Deep Learning Super-Resolution Reconstruction for Fast and Motion-Robust T2-weighted Prostate MRI

Application of high-density 2D receiver coil arrays for improved SNR in prostate MRI

PURPOSE

To study if adaptive image receive (AIR) receiver coil elements can be configured into a 2D array with high (>45% by diameter) element-to-element overlap, allowing improved SNR at depth (0.7-1.5× element diameter) versus conventional (20%) overlap.

METHODS

An anterior array composed of twenty 10-cm diameter elements with 45% overlap arranged into a 4 × 5 grid and a similar 3 × 7 twenty-one-element posterior array were constructed. SNR and g-factor were measured in a pelvic phantom using the new high-density (HD) arrays (41 total elements) and compared to vendor AIR-based arrays (30 total elements) with conventional overlap. T2-weighted fast-spin-echo (T2SE) images acquired using both arrays were compared in 20 subjects. SNR was estimated in vivo. Results were compared blindly by three uroradiologists using a five-point scale. Images using the HD arrays were also compared to a set of images acquired over a range of acceleration factors (R = 2.0, 2.5, 3.0) with the conventional arrays.

RESULTS

SNR within the phantom was on average 15% higher for R = 1.0, 1.5, and 2.0 using the HD arrays. Across the 20 subjects SNR within the prostate was 11% higher and assessed radiologically as significantly higher (p < 0.001) for the HD versus conventional arrays. At all acceleration factors the new HD arrays outperformed the conventional arrays (p ≤ 0.01), allowing increased R for similar SNR.

CONCLUSION

AIR elements can be configured into 2D arrays with high (45%) element-to-element overlap, consistently providing increased SNR at depth versus arrays with conventional (20%) overlap. The SNR improvement allows increased acceleration in T2SE prostate MRI.

Value-Based Radiology in Canada: Reducing Low-Value Care and Improving System Efficiency

Radiology departments are increasingly tasked with managing growing demands on services including long waitlists for scanning and interventional procedures, human health resource shortages, equipment needs, and challenges incorporating advanced imaging solutions. The burden of system inefficiencies and the overuse of "low-value" imaging causes downstream impact on patients at the individual level, the economy and healthcare system at the societal level, and planetary health at an overarching level. Low value imaging includes those performed for an inappropriate clinical indication, with little to no value to the management of the patient, and resulting in healthcare resource waste; it is estimated that up to a quarter of advanced imaging studies in Canada meet this criterion. Strategies to reduce low-value imaging include the development and use of referral guidelines, use of appropriateness criteria, optimization of existing protocols, and integration of clinical decision support tools into the ordering provider's workflow. Additional means of optimizing system efficiency such as centralized intake models, improved access to electronic medical records and outside imaging, enhanced communication with patients and referrers, and the utilization of artificial intelligence will further increase the value of radiology provided to patients and care providers.

Accelerated High-resolution T1- and T2-weighted Breast MRI with Deep Learning Super-resolution Reconstruction

RATIONALE AND OBJECTIVES

To assess the performance of an industry-developed deep learning (DL) algorithm to reconstruct low-resolution Cartesian T1-weighted dynamic contrast-enhanced (T1w) and T2-weighted turbo-spin-echo (T2w) sequences and compare them to standard sequences.

MATERIALS AND METHODS

Female patients with indications for breast MRI were included in this prospective study. The study protocol at 1.5 Tesla MRI included T1w and T2w. Both sequences were acquired in standard resolution (T1S and T2S) and in low-resolution with following DL reconstructions (T1DL and T2DL). For DL reconstruction, two convolutional networks were used: (1) Adaptive-CS-Net for denoising with compressed sensing, and (2) Precise-Image-Net for resolution upscaling of previously downscaled images. Overall image quality was assessed using 5-point-Likert scale (from 1=non-diagnostic to 5=excellent). Apparent signal-to-noise (aSNR) and contrast-to-noise (aCNR) ratios were calculated. Breast Imaging Reporting and Data System (BI-RADS) agreement between different sequence types was assessed.

RESULTS

A total of 47 patients were included (mean age, 58±11 years). Acquisition time for T1DL and T2DL were reduced by 51% (44 vs. 90 s per dynamic phase) and 46% (102 vs. 192 s), respectively. T1DL and T2DL showed higher overall image quality (e.g., 4 [IQR, 4-4] for T1S vs. 5 [IQR, 5-5] for T1DL, P<0.001). Both, T1DL and T2DL revealed higher aSNR and aCNR than T1S and T2S (e.g., aSNR: 32.35±10.23 for T2S vs. 27.88±6.86 for T2DL, P=0.014). Cohen k agreement by BI-RADS assessment was excellent (0.962, P<0.001).

CONCLUSION

DL for denoising and resolution upscaling reduces acquisition time and improves image quality for T1w and T2w breast MRI.

Deep Learning-Based Super-Resolution Reconstruction on Undersampled Brain Diffusion-Weighted MRI for Infarction Stroke: A Comparison to Conventional Iterative Reconstruction

BACKGROUND AND PURPOSE

DWI is crucial for detecting infarction stroke. However, its spatial resolution is often limited, hindering accurate lesion visualization. Our aim was to evaluate the image quality and diagnostic confidence of deep learning (DL)-based super-resolution reconstruction for brain DWI of infarction stroke.

