Diagnostic performance of deep learning-based reconstruction algorithm in 3D MR neurography

MR Neurography of the Lumbosacral Plexus: Technique and Disease Patterns

The lumbosacral plexus (LSP) comprises a complex network of nerves supplying the pelvis and lower extremities and may be affected by a wide range of diseases. Lumbosacral plexopathy can be challenging to diagnose due to overlapping clinical presentations and difficulty performing electrodiagnostic testing of the deep pelvic structures. MRI-more specifically, MR neurography (MRN)-can readily depict most LSP segments. MRN techniques, preferably performed at 3.0 T, continue to evolve, with most protocols including two-dimensional and optionally three-dimensional, heavily T2-weighted fat-suppressed sequences. This article provides technical tips for optimizing LSP MRN, as well as an overview of various LSP-related pathologic conditions, with accompanying illustrative examples. ©RSNA, 2025 Supplemental material is available for this article. See the invited commentary by Chhabra in this issue.

Magnetic Resonance Imaging of the Peripheral Nerves and Fascicles of the Knee Using Double Echo Steady State Sequence at 7 Tesla

OBJECTIVE

To evaluate the applicability of the double echo steady state (DESS) sequence at 7 tesla (7T) for high-resolution imaging of the peripheral nerves and fascicles of the knee.

MATERIALS AND METHODS

We prospectively included 32 healthy participants (mean age 39 ± 14 years, 20 females). The patients underwent 7T magnetic resonance imaging (MRI) of the knee using proton density turbo spin-echo fat suppression (PD-TSE FS), three-dimensional DESS (3D-DESS), and higher in-plane resolution DESS (DESSHR) sequences. The signal-to-noise ratios (SNRs) of the peroneal nerve (PN) and tibial nerve (TN) and contrast-to-noise ratios (CNRs) between the nerves and adjacent fat, vessels, and muscles were quantitatively measured by two readers and averaged. Five radiologists qualitatively assessed the overall image quality, pulsatile flow artifacts, and visualization of the PN and its branches, the TN, and the saphenous nerve (SN) using a five-point Likert-type scale, with the results averaged. The results of the three image sequences were compared.

RESULTS

The SNR for the TNs in the DESSHR sequence were lower than those in the PD-TSE FS (P < 0.001) and 3D-DESS (P = 0.024) sequences, whereas the SNR for the PNs did not differ significantly across the three sequences. The DESSHR sequence exhibited superior TN- or PN-to-fat and PN-to-muscle CNR values when compared with the PD-TSE FS and 3D-DESS sequences (P ≤ 0.016). The TN- and PN-to-vessel CNR values in the DESSHR and PD-TSE FS sequences were higher than those in the 3D-DESS sequence (P ≤ 0.001). Qualitative assessments revealed fewer pulsatile artifacts in 3D-DESS than in DESSHR and PD-TSE FS (P < 0.001), with DESSHR exhibiting fewer artifacts than PD-TSE FS (P = 0.035). DESSHR excelled in visualizing the common PN, TN, and SN when compared with other sequences (P < 0.001), whereas 3D-DESS provided superior visualization of PN branches when compared with other sequences (P ≤ 0.042).

CONCLUSION

The DESS sequence at 7T MRI enhances visualization of peripheral nerves and fascicular structures around the knee.

Imaging of Peripheral Nerves: AJR Expert Panel Narrative Review

Peripheral nerve imaging provides information that can be critical to the diagnosis, staging, and management of peripheral neuropathies. MRI and ultrasound are the imaging modalities of choice for clinical evaluation of the peripheral nerves given their high soft-tissue contrast and high resolution, respectively. This AJR Expert Panel Narrative Review describes MRI- and ultrasound-based techniques for peripheral nerve imaging; highlights considerations for imaging in the settings of trauma, entrapment syndromes, diffuse inflammatory neuropathies, and tumor; and discusses image-guided nerve interventions, focusing on nerve blocks and ablation.

Three-Dimensional Magnetic Resonance Imaging in the Musculoskeletal System: Clinical Applications and Opportunities to Improve Imaging Speed and Resolution

ABSTRACT

Although conventional 2-dimensional magnetic resonance (MR) sequences have traditionally comprised the foundational imaging strategy for visualization of musculoskeletal anatomy and pathology, the emergence of isotropic volumetric 3-dimensional sequences offers to advance musculoskeletal evaluation with comparatively similar image quality and diagnostic performance, shorter acquisition times, and the added advantages of improved spatial resolution and multiplanar reformation capability. The purpose of this review article is to summarize the available 3-dimensional MR sequences and their role in the management of patients with musculoskeletal disorders, including sports imaging, rheumatologic conditions, peripheral nerve imaging, bone and soft tissue tumor imaging, and whole-body MR imaging.

