10 scans from different vendors and magnets using a semiautomated dedicated PI-QUAL software program and compared the time needed for assessing image quality using two methods (semiautomated assessment versus manual filling of the scoring sheet). This semiautomated software is able to assess the technical parameters automatically, but the visual assessment is still performed by the radiologist. There was a significant reduction in the reporting time of prostate mpMRI quality according to PI-QUAL using the dedicated software program compared to manual filling (5'54″ versus 7'59″; p = 0.005). A semiautomated PI-QUAL software program allows the radiologist to assess the technical details related to the image quality of prostate mpMRI in a quick and reliable manner, allowing clinicians to have more confidence that the quality of mpMRI of the prostate is sufficient to determine patient care.

Revisiting DCE-MRI: Classification of Prostate Tissue Using Descriptive Signal Enhancement Features Derived From DCE-MRI Acquisition With High Spatiotemporal Resolution

METHODS

A retrospective study (from January 2016 to July 2019) including 75 subjects (mean, 65 years; 46-80 years) with 2.5-second temporal resolution DCE-MRI and PIRADS 4 or 5 lesions was performed. Fifty-four subjects had biopsy-proven prostate cancer (Gleason 6, 15; Gleason 7, 20; Gleason 8, 13; Gleason 9, 6), whereas 21 subjects had negative MRI/ultrasound fusion-guided biopsies. Voxel-wise analysis of contrast signal enhancement was performed for all time points using custom-developed software, including automatic arterial input function detection. Seven descriptive parameter maps were calculated: normalized maximum signal intensity, time to start, time to maximum, time-to-maximum slope, and maximum slope with normalization on maximum signal and the arterial input function (SMN1, SMN2). The parameters were compared with ADC using multiparametric machine-learning models to determine classification accuracy. A Wilcoxon test was used for the hypothesis test and the Spearman coefficient for correlation.

RESULTS

There were significant differences (P < 0.05) for all 7 DCE-derived parameters between the normal peripheral zone versus PIRADS 4 or 5 lesions and the biopsy-positive versus biopsy-negative lesions. Multiparametric analysis showed better performance when combining ADC + DCE as input (accuracy/sensitivity/specificity, 97%/93%/100%) relative to ADC alone (accuracy/sensitivity/specificity, 94%/95%/95%) and to DCE alone (accuracy/sensitivity/specificity, 78%/79%/77%) in differentiating the normal peripheral zone from PIRADS lesions, biopsy-positive versus biopsy-negative lesions (accuracy/sensitivity/specificity, 68%/33%/81%), and Gleason 6 versus ≥7 prostate cancer (accuracy/sensitivity/specificity, 69%/60%/72%).

CONCLUSIONS

Descriptive perfusion characteristics derived from high-resolution DCE-MRI using model-free computations show significant differences between normal and cancerous tissue but do not reach the accuracy achieved with solely ADC-based classification. Combining ADC with DCE-based input features improved classification accuracy for PIRADS lesions, discrimination of biopsy-positive versus biopsy-negative lesions, and differentiation between Gleason 6 versus Gleason ≥7 lesions.

Improving workflow in prostate MRI: AI-based decision-making on biparametric or multiparametric MRI

OBJECTIVES

To develop and validate an artificial intelligence algorithm to decide on the necessity of dynamic contrast-enhanced sequences (DCE) in prostate MRI.

METHODS

This study was approved by the institutional review board and requirement for study-specific informed consent was waived. A convolutional neural network (CNN) was developed on 300 prostate MRI examinations. Consensus of two expert readers on the necessity of DCE acted as reference standard. The CNN was validated in a separate cohort of 100 prostate MRI examinations from the same vendor and 31 examinations from a different vendor. Sensitivity/specificity were calculated using ROC curve analysis and results were compared to decisions made by a radiology technician.

RESULTS

The CNN reached a sensitivity of 94.4% and specificity of 68.8% (AUC: 0.88) for the necessity of DCE, correctly assigning 44%/34% of patients to a biparametric/multiparametric protocol. In 2% of all patients, the CNN incorrectly decided on omitting DCE. With a technician reaching a sensitivity of 63.9% and specificity of 89.1%, the use of the CNN would allow for an increase in sensitivity of 30.5%. The CNN achieved an AUC of 0.73 in a set of examinations from a different vendor.

CONCLUSIONS

The CNN would have correctly assigned 78% of patients to a biparametric or multiparametric protocol, with only 2% of all patients requiring re-examination to add DCE sequences. Integrating this CNN in clinical routine could render the requirement for on-table monitoring obsolete by performing contrast-enhanced MRI only when needed.

Spiral 3-Dimensional T1-Weighted Turbo Field Echo: Increased Speed for Magnetization-Prepared Gradient Echo Brain Magnetic Resonance Imaging

OBJECTIVES

Spiral magnetic resonance imaging acquisition may enable improved image quality and higher scan speeds than Cartesian trajectories. We tested the performance of four 3D T1-weighted (T1w) TFE sequences (magnetization-prepared gradient echo magnetic resonance sequence) with isotropic spatial resolution for brain imaging at 1.5 T in a clinical patient cohort based on qualitative and quantitative image quality metrics. Two prototypical spiral TFE sequences (spiral 1.0 and spiral 0.85) and a Cartesian compressed sensing technology accelerated TFE sequence (CS 2.5; acceleration factor of 2.5) were compared with a conventional (reference standard) Cartesian parallel imaging accelerated TFE sequence (SENSE; acceleration factor of 1.8).