MATERIALS AND METHODS

This retrospective study enrolled 114 consecutive participants who underwent brain DWI. The DWI images were reconstructed with 2 schemes: 1) DL-based super-resolution reconstruction (DWIDL); and 2) conventional compressed sensing reconstruction (DWICS). Qualitative image analysis included overall image quality, lesion conspicuity, and diagnostic confidence in infarction stroke of different lesion sizes. Quantitative image quality assessments were performed by measurements of SNR, contrast-to-noise ratio (CNR), ADC, and edge rise distance. Group comparisons were conducted by using a paired t test for normally distributed data and the Wilcoxon test for non-normally distributed data. The overall agreement between readers for qualitative ratings was assessed by using the Cohen κ coefficient. A P value less than .05 was considered statistically significant.

RESULTS

A total of 114 DWI examinations constituted the study cohort. For the qualitative assessment, overall image quality, lesion conspicuity, and diagnostic confidence in infarction stroke lesions (lesion size <1.5 cm) improved by DWIDL compared with DWICS (all P < .001). For the quantitative analysis, edge rise distance of DWIDL was reduced compared with that of DWICS (P < .001), and no significant difference in SNR, CNR, and ADC values (all P > .05).

CONCLUSIONS

Compared with the conventional compressed sensing reconstruction, the DL-based super-resolution reconstruction demonstrated superior image quality and was feasible for achieving higher diagnostic confidence in infarction stroke.

Deep Learning to Simulate Contrast-Enhanced MRI for Evaluating Suspected Prostate Cancer

Background Multiparametric MRI, including contrast-enhanced sequences, is recommended for evaluating suspected prostate cancer, but concerns have been raised regarding potential contrast agent accumulation and toxicity. Purpose To evaluate the feasibility of generating simulated contrast-enhanced MRI from noncontrast MRI sequences using deep learning and to explore their potential value for assessing clinically significant prostate cancer using Prostate Imaging Reporting and Data System (PI-RADS) version 2.1. Materials and Methods Male patients with suspected prostate cancer who underwent multiparametric MRI were retrospectively included from three centers from April 2020 to April 2023. A deep learning model (pix2pix algorithm) was trained to synthesize contrast-enhanced MRI scans from four noncontrast MRI sequences (T1-weighted imaging, T2-weighted imaging, diffusion-weighted imaging, and apparent diffusion coefficient maps) and then tested on an internal and two external datasets. The reference standard for model training was the second postcontrast phase of the dynamic contrast-enhanced sequence. Similarity between simulated and acquired contrast-enhanced images was evaluated using the multiscale structural similarity index. Three radiologists independently scored T2-weighted and diffusion-weighted MRI with either simulated or acquired contrast-enhanced images using PI-RADS, version 2.1; agreement was assessed with Cohen κ. Results A total of 567 male patients (mean age, 66 years ± 11 [SD]) were divided into a training test set (n = 244), internal test set (n = 104), external test set 1 (n = 143), and external test set 2 (n = 76). Simulated and acquired contrast-enhanced images demonstrated high similarity (multiscale structural similarity index: 0.82, 0.71, and 0.69 for internal test set, external test set 1, and external test set 2, respectively) with excellent reader agreement of PI-RADS scores (Cohen κ, 0.96; 95% CI: 0.94, 0.98). When simulated contrast-enhanced imaging was added to biparametric MRI, 34 of 323 (10.5%) patients were upgraded to PI-RADS 4 from PI-RADS 3. Conclusion It was feasible to generate simulated contrast-enhanced prostate MRI using deep learning. The simulated and acquired contrast-enhanced MRI scans exhibited high similarity and demonstrated excellent agreement in assessing clinically significant prostate cancer based on PI-RADS, version 2.1. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Neji and Goh in this issue.

Faster Acquisition and Improved Image Quality of T2-Weighted Dixon Breast MRI at 3T Using Deep Learning: A Prospective Study

OBJECTIVE

The aim of this study was to compare image quality features and lesion characteristics between a faster deep learning (DL) reconstructed T2-weighted (T2-w) fast spin-echo (FSE) Dixon sequence with super-resolution (T2DL) and a conventional T2-w FSE Dixon sequence (T2STD) for breast magnetic resonance imaging (MRI).

MATERIALS AND METHODS

This prospective study was conducted between November 2022 and April 2023 using a 3T scanner. Both T2DL and T2STD sequences were acquired for each patient. Quantitative analysis was based on region-of-interest (ROI) measurements of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Qualitative analysis was performed independently by two radiologists using Likert scales to evaluate various image quality features, morphology, and diagnostic confidence for cysts and breast cancers. Reader preference between T2DL and T2STD was assessed via side-by-side comparison, and inter-reader reliability was also analyzed.

RESULTS

Total of 151 women were enrolled, with 140 women (mean age: 52 ± 14 years; 85 cysts and 31 breast cancers) included in the final analysis. The acquisition time was 110 s ± 0 for T2DL compared to 266 s ± 0 for T2STD. SNR and CNR were significantly higher in T2DL (P < 0.001). T2DL was associated with higher image quality scores, reduced noise, and fewer artifacts (P < 0.001). All evaluated anatomical regions (breast and axilla), breast implants, and bone margins were rated higher in T2DL (P ≤ 0.008), except for bone marrow, which scored higher in T2STD (P < 0.001). Scores for conspicuity, sharpness/margins, and microstructure of cysts and breast cancers were higher in T2DL (P ≤ 0.002). Diagnostic confidence for cysts was improved with T2DL (P < 0.001). Readers significantly preferred T2DL over T2STD in side-by-side comparisons (P < 0.001).

