Deep learning reconstruction for 1.5 T cervical spine MRI: effect on interobserver agreement in the evaluation of degenerative changes

Super-Resolution Deep Learning Reconstruction for T2*-Weighted Images: Improvement in Microbleed Lesion Detection and Image Quality

Super-resolution deep learning reconstruction (SR-DLR) is a promising tool for improving image quality by enhancing spatial resolution compared to conventional deep learning reconstruction (DLR). This study aimed to evaluate whether SR-DLR improves microbleed detection and visualization in brain magnetic resonance imaging (MRI) compared to DLR. This retrospective study included 69 patients (66.2 ± 13.8 years; 44 females) who underwent 3 T brain MRI with T2*-weighted 2D gradient echo and 3D flow-sensitive black blood imaging (reference standard) between June and August 2024. T2*-weighted images were reconstructed using SR-DLR and DLR. Three blinded readers detected microbleeds and assessed image quality, including microbleed and normal structure visibility, sharpness, noise, artifacts, and overall quality. Quantitative analysis involved measuring signal intensity along the septum pellucidum. Microbleed detection performance was analyzed using jackknife alternative free-response receiver operating characteristic analysis, while image quality was analyzed using the Wilcoxon signed-rank test and paired t-test. SR-DLR significantly outperformed DLR in microbleed detection (figure of merit: 0.690 vs. 0.645, p < 0.001). SR-DLR also demonstrated higher sensitivity for microbleed detection. Qualitative analysis showed better microbleed visualization for two readers (p < 0.001) and improved image sharpness for all readers (p ≤ 0.008). Quantitative analysis revealed enhanced sharpness, especially in full width at half maximum and edge rise slope (p < 0.001). SR-DLR improved image sharpness and quality, leading to better microbleed detection and visualization in brain MRI compared to DLR.

Super-resolution deep learning reconstruction to evaluate lumbar spinal stenosis status on magnetic resonance myelography

PURPOSE

To investigate whether super-resolution deep learning reconstruction (SR-DLR) of MR myelography-aided evaluations of lumbar spinal stenosis.

MATERIAL AND METHODS

In this retrospective study, lumbar MR myelography of 40 patients (16 males and 24 females; mean age, 59.4 ± 31.8 years) were analyzed. Using the MR imaging data, MR myelography was separately reconstructed via SR-DLR, deep learning reconstruction (DLR), and conventional zero-filling interpolation (ZIP). Three radiologists, blinded to patient background data and MR reconstruction information, independently evaluated the image sets in terms of the following items: the numbers of levels affected by lumbar spinal stenosis; and cauda equina depiction, sharpness, noise, artifacts, and overall image quality.

RESULTS

The median interobserver agreement in terms of the numbers of lumbar spinal stenosis levels were 0.819, 0.735, and 0.729 for SR-DLR, DLR, and ZIP images, respectively. The imaging quality of the cauda equina, and image sharpness, noise, and overall quality on SR-DLR images were significantly better than those on DLR and ZIP images, as rated by all readers (p < 0.001, Wilcoxon signed-rank test). No significant differences were observed for artifacts on SR-DLR against DLR and ZIP.

CONCLUSIONS

SR-DLR improved the image quality of lumbar MR myelographs compared to DLR and ZIP, and was associated with better interobserver agreement during assessment of lumbar spinal stenosis status.

Deep Learning-Based Reconstruction for Accelerated Cervical Spine MRI: Utility in the Evaluation of Myelopathy and Degenerative Diseases

BACKGROUND AND PURPOSE

Deep learning (DL)-based reconstruction enables improving the quality of MR images acquired with a short scan time. We aimed to prospectively compare the image quality and diagnostic performance in evaluating cervical degenerative spine diseases and myelopathy between conventional cervical MRI and accelerated cervical MRI with a commercially available vendor-neutral DL-based reconstruction.