Evaluation of Image Quality and Scan Time Efficiency in Accelerated 3D T1-Weighted Pediatric Brain MRI Using Deep Learning-Based Reconstruction

OBJECTIVE

This study evaluated the effect of an accelerated three-dimensional (3D) T1-weighted pediatric brain MRI protocol using a deep learning (DL)-based reconstruction algorithm on scan time and image quality.

MATERIALS AND METHODS

This retrospective study included 46 pediatric patients who underwent conventional and accelerated, pre- and post-contrast, 3D T1-weighted brain MRI using a 3T scanner (SIGNA Premier; GE HealthCare) at a single tertiary referral center between March 1, 2023, and April 30, 2023. Conventional scans were reconstructed using intensity Filter A (Conv), whereas accelerated scans were reconstructed using intensity Filter A (Fast_A) and a DL-based algorithm (Fast_DL). Image quality was assessed quantitatively based on the coefficient of variation, relative contrast, apparent signal-to-noise ratio (aSNR), and apparent contrast-to-noise ratio (aCNR) and qualitatively according to radiologists' ratings of overall image quality, artifacts, noisiness, gray-white matter differentiation, and lesion conspicuity.

RESULTS

The acquisition times for the pre- and post-contrast scans were 191 and 135 seconds, respectively, for the conventional scan. With the accelerated protocol, these were reduced to 135 and 80 seconds, achieving time reductions of 29.3% and 40.7%, respectively. DL-based reconstruction significantly reduced the coefficient of variation, improved the aSNR, aCNR, and overall image quality, and reduced the number of artifacts compared with the conventional acquisition method (all P < 0.05). However, the lesion conspicuity remained similar between the two protocols.

CONCLUSION

Utilizing a DL-based reconstruction algorithm in accelerated 3D T1-weighted pediatric brain MRI can significantly shorten the acquisition time, enhance image quality, and reduce artifacts, making it a viable option for pediatric imaging.

Deep learning reconstruction of zero-echo time sequences to improve visualization of osseous structures and associated pathologies in MRI of cervical spine

OBJECTIVES

To determine whether deep learning-based reconstructions of zero-echo-time (ZTE-DL) sequences enhance image quality and bone visualization in cervical spine MRI compared to traditional zero-echo-time (ZTE) techniques, and to assess the added value of ZTE-DL sequences alongside standard cervical spine MRI for comprehensive pathology evaluation.

METHODS

In this retrospective study, 52 patients underwent cervical spine MRI using ZTE, ZTE-DL, and T2-weighted 3D sequences on a 1.5-Tesla scanner. ZTE-DL sequences were reconstructed from raw data using the AirReconDL algorithm. Three blinded readers independently evaluated image quality, artifacts, and bone delineation on a 5-point Likert scale. Cervical structures and pathologies, including soft tissue and bone components in spinal canal and neural foraminal stenosis, were analyzed. Image quality was quantitatively assessed by signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR).

RESULTS

Mean image quality scores were 2.0 ± 0.7 for ZTE and 3.2 ± 0.6 for ZTE-DL, with ZTE-DL exhibiting fewer artifacts and superior bone delineation. Significant differences were observed between T2-weighted and ZTE-DL sequences for evaluating intervertebral space, anterior osteophytes, spinal canal, and neural foraminal stenosis (p < 0.05), with ZTE-DL providing more accurate assessments. ZTE-DL also showed improved evaluation of the osseous components of neural foraminal stenosis compared to ZTE (p < 0.05).

CONCLUSIONS

ZTE-DL sequences offer superior image quality and bone visualization compared to ZTE sequences and enhance standard cervical spine MRI in assessing bone involvement in spinal canal and neural foraminal stenosis.

CRITICAL RELEVANCE STATEMENT

Deep learning-based reconstructions improve zero-echo-time sequences in cervical spine MRI by enhancing image quality and bone visualization. This advancement offers additional insights for assessing bone involvement in spinal canal and neural foraminal stenosis, advancing clinical radiology practice.

KEY POINTS

Conventional MRI encounters challenges with osseous structures due to low signal-to-noise ratio. Zero-echo-time (ZET) sequences offer CT-like images of the C-spine but with lower quality. Deep learning reconstructions improve image quality of zero-echo-time sequences. ZTE sequences with deep learning reconstructions refine cervical spine osseous pathology assessment. These sequences aid assessment of bone involvement in spinal and foraminal stenosis.