CONCLUSION

T2DL effectively corrected for SNR loss caused by accelerated image acquisition and provided a 58% reduction in acquisition time compared to T2STD. This led to fewer artifacts and improved overall image quality. Thus, T2DL is feasible and has the potential to replace conventional T2-w sequences for breast MRI examinations.

Enhancing thin slice 3D T2-weighted prostate MRI with super-resolution deep learning reconstruction: Impact on image quality and PI-RADS assessment

PURPOSES

This study aimed to assess the effectiveness of Super-Resolution Deep Learning Reconstruction (SR-DLR) -a deep learning-based technique that enhances image resolution and quality during MRI reconstruction- in improving the image quality of thin-slice 3D T2-weighted imaging (T2WI) and Prostate Imaging-Reporting and Data System (PI-RADS) assessment in prostate Magnetic Resonance Imaging (MRI).

METHODS

This retrospective study included 33 patients who underwent prostate MRI with SR-DLR between November 2022 and April 2023. Thin-slice 3D-T2WI of the prostate was obtained and reconstructed with and without SR-DLR (matrix: 720 × 720 and 240 × 240, respectively). We calculated the contrast and contrast-to-noise ratio (CNR) between the internal and external glands of the prostate, as well as the slope of pelvic bone and adipose tissue. Two radiologists evaluated qualitative image quality and assessed PI-RADS scores of each reconstruction.

RESULTS

The final analysis included 28 male patients (age range: 47-88 years; mean age: 70.8 years). The CNR with SR-DLR was significantly higher than without SR-DLR (1.93 [IQR: 0.79, 3.83] vs. 1.88 [IQR: 0.63, 3.82], p = 0.002). No significant difference in contrast was observed between images with and without SR-DLR (p = 0.864). The slope with SR-DLR was significantly higher than without SR-DLR (0.21 [IQR: 0.15, 0.25] vs. 0.15 [IQR: 0.12, 0.19], p < 0.01). Qualitative scores for contrast, sharpness, artifacts, and overall image quality were significantly higher with SR-DLR than without SR-DLR (p < 0.05 for all). The kappa values for 2D-T2WI and 3D-T2WI increased from 0.694 and 0.640 to 0.870 and 0.827 with SR-DLR for both readers.

CONCLUSIONS

SR-DLR has the potential to improve image quality and the ability to assess PI-RADS scores in thin-slice 3D-T2WI of the prostate without extending MRI acquisition time.

SUMMARY

Super-Resolution Deep Learning Reconstruction (SR-DLR) significantly improved image quality of thin-slice 3D T2-weighted imaging (T2WI) without extending the acquisition time. Additionally, the PI-RADS scores from 3D-T2WI with SR-DLR demonstrated higher agreement with those from 2D-T2WI.

A Feasibility Study of AI-Assisted Compressed Sensing in Prostate T2-Weighted Imaging

RATIONALE AND OBJECTIVES

To evaluate the image quality and PI-RADS scoring performance of prostate T2-weighted imaging (T2WI) based on AI-assisted compressed sensing (ACS).

MATERIALS AND METHODS

In this prospective study, adult male urological outpatients or inpatients underwent prostate MRI, including T2WI, diffusion-weighted imaging and apparent diffusion coefficient maps. Three accelerated scanning protocols using parallel imaging (PI) and ACS: T2WIPI, T2WIACS1 and T2WIACS2 were evaluated through comparative analysis. Quantitative analysis included signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), slope profile, and edge rise distance (ERD). Image quality was qualitatively assessed using a five-point Likert scale (ranging from 1 = non-diagnostic to 5 = excellent). PI-RADS scores were determined for the largest or most suspicious lesions in each patient. The Friedman test and one-way ANOVA with post hoc tests were utilized for group comparisons, with statistical significance set at P < 0.05.

RESULTS

This study included 40 participants. Compared to PI, ACS reduced acquisition time by over 50%, significantly enhancing the CNR of sagittal and axial T2WI (P < 0.05), significantly improving the image quality of sagittal and axial T2WI (P < 0.05). No significant differences were observed in slope profile, ERD, and PI-RADS scores between groups (P > 0.05).

CONCLUSION

ACS reduced prostate T2WI acquisition time by half while improving image quality without affecting PI-RADS scores.

Ultra-high gradient performance 3-Tesla MRI for super-fast and high-quality prostate imaging: initial experience

OBJECTIVES

To implement and evaluate a super-fast and high-quality biparametric MRI (bpMRI) protocol for prostate imaging acquired at a new ultra-high gradient 3.0-T MRI system.

METHODS

Participants with clinically suspected prostate cancer prospectively underwent a multiparametric MRI (mpMRI) on a new 3.0-T MRI scanner (maximum gradient strength: 200 mT/m, maximum slew rate: 200 T/m/s). The bpMRI protocol was extracted from the full mpMRI protocol, including axial T2-weighted and diffusion-weighted (DWI) sequences (b0/800, b1500). Overall image quality was rated by two readers on a five-point Likert scale from (1) non-diagnostic to (5) excellent. PI-RADS 2.1 scores were assessed by three readers separately for the bpMRI and mpMRI protocols. Cohen's and Fleiss' κ were calculated for PI-RADS agreement between protocols and interrater reliability between readers, respectively.