MATERIALS AND METHODS

Fifty patients with degenerative cervical spine disease or myelopathy underwent both conventional cervical MRI and accelerated cervical MRI by using a DL-based reconstruction operating within the DICOM domain. The images were evaluated both quantitatively, based on SNR and contrast-to-noise ratio (CNR), and qualitatively, by using a 5-point scoring system for the overall image quality and clarity of anatomic structures on sagittal T1WI, sagittal contrast-enhanced (CE) T1WI, and axial/sagittal T2WI. Four radiologists assessed the sensitivity and specificity of the 2 protocols for detecting degenerative diseases and myelopathy.

RESULTS

The DL-based protocol reduced MRI acquisition time by 47%-48% compared with the conventional protocol. DL-reconstructed images demonstrated a higher SNR on sagittal T1WI (P = .046) and a higher CNR on sagittal T2WI (P = .03) than conventional images. The SNR on sagittal T2WI and the CNR on sagittal T1WI did not significantly differ (P > .05). DL-reconstructed images had better overall image quality on sagittal T1WI (P < .001), sagittal T2WI (Dixon in-phase or TSE) (P < .001), and sagittal T2WI (Dixon water-only) (P = .013) and similar image quality on axial T2WI and sagittal CE T1WI (P > .05). DL-reconstructed images had better clarity of anatomic structures (P values were < .001 for all structures, except for the neural foramen [P = .024]). DL-reconstructed images had a higher sensitivity for detecting neural foraminal stenosis (P = .005) and similar sensitivities for diagnosing other degenerative spinal diseases and myelopathy (P > .05). The specificities for diagnosing degenerative spinal diseases and myelopathy did not differ between the 2 images (P > .05).

CONCLUSIONS

The accelerated cervical MRI reconstructed with a vendor-neutral DL-based reconstruction algorithm did not compromise image quality and had higher or similar diagnostic performance for diagnosing cervical degenerative spine diseases and myelopathy compared with the conventional protocol.

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.

Super-resolution Deep Learning Reconstruction for 3D Brain MR Imaging: Improvement of Cranial Nerve Depiction and Interobserver Agreement in Evaluations of Neurovascular Conflict

RATIONALE AND OBJECTIVES

To determine if super-resolution deep learning reconstruction (SR-DLR) improves the depiction of cranial nerves and interobserver agreement when assessing neurovascular conflict in 3D fast asymmetric spin echo (3D FASE) brain MR images, as compared to deep learning reconstruction (DLR).

MATERIALS AND METHODS

This retrospective study involved reconstructing 3D FASE MR images of the brain for 37 patients using SR-DLR and DLR. Three blinded readers conducted qualitative image analyses, evaluating the degree of neurovascular conflict, structure depiction, sharpness, noise, and diagnostic acceptability. Quantitative analyses included measuring edge rise distance (ERD), edge rise slope (ERS), and full width at half maximum (FWHM) using the signal intensity profile along a linear region of interest across the center of the basilar artery.

RESULTS

Interobserver agreement on the degree of neurovascular conflict of the facial nerve was generally higher with SR-DLR (0.429-0.923) compared to DLR (0.175-0.689). SR-DLR exhibited increased subjective image noise compared to DLR (p ≥ 0.008). However, all three readers found SR-DLR significantly superior in terms of sharpness (p < 0.001); cranial nerve depiction, particularly of facial and acoustic nerves, as well as the osseous spiral lamina (p < 0.001); and diagnostic acceptability (p ≤ 0.002). The FWHM (mm)/ERD (mm)/ERS (mm-1) for SR-DLR and DLR was 3.1-4.3/0.9-1.1/8795.5-10,703.5 and 3.3-4.8/1.4-2.1/5157.9-7705.8, respectively, with SR-DLR's image sharpness being significantly superior (p ≤ 0.001).

CONCLUSION

SR-DLR enhances image sharpness, leading to improved cranial nerve depiction and a tendency for greater interobserver agreement regarding facial nerve neurovascular conflict.