Enhanced bone assessment of the shoulder using zero-echo time MRI with deep-learning image reconstruction

OBJECTIVES

To assess a deep learning-based reconstruction algorithm (DLRecon) in zero echo-time (ZTE) MRI of the shoulder at 1.5 Tesla for improved delineation of osseous findings.

METHODS

In this retrospective study, 63 consecutive exams of 52 patients (28 female) undergoing shoulder MRI at 1.5 Tesla in clinical routine were included. Coronal 3D isotropic radial ZTE pulse sequences were acquired in the standard MR shoulder protocol. In addition to standard-of-care (SOC) image reconstruction, the same raw data was reconstructed with a vendor-supplied prototype DLRecon algorithm. Exams were classified into three subgroups: no pathological findings, degenerative changes, and posttraumatic changes, respectively. Two blinded readers performed bone assessment on a 4-point scale (0-poor, 3-perfect) by qualitatively grading image quality features and delineation of osseous pathologies including diagnostic confidence in the respective subgroups. Quantitatively, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of bone were measured. Qualitative variables were compared using the Wilcoxon signed-rank test for ordinal data and the McNemar test for dichotomous variables; quantitative measures were compared with Student's t-testing.

RESULTS

DLRecon scored significantly higher than SOC in all visual metrics of image quality (all, p < 0.03), except in the artifact category (p = 0.37). DLRecon also received superior qualitative scores for delineation of osseous pathologies and diagnostic confidence (p ≤ 0.03). Quantitatively, DLRecon achieved superior CNR (95 CI [1.4-3.1]) and SNR (95 CI [15.3-21.5]) of bone than SOC (p < 0.001).

CONCLUSION

DLRecon enhanced image quality in ZTE MRI and improved delineation of osseous pathologies, allowing for increased diagnostic confidence in bone assessment.

Deep learning-based pseudo-CT synthesis from zero echo time MR sequences of the pelvis

OBJECTIVES

To generate pseudo-CT (pCT) images of the pelvis from zero echo time (ZTE) MR sequences and compare them to conventional CT.

METHODS

Ninety-one patients were prospectively scanned with CT and MRI including ZTE sequences of the pelvis. Eleven ZTE image volumes were excluded due to implants and severe B1 field inhomogeneity. Out of the 80 data sets, 60 were used to train and update a deep learning (DL) model for pCT image synthesis from ZTE sequences while the remaining 20 cases were selected as an evaluation cohort. CT and pCT images were assessed qualitatively and quantitatively by two readers.

RESULTS

Mean pCT ratings of qualitative parameters were good to perfect (2-3 on a 4-point scale). Overall intermodality agreement between CT and pCT was good (ICC = 0.88 (95% CI: 0.85-0.90); p < 0.001) with excellent interreader agreements for pCT (ICC = 0.91 (95% CI: 0.88-0.93); p < 0.001). Most geometrical measurements did not show any significant difference between CT and pCT measurements (p > 0.05) with the exception of transverse pelvic diameter measurements and lateral center-edge angle measurements (p = 0.001 and p = 0.002, respectively). Image quality and tissue differentiation in CT and pCT were similar without significant differences between CT and pCT CNRs (all p > 0.05).

CONCLUSIONS

Using a DL-based algorithm, it is possible to synthesize pCT images of the pelvis from ZTE sequences. The pCT images showed high bone depiction quality and accurate geometrical measurements compared to conventional CT. CRITICAL RELEVANCE STATEMENT: pCT images generated from MR sequences allow for high accuracy in evaluating bone without the need for radiation exposure. Radiological applications are broad and include assessment of inflammatory and degenerative bone disease or preoperative planning studies.

KEY POINTS

pCT, based on DL-reconstructed ZTE MR images, may be comparable with true CT images. Overall, the intermodality agreement between CT and pCT was good with excellent interreader agreements for pCT. Geometrical measurements and tissue differentiation were similar in CT and pCT images.

Improved 3D DESS MR neurography of the lumbosacral plexus with deep learning and geometric image combination reconstruction

OBJECTIVE

To evaluate the impact of deep learning (DL) reconstruction in enhancing image quality and nerve conspicuity in LSP MRN using DESS sequences. Additionally, a geometric image combination (GIC) method to improve DESS signals' combination was proposed.