RESULTS

Seventy-seven male participants (mean age, 66 ± 8 years) were included. Acquisition time of the bpMRI protocol was reduced by 62% (bpMRI: 5 min, 33 ± 21 s; mpMRI: 14 min, 50 ± 42 s). The bpMRI protocol showed excellent overall image quality for both the T2-weighted (median score both readers: 5 [IQR: 4-5]) and DWI (b1500) sequence (median score reader 1: 4 [IQR: 4-5]; reader 2: 4 [IQR: 4-4]). PI-RADS score agreement between protocols was excellent (Cohen's κ range: 0.91-0.95 [95% CI: 0.89, 0.99]) with an overall good interrater reliability (Fleiss' κ, 0.86 [95% CI: 0.80, 0.92]).

CONCLUSION

Ultra-high gradient MRI allows the establishment of a high-quality and rapidly acquired bpMRI with high PI-RADS agreement to a full mpMRI protocol.

TRIALS REGISTRATION

Clinicaltrials.gov, NCT06244680, Registered 06 February 2024, retrospectively registered, https://classic.

CLINICALTRIALS

gov/ct2/show/NCT06244680 .

CRITICAL RELEVANCE STATEMENT

A novel 3.0-Tesla MRI system with an ultra-high gradient performance enabled high-quality biparametric prostate MRI in 5.5 min while achieving excellent PI-RADS agreement with a standard multiparametric protocol.

KEY POINTS

Multi- and biparametric prostate MRIs were prospectively acquired utilizing a maximum gradient of 200 mT/m. Super-fast biparametric MRIs showed excellent image quality and had high PI-RADS agreement with multiparametric MRIs. Implementation of high gradient MRI in clinical routine allows accelerated and high-quality biparametric prostate examinations.

Deep learning-accelerated T2WI of the prostate for transition zone lesion evaluation and extraprostatic extension assessment

This bicenter retrospective analysis included 162 patients who had undergone prostate biopsy following prebiopsy MRI, excluding those with PCa identified only in the peripheral zone (PZ). DLR T2WI achieved a 69% reduction in scan time relative to TSE T2WI. The intermethod agreement between the two T2WI sets in terms of the Prostate Imaging Reporting and Data System (PI-RADS) classification and extraprostatic extension (EPE) grade was measured using the intraclass correlation coefficient (ICC) and diagnostic performance was assessed with the area under the receiver operating characteristic curve (AUC). Clinically significant PCa (csPCa) was found in 74 (45.7%) patients. Both T2WI methods showed high intermethod agreement for the overall PI-RADS classification (ICC: 0.907-0.949), EPE assessment (ICC: 0.925-0.957) and lesion size measurement (ICC: 0.980-0.996). DLR T2WI and TSE T2WI showed similar AUCs (0.666-0.814 versus 0.684-0.832) for predicting EPE. The AUCs for detecting csPCa with DLR T2WI (0.834-0.935) and TSE T2WI (0.891-0.935) were comparable in 139 patients with TZ lesions with no significant differences (P > 0.05). The findings suggest that DLR T2WI is an efficient alternative for TZ lesion assessment, offering reduced scan times without compromising diagnostic accuracy.

Spatial resolution enhancement using deep learning improves chest disease diagnosis based on thick slice CT

CT is crucial for diagnosing chest diseases, with image quality affected by spatial resolution. Thick-slice CT remains prevalent in practice due to cost considerations, yet its coarse spatial resolution may hinder accurate diagnoses. Our multicenter study develops a deep learning synthetic model with Convolutional-Transformer hybrid encoder-decoder architecture for generating thin-slice CT from thick-slice CT on a single center (1576 participants) and access the synthetic CT on three cross-regional centers (1228 participants). The qualitative image quality of synthetic and real thin-slice CT is comparable (p = 0.16). Four radiologists' accuracy in diagnosing community-acquired pneumonia using synthetic thin-slice CT surpasses thick-slice CT (p < 0.05), and matches real thin-slice CT (p > 0.99). For lung nodule detection, sensitivity with thin-slice CT outperforms thick-slice CT (p < 0.001) and comparable to real thin-slice CT (p > 0.05). These findings indicate the potential of our model to generate high-quality synthetic thin-slice CT as a practical alternative when real thin-slice CT is preferred but unavailable.

Advancing clinical MRI exams with artificial intelligence: Japan's contributions and future prospects

In this narrative review, we review the applications of artificial intelligence (AI) into clinical magnetic resonance imaging (MRI) exams, with a particular focus on Japan's contributions to this field. In the first part of the review, we introduce the various applications of AI in optimizing different aspects of the MRI process, including scan protocols, patient preparation, image acquisition, image reconstruction, and postprocessing techniques. Additionally, we examine AI's growing influence in clinical decision-making, particularly in areas such as segmentation, radiation therapy planning, and reporting assistance. By emphasizing studies conducted in Japan, we highlight the nation's contributions to the advancement of AI in MRI. In the latter part of the review, we highlight the characteristics that make Japan a unique environment for the development and implementation of AI in MRI examinations. Japan's healthcare landscape is distinguished by several key factors that collectively create a fertile ground for AI research and development. Notably, Japan boasts one of the highest densities of MRI scanners per capita globally, ensuring widespread access to the exam. Japan's national health insurance system plays a pivotal role by providing MRI scans to all citizens irrespective of socioeconomic status, which facilitates the collection of inclusive and unbiased imaging data across a diverse population. Japan's extensive health screening programs, coupled with collaborative research initiatives like the Japan Medical Imaging Database (J-MID), enable the aggregation and sharing of large, high-quality datasets. With its technological expertise and healthcare infrastructure, Japan is well-positioned to make meaningful contributions to the MRI-AI domain. The collaborative efforts of researchers, clinicians, and technology experts, including those in Japan, will continue to advance the future of AI in clinical MRI, potentially leading to improvements in patient care and healthcare efficiency.