Iterative Motion Correction Technique with Deep Learning Reconstruction for Brain MRI: A Volunteer and Patient Study

The aim of this study was to investigate the effect of iterative motion correction (IMC) on reducing artifacts in brain magnetic resonance imaging (MRI) with deep learning reconstruction (DLR). The study included 10 volunteers (between September 2023 and December 2023) and 30 patients (between June 2022 and July 2022) for quantitative and qualitative analyses, respectively. Volunteers were instructed to remain still during the first MRI with fluid-attenuated inversion recovery sequence (FLAIR) and to move during the second scan. IMCoff DLR images were reconstructed from the raw data of the former acquisition; IMCon and IMCoff DLR images were reconstructed from the latter acquisition. After registration of the motion images, the structural similarity index measure (SSIM) was calculated using motionless images as reference. For qualitative analyses, IMCon and IMCoff FLAIR DLR images of the patients were reconstructed and evaluated by three blinded readers in terms of motion artifacts, noise, and overall quality. SSIM for IMCon images was 0.952, higher than that for IMCoff images (0.949) (p < 0.001). In qualitative analyses, although noise in IMCon images was rated as increased by two of the three readers (both p < 0.001), all readers agreed that motion artifacts and overall quality were significantly better in IMCon images than in IMCoff images (all p < 0.001). In conclusion, IMC reduced motion artifacts in brain FLAIR DLR images while maintaining similarity to motionless images.

Deep-learning reconstructed lumbar spine 3D MRI for surgical planning: pedicle screw placement and geometric measurements compared to CT

PURPOSE

To test equivalency of deep-learning 3D lumbar spine MRI with "CT-like" contrast to CT for virtual pedicle screw planning and geometric measurements in robotic-navigated spinal surgery.

METHODS

Between December 2021 and June 2022, 16 patients referred for spinal fusion and decompression surgery with pre-operative CT and 3D MRI were retrospectively assessed. Pedicle screws were virtually placed on lumbar (L1-L5) and sacral (S1) vertebrae by three spine surgeons, and metrics (lateral deviation, axial/sagittal angles) were collected. Vertebral body length/width (VL/VW) and pedicle height/width (PH/PW) were measured at L1-L5 by three radiologists. Analysis included equivalency testing using the 95% confidence interval (CI), a margin of ± 1 mm (± 2.08° for angles), and intra-class correlation coefficients (ICCs).

RESULTS

Across all vertebral levels, both combined and separately, equivalency between CT and MRI was proven for all pedicle screw metrics and geometric measurements, except for VL at L1 (mean difference: - 0.64 mm; [95%CI - 1.05, - 0.24]), L2 (- 0.65 mm; [95%CI - 1.11, - 0.20]), and L4 (- 0.78 mm; [95%CI - 1.11, - 0.46]). Inter- and intra-rater ICC for screw metrics across all vertebral levels combined ranged from 0.68 to 0.91 and 0.89-0.98 for CT, and from 0.62 to 0.92 and 0.81-0.97 for MRI, respectively. Inter- and intra-rater ICC for geometric measurements ranged from 0.60 to 0.95 and 0.84-0.97 for CT, and 0.61-0.95 and 0.93-0.98 for MRI, respectively.

CONCLUSION

Deep-learning 3D MRI facilitates equivalent virtual pedicle screw placements and geometric assessments for most lumbar vertebrae, with the exception of vertebral body length at L1, L2, and L4, compared to CT for pre-operative planning in patients considered for robotic-navigated spine surgery.

Prospective and multi-reader evaluation of deep learning reconstruction-based accelerated rectal MRI: image quality, diagnostic performance, and reading time

OBJECTIVES

To evaluate deep learning reconstruction (DLR)-based accelerated rectal magnetic resonance imaging (MRI) compared with standard MRI.

MATERIALS AND METHODS

Patients with biopsy-confirmed rectal adenocarcinoma between November/2022 and May/2023 in a single centre were prospectively enrolled for an intra-individual comparison between standard fast spin-echo (FSEstandard) and DLR-based FSE (FSEDL) sequences. Quantitative and qualitative image quality metrics of the pre-therapeutic MRIs were evaluated in all patients; diagnostic performance and evaluating time for T-staging, N-staging, extramural vascular invasion (EMVI), and mesorectal fascia (MRF) status was further analysed in patients undergoing curative surgery, with histopathologic results as the diagnostic gold standard.