MATERIALS AND METHODS

The SENSE (5:52 minutes), CS 2.5 (3:17 minutes), and spiral 1.0 (2:16 minutes) sequences all had identical spatial resolutions (1.0 mm). The spiral 0.85 (3:47 minutes) had a higher spatial resolution (0.85 mm). The 4 TFE sequences were acquired in 41 patients (20 with and 21 without contrast media). Three readers rated qualitative image quality (12 categories) and selected their preferred sequence for each patient. Two readers performed quantitative analysis whereby 6 metrics were derived: contrast-to-noise ratio for white and gray matter (CNRWM/GM), contrast ratio for gray matter-CSF (CRGM/CSF), and white matter-CSF (CRWM/CSF); and coefficient of variations for gray matter (CVGM), white matter (CVWM), and CSF (CVCSF). Friedman tests with post hoc Nemenyi tests, exact binomial tests, analysis of variance with post hoc Dunnett tests, and Krippendorff alphas were computed.

RESULTS

Concerning qualitative analysis, the CS 2.5 sequence significantly outperformed the SENSE in 4/1 (with/without contrast) categories, whereas the spiral 1.0 and spiral 0.85 showed significantly improved scores in 10/9and 7/7 categories, respectively (P's < 0.001-0.039). The spiral 1.0 was most frequently selected as the preferred sequence (reader 1, 10/15 times; reader 2, 9/12 times; reader 3, 11/13times [with/without contrast]). Interreader agreement ranged from substantial to almost perfect (alpha = 0.615-0.997). Concerning quantitative analysis, compared with the SENSE, the CS 2.5 had significantly better scores in 2 categories (CVWM, CVCSF) and worse scores in 2 categories (CRGM/CSF, CRWM/CSF), the spiral 1.0 had significantly improved scores in 4 categories (CNRWM/GM, CRGM/CSF, CRWM/CSF, CVWM), and the spiral 0.85 had significantly better scores in 2 categories (CRGM/CSF, CRWM/CSF).

CONCLUSIONS

Spiral T1w TFE sequences may deliver high-quality clinical brain imaging, thus matching the performance of conventional parallel imaging accelerated T1w TFEs. Imaging can be performed at scan times as short as 2:16 minutes per sequence (61.4% scan time reduction compared with SENSE). Optionally, spiral imaging enables increased spatial resolution while maintaining the scan time of a Cartesian-based acquisition schema.

Measured Multipoint Ultra-High b-Value Diffusion MRI in the Assessment of MRI-Detected Prostate Lesions

OBJECTIVES

The aim of this study was to assess quantitative ultra-high b-value (UHB) diffusion magnetic resonance imaging (MRI)-derived parameters in comparison to standard clinical apparent diffusion coefficient (SD-ADC-2b-1000, SD-ADC-2b-1500) for the prediction of clinically significant prostate cancer, defined as Gleason Grade Group greater than or equal to 2.

MATERIALS AND METHODS

Seventy-three patients who underwent 3-T prostate MRI with diffusion-weighted imaging acquired at b = 50/500/1000/1500s/mm2 and b = 100/500/1000/1500/2250/3000/4000 s/mm2 were included. Magnetic resonance lesions were segmented manually on individual sequences, then matched to targeted transrectal ultrasonography/MRI fusion biopsies. Monoexponential 2-point and multipoint fits of standard diffusion and of UHB diffusion were calculated with incremental b-values. Furthermore, a kurtosis fit with parameters Dapp and Kapp with incremental b-values was obtained. Each parameter was examined for prediction of clinically significant prostate cancer using bootstrapped receiver operating characteristics and decision curve analysis. Parameter models were compared using Vuong test.

RESULTS

Fifty of 73 men (age, 66 years [interquartile range, 61-72]; prostate-specific antigen, 6.6 ng/mL [interquartile range, 5-9.7]) had 64 MRI-detected lesions. The performance of SD-ADC-2b-1000 (area under the curve, 0.82) and SD-ADC-2b-1500 (area under the curve, 0.82) was not statistically different (P = 0.99), with SD-ADC-2b-1500 selected as reference. Compared with the reference model, none of the 19 tested logistic regression parameter models including multipoint and 2-point UHB-ADC, Dapp, and Kapp with incremental b-values of up to 4000 s/mm2 outperformed SD-ADC-2b-1500 (all P's > 0.05). Decision curve analysis confirmed these results indicating no higher net benefit for UHB parameters in comparison to SD-ADC-2b-1500 in the clinically important range from 3% to 20% of cancer threshold probability. Net reduction analysis showed no reduction of MR lesions requiring biopsy.

CONCLUSIONS

Despite evaluation of a large b-value range and inclusion of 2-point, multipoint, and kurtosis models, none of the parameters provided better predictive performance than standard 2-point ADC measurements using b-values 50/1000 or 50/1500. Our results suggest that most of the diagnostic benefits available in diffusion MRI are already represented in an ADC composed of one low and one 1000 to 1500 s/mm2 b-value.