External Validation of a Previously Developed Deep Learning-based Prostate Lesion Detection Algorithm on Paired External and In-House Biparametric MRI Scans

Purpose To evaluate the performance of an artificial intelligence (AI) model in detecting overall and clinically significant prostate cancer (csPCa)-positive lesions on paired external and in-house biparametric MRI (bpMRI) scans and assess performance differences between each dataset. Materials and Methods This single-center retrospective study included patients who underwent prostate MRI at an external institution and were rescanned at the authors' institution between May 2015 and May 2022. A genitourinary radiologist performed prospective readouts on in-house MRI scans following the Prostate Imaging Reporting and Data System (PI-RADS) version 2.0 or 2.1 and retrospective image quality assessments for all scans. A subgroup of patients underwent an MRI/US fusion-guided biopsy. A bpMRI-based lesion detection AI model previously developed using a completely separate dataset was tested on both MRI datasets. Detection rates were compared between external and in-house datasets with use of the paired comparison permutation tests. Factors associated with AI detection performance were assessed using multivariable generalized mixed-effects models, incorporating features selected through forward stepwise regression based on the Akaike information criterion. Results The study included 201 male patients (median age, 66 years [IQR, 62-70 years]; prostate-specific antigen density, 0.14 ng/mL2 [IQR, 0.10-0.22 ng/mL2]) with a median interval between external and in-house MRI scans of 182 days (IQR, 97-383 days). For intraprostatic lesions, AI detected 39.7% (149 of 375) on external and 56.0% (210 of 375) on in-house MRI scans (P < .001). For csPCa-positive lesions, AI detected 61% (54 of 89) on external and 79% (70 of 89) on in-house MRI scans (P < .001). On external MRI scans, better overall lesion detection was associated with a higher PI-RADS score (odds ratio [OR] = 1.57; P = .005), larger lesion diameter (OR = 3.96; P < .001), better diffusion-weighted MRI quality (OR = 1.53; P = .02), and fewer lesions at MRI (OR = 0.78; P = .045). Better csPCa detection was associated with a shorter MRI interval between external and in-house scans (OR = 0.58; P = .03) and larger lesion size (OR = 10.19; P < .001). Conclusion The AI model exhibited modest performance in identifying both overall and csPCa-positive lesions on external bpMRI scans. Keywords: MR Imaging, Urinary, Prostate Supplemental material is available for this article. © RSNA, 2024.

Performance of an ultra-fast deep-learning accelerated MRI screening protocol for prostate cancer compared to a standard multiparametric protocol

OBJECTIVES

To establish and evaluate an ultra-fast MRI screening protocol for prostate cancer (PCa) in comparison to the standard multiparametric (mp) protocol, reducing scan time and maintaining adequate diagnostic performance.

MATERIALS AND METHODS

This prospective single-center study included consecutive biopsy-naïve patients with suspected PCa between December 2022 and March 2023. A PI-RADSv2.1 conform mpMRI protocol was acquired in a 3 T scanner (scan time: 25 min 45 sec). In addition, two deep-learning (DL) accelerated sequences (T2- and diffusion-weighted) were acquired, serving as a screening protocol (scan time: 3 min 28 sec). Two readers evaluated image quality and the probability of PCa regarding PI-RADSv2.1 scores in two sessions. The diagnostic performance of the screening protocol with mpMRI serving as the reference standard was derived. Inter- and intra-reader agreements were evaluated using weighted kappa statistics.

RESULTS

We included 77 patients with 97 lesions (mean age: 66 years; SD: 7.7). Diagnostic performance of the screening protocol was excellent with a sensitivity and specificity of 100%/100% and 89%/98% (cut-off ≥ PI-RADS 4) for reader 1 (R1) and reader 2 (R2), respectively. Mean image quality was 3.96 (R1) and 4.35 (R2) for the standard protocol vs. 4.74 and 4.57 for the screening protocol (p < 0.05). Inter-reader agreement was moderate (κ: 0.55) for the screening protocol and substantial (κ: 0.61) for the multiparametric protocol.

CONCLUSION

The ultra-fast screening protocol showed similar diagnostic performance and better imaging quality compared to the mpMRI in under 15% of scan time, improving efficacy and enabling the implementation of screening protocols in clinical routine.

CLINICAL RELEVANCE STATEMENT

The ultra-fast protocol enables examinations without contrast administration, drastically reducing scan time to 3.5 min with similar diagnostic performance and better imaging quality. This facilitates patient-friendly, efficient examinations and addresses the conflict of increasing demand for examinations at currently exhausted capacities.

KEY POINTS

Time-consuming MRI protocols are in conflict with an expected increase in examinations required for prostate cancer screening. An ultra-fast MRI protocol shows similar performance and better image quality compared to the standard protocol. Deep-learning acceleration facilitates efficient and patient-friendly examinations, thus improving prostate cancer screening capacity.