MATERIALS AND METHODS

Adult patients undergoing 3.0 Tesla LSP MRN with DESS were prospectively enrolled. The 3D DESS echoes were separately reconstructed with and without DL and DL-GIC combined reconstructions. In a subset of patients, 3D T2-weighted short tau inversion recovery (STIR-T2w) sequences were also acquired. Three radiologists rated 4 image stacks ('DESS S2', 'DESS S2 DL', 'DESS GIC DL' and 'STIR-T2w DL') for bulk motion, vascular suppression, nerve fascicular architecture, and overall nerve conspicuity. Relative SNR, nerve-to-muscle, -fat, and -vessel contrast ratios were measured. Statistical analysis included ANOVA and Wilcoxon signed-rank tests. p < 0.05 was considered statistically significant.

RESULTS

Forty patients (22 females; mean age = 48.6 ± 18.5 years) were enrolled. Quantitatively, 'DESS GIC DL' demonstrated superior relative SNR (p < 0.001), while 'DESS S2 DL' exhibited superior nerve-to-background contrast ratio (p value range: 0.002 to < 0.001). Qualitatively, DESS provided superior vascular suppression and depiction of sciatic nerve fascicular architecture but more bulk motion as compared to 'STIR-T2w DL'. 'DESS GIC DL' demonstrated better nerve visualization for several smaller, distal nerve segments than 'DESS S2 DL' and 'STIR-T2w DL'.

CONCLUSION

Application of a DL reconstruction with geometric image combination in DESS MRN improves nerve conspicuity of the LSP, especially for its smaller branch nerves.

Thin-slice elbow MRI with deep learning reconstruction: Superior diagnostic performance of elbow ligament pathologies

PURPOSE

With the slice thickness routinely used in elbow MRI, small or subtle lesions may be overlooked or misinterpreted as insignificant. To compare 1 mm slice thickness MRI (1 mm MRI) with deep learning reconstruction (DLR) to 3 mm slice thickness MRI (3 mm MRI) without/with DLR, and 1 mm MRI without DLR regarding image quality and diagnostic performance for elbow tendons and ligaments.

METHODS

This retrospective study included 53 patients between February 2021 and January 2022, who underwent 3 T elbow MRI, including T2-weighted fat-saturated coronal 3 mm and 1 mm MRI without/with DLR. Two radiologists independently assessed four MRI scans for image quality and artefacts, and identified the pathologies of the five elbow tendons and ligaments. In 19 patients underwent elbow surgery after elbow MRI, diagnostic performance was evaluated using surgical records as a reference standard.

RESULTS

For both readers, 3 mm MRI with DLR had significant higher image quality scores than 3 mm MRI without DLR and 1 mm MRI with DLR (all P < 0.01). For common extensor tendon and elbow ligament pathologies, 1 mm MRI with DLR showed the highest number of pathologies for both readers. The 1 mm MRI with DLR had the highest kappa values for all tendons and ligaments. For reader 1, 1 mm MRI with DLR showed superior diagnostic performance than 3 mm MRI without/with DLR. For reader 2, 1 mm MRI with DLR showed the highest diagnostic performance; however, there was no significant difference.

CONCLUSIONS

One mm MRI with DLR showed the highest diagnostic performance for evaluating elbow tendon and ligament pathologies, with similar subjective image qualities and artefacts.

Optimized 3D brachial plexus MR neurography using deep learning reconstruction

OBJECTIVE

To evaluate whether 'fast,' unilateral, brachial plexus, 3D magnetic resonance neurography (MRN) acquisitions with deep learning reconstruction (DLR) provide similar image quality to longer, 'standard' scans without DLR.

MATERIALS AND METHODS

An IRB-approved prospective cohort of 30 subjects (13F; mean age = 50.3 ± 17.8y) underwent clinical brachial plexus 3.0 T MRN with 3D oblique-coronal STIR-T2-weighted-FSE. 'Standard' and 'fast' scans (time reduction = 23-48%, mean = 33%) were reconstructed without and with DLR. Evaluation of signal-to-noise ratio (SNR) and edge sharpness was performed for 4 image stacks: 'standard non-DLR,' 'standard DLR,' 'fast non-DLR,' and 'fast DLR.' Three raters qualitatively evaluated 'standard non-DLR' and 'fast DLR' for i) bulk motion (4-point scale), ii) nerve conspicuity of proximal and distal suprascapular and axillary nerves (5-point scale), and iii) nerve signal intensity, size, architecture, and presence of a mass (binary). ANOVA or Wilcoxon signed rank test compared differences. Gwet's agreement coefficient (AC2) assessed inter-rater agreement.