RESULTS

A total of 117 patients were enrolled, with 60 patients undergoing curative surgery. FSEDL reduced the acquisition time by 65% than FSEstandard. FSEDL exhibited higher signal-to-noise ratios, contrast-to-noise ratio, and subjective scores (noise, tumour margin clarity, visualisation of bowel wall layering and MRF, overall image quality, and diagnostic confidence) than FSEstandard (p < 0.001). Reduced artefacts were observed in FSEDL for patients without spasmolytics (p < 0.05). FSEDL provided higher T-staging accuracy by junior readers than FSEstandard (reader 1, 58.33% vs 70.00%, p = 0.016; reader 3, 60.00% vs 76.67%, p = 0.021), with similar N-staging, EMVI, and MRF performance. No significant difference was observed for senior readers. FSEDL exhibited shorter diagnostic time in all readers' T-staging and overall evaluation, and junior readers' EMVI and MRF (p < 0.05).

CONCLUSION

FSEDL provided improved image quality, reading time, and junior radiologists' T-staging accuracy than FSEstandard, while reducing the acquisition time by 65%.

CLINICAL RELEVANCE STATEMENT

DLR is clinically applicable for rectal MRI, providing improved image quality with shorter scanning time, which may ease the examination burden. It is beneficial for diagnostic optimisation in improving junior radiologists' T-staging accuracy and reading time.

KEY POINTS

The rising incidence of rectal cancer has demanded enhanced efficiency and quality in imaging examinations. FSEDL demonstrated superior image quality and had a 65% reduced acquisition time. FSEDL can improve the diagnostic accuracy of T-staging and reduce the reading time for assessing rectal cancer.

Assessment of multi-modal magnetic resonance imaging for glioma based on a deep learning reconstruction approach with the denoising method

BACKGROUND

Deep learning reconstruction (DLR) with denoising has been reported as potentially improving the image quality of magnetic resonance imaging (MRI). Multi-modal MRI is a critical non-invasive method for tumor detection, surgery planning, and prognosis assessment; however, the DLR on multi-modal glioma imaging has not been assessed.

PURPOSE

To assess multi-modal MRI for glioma based on the DLR method.

MATERIAL AND METHODS

We assessed multi-modal images of 107 glioma patients (49 preoperative and 58 postoperative). All the images were reconstructed with both DLR and conventional reconstruction methods, encompassing T1-weighted (T1W), contrast-enhanced T1W (CE-T1), T2-weighted (T2W), and T2 fluid-attenuated inversion recovery (T2-FLAIR). The image quality was evaluated using signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and edge sharpness. Visual assessment and diagnostic assessment were performed blindly by neuroradiologists.

RESULTS

In contrast with conventionally reconstructed images, (residual) tumor SNR for all modalities and tumor to white/gray matter CNR from DLR images were higher in T1W, T2W, and T2-FLAIR sequences. The visual assessment of DLR images demonstrated the superior visualization of tumor in T2W, edema in T2-FLAIR, enhanced tumor and necrosis part in CE-T1, and fewer artifacts in all modalities. Improved diagnostic efficiency and confidence were observed for preoperative cases with DLR images.

CONCLUSION

DLR of multi-modal MRI reconstruction prototype for glioma has demonstrated significant improvements in image quality. Moreover, it increased diagnostic efficiency and confidence of glioma.

Super-resolution Deep Learning Reconstruction Cervical Spine 1.5T MRI: Improved Interobserver Agreement in Evaluations of Neuroforaminal Stenosis Compared to Conventional Deep Learning Reconstruction