Deep learning super-resolution reconstruction for fast and high-quality cine cardiovascular magnetic resonance

OBJECTIVES

To compare standard-resolution balanced steady-state free precession (bSSFP) cine images with cine images acquired at low resolution but reconstructed with a deep learning (DL) super-resolution algorithm.

MATERIALS AND METHODS

Cine cardiovascular magnetic resonance (CMR) datasets (short-axis and 4-chamber views) were prospectively acquired in healthy volunteers and patients at normal (cineNR: 1.89 × 1.96 mm2, reconstructed at 1.04 × 1.04 mm2) and at a low-resolution (2.98 × 3.00 mm2, reconstructed at 1.04 × 1.04 mm2). Low-resolution images were reconstructed using compressed sensing DL denoising and resolution upscaling (cineDL). Left ventricular ejection fraction (LVEF), end-diastolic volume index (LVEDVi), and strain were assessed. Apparent signal-to-noise (aSNR) and contrast-to-noise ratios (aCNR) were calculated. Subjective image quality was assessed on a 5-point Likert scale. Student's paired t-test, Wilcoxon matched-pairs signed-rank-test, and intraclass correlation coefficient (ICC) were used for statistical analysis.

RESULTS

Thirty participants were analyzed (37 ± 16 years; 20 healthy volunteers and 10 patients). Short-axis views whole-stack acquisition duration of cineDL was shorter than cineNR (57.5 ± 8.7 vs 98.7 ± 12.4 s; p < 0.0001). No differences were noted for: LVEF (59 ± 7 vs 59 ± 7%; ICC: 0.95 [95% confidence interval: 0.94, 0.99]; p = 0.17), LVEDVi (85.0 ± 13.5 vs 84.4 ± 13.7 mL/m2; ICC: 0.99 [0.98, 0.99]; p = 0.12), longitudinal strain (-19.5 ± 4.3 vs -19.8 ± 3.9%; ICC: 0.94 [0.88, 0.97]; p = 0.52), short-axis aSNR (81 ± 49 vs 69 ± 38; p = 0.32), aCNR (53 ± 31 vs 45 ± 27; p = 0.33), or subjective image quality (5.0 [IQR 4.9, 5.0] vs 5.0 [IQR 4.7, 5.0]; p = 0.99).

CONCLUSION

Deep-learning reconstruction of cine images acquired at a lower spatial resolution led to a decrease in acquisition times of 42% with shorter breath-holds without affecting volumetric results or image quality.

KEY POINTS

Question Cine CMR acquisitions are time-intensive and vulnerable to artifacts. Findings Low-resolution upscaled reconstructions using DL super-resolution decreased acquisition times by 35-42% without a significant difference in volumetric results or subjective image quality. Clinical relevance DL super-resolution reconstructions of bSSFP cine images acquired at a lower spatial resolution reduce acquisition times while preserving diagnostic accuracy, improving the clinical feasibility of cine imaging by decreasing breath hold duration.

Alternating low-rank tensor reconstruction for improved multiparametric mapping with cardiovascular MR Multitasking

PURPOSE

To develop a novel low-rank tensor reconstruction approach leveraging the complete acquired data set to improve precision and repeatability of multiparametric mapping within the cardiovascular MR Multitasking framework.

METHODS

A novel approach that alternated between estimation of temporal components and spatial components using the entire data set acquired (i.e., including navigator data and imaging data) was developed to improve reconstruction. The precision and repeatability of the proposed approach were evaluated on numerical simulations, 10 healthy subjects, and 10 cardiomyopathy patients at multiple scan times for 2D myocardial T1/T2 mapping with MR Multitasking and were compared with those of the previous navigator-derived fixed-basis approach.

RESULTS

In numerical simulations, the proposed approach outperformed the previous fixed-basis approach with lower T1 and T2 error against the ground truth at all scan times studied and showed better motion fidelity. In human subjects, the proposed approach showed no significantly different sharpness or T1/T2 measurement and significantly improved T1 precision by 20%-25%, T2 precision by 10%-15%, T1 repeatability by about 30%, and T2 repeatability by 25%-35% at 90-s and 50-s scan times The proposed approach at the 50-s scan time also showed comparable results with that of the previous fixed-basis approach at the 90-s scan time.

CONCLUSION

The proposed approach improved precision and repeatability for quantitative imaging with MR Multitasking while maintaining comparable motion fidelity, T1/T2 measurement, and septum sharpness and had the potential for further reducing scan time from 90 s to 50 s.

Fully automated segmentation and volumetric measurement of ocular adnexal lymphoma by deep learning-based self-configuring nnU-net on multi-sequence MRI: a multi-center study

PURPOSE

To evaluate nnU-net's performance in automatically segmenting and volumetrically measuring ocular adnexal lymphoma (OAL) on multi-sequence MRI.

METHODS

We collected T1-weighted (T1), T2-weighted and T1-weighted contrast-enhanced images with/without fat saturation (T2_FS/T2_nFS, T1c_FS/T1c_nFS) of OAL from four institutions. Two radiologists manually annotated lesions as the ground truth using ITK-SNAP. A deep learning framework, nnU-net, was developed and trained using two models. Model 1 was trained on T1, T2, and T1c, while Model 2 was trained exclusively on T1 and T2. A 5-fold cross-validation was utilized in the training process. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), sensitivity, and positive prediction value (PPV). Volumetric assessment was performed using Bland-Altman plots and Lin's concordance correlation coefficient (CCC).