RESULTS

Quantitative SNR and edge sharpness were superior for DLR versus non-DLR (SNR by + 4.57 to + 6.56 [p < 0.001] for 'standard' and + 4.26 to + 4.37 [p < 0.001] for 'fast;' sharpness by + 0.23 to + 0.52/pixel for 'standard' [p < 0.018] and + 0.21 to + 0.25/pixel for 'fast' [p < 0.003]) and similar between 'standard non-DLR' and 'fast DLR' (SNR: p = 0.436-1, sharpness: p = 0.067-1). Qualitatively, 'standard non-DLR' and 'fast DLR' had similar motion artifact, as well as nerve conspicuity, signal intensity, size and morphology, with high inter-rater agreement (AC2: 'standard' = 0.70-0.98, 'fast DLR' = 0.69-0.97).

CONCLUSION

DLR applied to faster, 3D MRN acquisitions provides similar image quality to standard scans. A faster, DL-enabled protocol may replace currently optimized non-DL protocols.

Magnetic Resonance Neurography of the Lumbosacral Plexus

Pain and weakness in the low back, pelvis, and lower extremities are diagnostically challenging, and imaging can be an important step in the workup and management of these patients. Technical advances in magnetic resonance neurography (MRN) have significantly improved its utility for imaging the lumbosacral plexus (LSP). In this article, the authors review LSP anatomy and selected pathology examples. In addition, the authors will discuss technical considerations for MRN with specific points for the branch nerves off the plexus.

Quantitative double echo steady state T2 mapping of upper extremity peripheral nerves and muscles

Introduction

T2 mapping can characterize peripheral neuropathy and muscle denervation due to axonal damage. Three-dimensional double echo steady-state (DESS) can simultaneously provide 3D qualitative information and T2 maps with equivalent spatial resolution. However, insufficient signal-to-noise ratio may bias DESS-T2 values. Deep learning reconstruction (DLR) techniques can reduce noise, and hence may improve quantitation of high-resolution DESS-T2. This study aims to (i) evaluate the effect of DLR methods on DESS-T2 values, and (ii) to evaluate the feasibility of using DESS-T2 maps to differentiate abnormal from normal nerves and muscles in the upper extremities, with abnormality as determined by electromyography.

Methods and results

Analysis of images from 25 subjects found that DLR decreased DESS-T2 values in abnormal muscles (DLR = 37.71 ± 9.11 msec, standard reconstruction = 38.56 ± 9.44 msec, p = 0.005) and normal muscles (DLR: 27.18 ± 6.34 msec, standard reconstruction: 27.58 ± 6.34 msec, p < 0.001) consistent with a noise reduction bias. Mean DESS-T2, both with and without DLR, was higher in abnormal nerves (abnormal = 75.99 ± 38.21 msec, normal = 35.10 ± 9.78 msec, p < 0.001) and muscles (abnormal = 37.71 ± 9.11 msec, normal = 27.18 ± 6.34 msec, p < 0.001). A higher DESS-T2 in muscle was associated with electromyography motor unit recruitment (p < 0.001).

Discussion

These results suggest that quantitative DESS-T2 is improved by DLR and can differentiate the nerves and muscles involved in peripheral neuropathies from those uninvolved.

Lumbar safety triangle: comparative study of coronal and coronal oblique planes in 3.0-T magnetic resonance imaging

Objective

To compare the measurements of the lumbar safety triangle (Kambin's triangle) and the invasion of the dorsal root ganglion in the triangle in coronal and coronal oblique planes.

Materials and Methods

A cross-sectional study, in which 210 3.0-T magnetic resonance images of L2-L5 were analyzed in coronal and coronal oblique planes. Exams with lumbar spine anomalies were excluded. Demographic (sex and age) and radiological variables were recorded by a single evaluator.

Results

Most sample was female (57.1%), mean age 45.5 ± 13.3 (18-98 years). The measurements average, as well as the areas, gradually increased from L2 to L5. The dorsal root ganglion invaded the triangle in all images. The safety triangle average area was smaller in the coronal oblique plane than in the coronal plane. Of the seven dimensions of safety triangle obtained for each level of the lumbar spine, six were significantly smaller in the coronal oblique plane than in the coronal plane. The only dimension that showed no difference was the smallest ganglion dimension.

Conclusion

The dimensions and areas investigated were smaller in coronal oblique plane, especially the area (difference > 1 mm). The analysis of the triangular zone in this plane becomes important in the preoperative assessment of minimally invasive procedures.