RESULTS

A total of 147 patients from one center were selected as training set and 33 patients from three centers were regarded as test set. For both Model 1 and 2, nnU-net demonstrated outstanding segmentation performance on T2_FS with DSC of 0.80-0.82, PPV of 84.5-86.1%, and sensitivity of 77.6-81.2%, respectively. Model 2 failed to detect 19 cases of T1c, whereas the DSC, PPV, and sensitivity for T1_nFS were 0.59, 91.2%, and 51.4%, respectively. Bland-Altman plots revealed minor tumor volume differences with 0.22-1.24 cm3 between nnU-net prediction and ground truth on T2_FS. The CCC were 0.96 and 0.93 in Model 1 and 2 for T2_FS images, respectively.

CONCLUSION

The nnU-net offered excellent performance in automated segmentation and volumetric assessment in MRI of OAL, particularly on T2_FS images.

Recent trends in AI applications for pelvic MRI: a comprehensive review

Magnetic resonance imaging (MRI) is an essential tool for evaluating pelvic disorders affecting the prostate, bladder, uterus, ovaries, and/or rectum. Since the diagnostic pathway of pelvic MRI can involve various complex procedures depending on the affected organ, the Reporting and Data System (RADS) is used to standardize image acquisition and interpretation. Artificial intelligence (AI), which encompasses machine learning and deep learning algorithms, has been integrated into both pelvic MRI and the RADS, particularly for prostate MRI. This review outlines recent developments in the use of AI in various stages of the pelvic MRI diagnostic pathway, including image acquisition, image reconstruction, organ and lesion segmentation, lesion detection and classification, and risk stratification, with special emphasis on recent trends in multi-center studies, which can help to improve the generalizability of AI.

The importance and future of prostate MRI report templates: improving oncological care

The radiologist's report is crucial for guiding care post-imaging, with ongoing advancements in report construction. Recent studies across various modalities and organ systems demonstrate enhanced clarity and communication through structured reports. This article will explain the benefits of disease-state specific reporting templates using prostate MRI as the model system. We identify key reporting components for prostate cancer detection and staging as well as imaging in active surveillance and following therapy. We discuss relevant reporting systems including PI-QUAL, PI-RADS, PRECISE, PI-RR and PI-FAB systems. Additionally, we examine optimal reporting structure including disruptive technologies such as graphical reporting and using artificial intelligence to improve report clarity and applicability.

MRI versus Dual-Energy CT in Local-Regional Staging of Gastric Cancer

Background Preoperative local-regional tumor staging of gastric cancer (GC) is critical for appropriate treatment planning. The comparative accuracy of multiparametric MRI (mpMRI) versus dual-energy CT (DECT) for staging of GC is not known. Purpose To compare the diagnostic accuracy of personalized mpMRI with that of DECT for local-regional T and N staging in patients with GC receiving curative surgical intervention. Materials and Methods Patients with GC who underwent gastric mpMRI and DECT before gastrectomy with lymphadenectomy were eligible for this single-center prospective noninferiority study between November 2021 and September 2022. mpMRI comprised T2-weighted imaging, multiorientational zoomed diffusion-weighted imaging, and extradimensional volumetric interpolated breath-hold examination dynamic contrast-enhanced imaging. Dual-phase DECT images were reconstructed at 40 keV and standard 120 kVp-like images. Using gastrectomy specimens as the reference standard, the diagnostic accuracy of mpMRI and DECT for T and N staging was compared by six radiologists in a pairwise blinded manner. Interreader agreement was assessed using the weighted κ and Kendall W statistics. The McNemar test was used for head-to-head accuracy comparisons between DECT and mpMRI. Results This study included 202 participants (mean age, 62 years ± 11 [SD]; 145 male). The interreader agreement of the six readers for T and N staging of GC was excellent for both mpMRI (κ = 0.89 and 0.85, respectively) and DECT (κ = 0.86 and 0.84, respectively). Regardless of reader experience, higher accuracy was achieved with mpMRI than with DECT for both T (61%-77% vs 50%-64%; all P < .05) and N (54%-68% vs 51%-58%; P = .497-.005) staging, specifically T1 (83% vs 65%) and T4a (78% vs 68%) tumors and N1 (41% vs 24%) and N3 (64% vs 45%) nodules (all P < .05). Conclusion Personalized mpMRI was superior in T staging and noninferior or superior in N staging compared with DECT for patients with GC. Clinical trial registration no. NCT05508126 © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Méndez and Martín-Garre in this issue.

Deep learning reconstruction for lumbar spine MRI acceleration: a prospective study

BACKGROUND

We compared magnetic resonance imaging (MRI) turbo spin-echo images reconstructed using a deep learning technique (TSE-DL) with standard turbo spin-echo (TSE-SD) images of the lumbar spine regarding image quality and detection performance of common degenerative pathologies.

METHODS

This prospective, single-center study included 31 patients (15 males and 16 females; aged 51 ± 16 years (mean ± standard deviation)) who underwent lumbar spine exams with both TSE-SD and TSE-DL acquisitions for degenerative spine diseases. Images were analyzed by two radiologists and assessed for qualitative image quality using a 4-point Likert scale, quantitative signal-to-noise ratio (SNR) of anatomic landmarks, and detection of common pathologies. Paired-sample t, Wilcoxon, and McNemar tests, unweighted/linearly weighted Cohen κ statistics, and intraclass correlation coefficients were used.

RESULTS

Scan time for TSE-DL and TSE-SD protocols was 2:55 and 5:17 min:s, respectively. The overall image quality was either significantly higher for TSE-DL or not significantly different between TSE-SD and TSE-DL. TSE-DL demonstrated higher SNR and subject noise scores than TSE-SD. For pathology detection, the interreader agreement was substantial to almost perfect for TSE-DL, with κ values ranging from 0.61 to 1.00; the interprotocol agreement was almost perfect for both readers, with κ values ranging from 0.84 to 1.00. There was no significant difference in the diagnostic confidence or detection rate of common pathologies between the two sequences (p ≥ 0.081).

CONCLUSIONS

TSE-DL allowed for a 45% reduction in scan time over TSE-SD in lumbar spine MRI without compromising the overall image quality and showed comparable detection performance of common pathologies in the evaluation of degenerative lumbar spine changes.

RELEVANCE STATEMENT

Deep learning-reconstructed lumbar spine MRI protocol enabled a 45% reduction in scan time compared with conventional reconstruction, with comparable image quality and detection performance of common degenerative pathologies.

KEY POINTS

• Lumbar spine MRI with deep learning reconstruction has broad application prospects. • Deep learning reconstruction of lumbar spine MRI saved 45% scan time without compromising overall image quality. • When compared with standard sequences, deep learning reconstruction showed similar detection performance of common degenerative lumbar spine pathologies.

AI in imaging: the regulatory landscape

Artificial intelligence (AI) methods have been applied to medical imaging for several decades, but in the last few years, the number of publications and the number of AI-enabled medical devices coming on the market have significantly increased. While some AI-enabled approaches are proving very valuable, systematic reviews of the AI imaging field identify significant weaknesses in a significant proportion of the literature. Medical device regulators have recently become more proactive in publishing guidance documents and recognizing standards that will require that the development and validation of AI-enabled medical devices need to be more rigorous than required for tradition "rule-based" software. In particular, developers are required to better identify and mitigate risks (such as bias) that arise in AI-enabled devices, and to ensure that the devices are validated in a realistic clinical setting to ensure their output is clinically meaningful. While this evolving regulatory landscape will mean that device developers will take longer to bring novel AI-based medical imaging devices to market, such additional rigour is necessary to address existing weaknesses in the field and ensure that patients and healthcare professionals can trust AI-enabled devices. There would also be benefits in the academic community taking into account this regulatory framework, to improve the quality of the literature and make it easier for academically developed AI tools to make the transition to medical devices that impact healthcare.

Deep learning denoising reconstruction for improved image quality in fetal cardiac cine MRI

Purpose

This study aims to evaluate deep learning (DL) denoising reconstructions for image quality improvement of Doppler ultrasound (DUS)-gated fetal cardiac MRI in congenital heart disease (CHD).

Methods

Twenty-five fetuses with CHD (mean gestational age: 35 ± 1 weeks) underwent fetal cardiac MRI at 3T. Cine imaging was acquired using a balanced steady-state free precession (bSSFP) sequence with Doppler ultrasound gating. Images were reconstructed using both compressed sensing (bSSFP CS) and a pre-trained convolutional neural network trained for DL denoising (bSSFP DL). Images were compared qualitatively based on a 5-point Likert scale (from 1 = non-diagnostic to 5 = excellent) and quantitatively by calculating the apparent signal-to-noise ratio (aSNR) and contrast-to-noise ratio (aCNR). Diagnostic confidence was assessed for the atria, ventricles, foramen ovale, valves, great vessels, aortic arch, and pulmonary veins.

Results

Fetal cardiac cine MRI was successful in 23 fetuses (92%), with two studies excluded due to extensive fetal motion. The image quality of bSSFP DL cine reconstructions was rated superior to standard bSSFP CS cine images in terms of contrast [3 (interquartile range: 2-4) vs. 5 (4-5), P < 0.001] and endocardial edge definition [3 (2-4) vs. 4 (4-5), P < 0.001], while the extent of artifacts was found to be comparable [4 (3-4.75) vs. 4 (3-4), P = 0.40]. bSSFP DL images had higher aSNR and aCNR compared with the bSSFP CS images (aSNR: 13.4 ± 6.9 vs. 8.3 ± 3.6, P < 0.001; aCNR: 26.6 ± 15.8 vs. 14.4 ± 6.8, P < 0.001). Diagnostic confidence of the bSSFP DL images was superior for the evaluation of cardiovascular structures (e.g., atria and ventricles: P = 0.003).

Conclusion

DL image denoising provides superior quality for DUS-gated fetal cardiac cine imaging of CHD compared to standard CS image reconstruction.

Deep learning-based noise reduction preserves quantitative MRI biomarkers in patients with brain tumors

The use of relaxometry and Diffusion-Tensor Imaging sequences for brain tumor assessment is limited by their long acquisition time. We aim to test the effect of a denoising algorithm based on a Deep Learning Reconstruction (DLR) technique on quantitative MRI parameters while reducing scan time. In 22 consecutive patients with brain tumors, DLR applied to fast and noisy MR sequences preserves the mean values of quantitative parameters (Fractional anisotropy, mean Diffusivity, T1 and T2-relaxation time) and produces maps with higher structural similarity compared to long duration sequences. This could promote wider use of these biomarkers in clinical setting.