The aim of this study was to investigate whether super-resolution deep learning reconstruction (SR-DLR) is superior to conventional deep learning reconstruction (DLR) with respect to interobserver agreement in the evaluation of neuroforaminal stenosis using 1.5T cervical spine MRI. This retrospective study included 39 patients who underwent 1.5T cervical spine MRI. T2-weighted sagittal images were reconstructed with SR-DLR and DLR. Three blinded radiologists independently evaluated the images in terms of the degree of neuroforaminal stenosis, depictions of the vertebrae, spinal cord and neural foramina, sharpness, noise, artefacts and diagnostic acceptability. In quantitative image analyses, a fourth radiologist evaluated the signal-to-noise ratio (SNR) by placing a circular or ovoid region of interest on the spinal cord, and the edge slope based on a linear region of interest placed across the surface of the spinal cord. Interobserver agreement in the evaluations of neuroforaminal stenosis using SR-DLR and DLR was 0.422-0.571 and 0.410-0.542, respectively. The kappa values between reader 1 vs. reader 2 and reader 2 vs. reader 3 significantly differed. Two of the three readers rated depictions of the spinal cord, sharpness, and diagnostic acceptability as significantly better with SR-DLR than with DLR. Both SNR and edge slope (/mm) were also significantly better with SR-DLR (12.9 and 6031, respectively) than with DLR (11.5 and 3741, respectively) (p < 0.001 for both). In conclusion, compared to DLR, SR-DLR improved interobserver agreement in the evaluations of neuroforaminal stenosis using 1.5T cervical spine MRI.

Assessment of image quality and diagnostic accuracy for cervical spondylosis using T2w-STIR sequence with a deep learning-based reconstruction approach

OBJECTIVES

To investigate potential of enhancing image quality, maintaining interobserver consensus, and elevating disease diagnostic efficacy through the implementation of deep learning-based reconstruction (DLR) processing in 3.0 T cervical spine fast magnetic resonance imaging (MRI) images, compared with conventional images.

METHODS

The 3.0 T cervical spine MRI images of 71 volunteers were categorized into two groups: sagittal T2-weighted short T1 inversion recovery without DLR (Sag T2w-STIR) and with DLR (Sag T2w-STIR-DLR). The assessment covered artifacts, perceptual signal-to-noise ratio, clearness of tissue interfaces, fat suppression, overall image quality, and the delineation of spinal cord, vertebrae, discs, dopamine, and joints. Spanning canal stenosis, neural foraminal stenosis, herniated discs, annular fissures, hypertrophy of the ligamentum flavum or vertebral facet joints, and intervertebral disc degeneration were evaluated by three impartial readers.

RESULTS

Sag T2w-STIR-DLR images exhibited markedly superior performance across quality indicators (median = 4 or 5) compared to Sag T2w-STIR sequences (median = 3 or 4) (p < 0.001). No statistically significant differences were observed between the two sequences in terms of diagnosis and grading (p > 0.05). The interobserver agreement for Sag T2w-STIR-DLR images (0.604-0.931) was higher than the other (0.545-0.853), Sag T2w-STIR-DLR (0.747-1.000) demonstrated increased concordance between reader 1 and reader 3 in comparison to Sag T2w-STIR (0.508-1.000). Acquisition time diminished from 364 to 197 s through the DLR scheme.

CONCLUSIONS

Our investigation establishes that 3.0 T fast MRI images subjected to DLR processing present heightened image quality, bolstered diagnostic performance, and reduced scanning durations for cervical spine MRI compared with conventional sequences.

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.

Faster acquisition of magnetic resonance imaging sequences of the knee via deep learning reconstruction: a volunteer study

AIM

To evaluate whether deep learning reconstruction (DLR) can accelerate the acquisition of magnetic resonance imaging (MRI) sequences of the knee for clinical use.

MATERIALS AND METHODS

Using a 1.5-T MRI scanner, sagittal fat-suppressed T2-weighted imaging (fs-T2WI), coronal proton density-weighted imaging (PDWI), and coronal T1-weighted imaging (T1WI) were performed. DLR was applied to images with a number of signal averages (NSA) of 1 to obtain 1DLR images. Then 1NSA, 1DLR, and 4NSA images were compared subjectively, and by noise (standard deviation of intra-articular water or medial meniscus) and contrast-to-noise ratio between two anatomical structures or between an anatomical structure and intra-articular water.

RESULTS

Twenty-seven healthy volunteers (age: 40.6 ± 11.9 years) were enrolled. Three 1DLR image sequences were obtained within 200 s (approximately 12 minutes for 4NSA image). According to objective evaluations, PDWI 1DLR images showed the smallest noise and significantly higher contrast than 1NSA and 4NSA images. For fs-T2WI, smaller noise and higher contrast were observed in the order of 4NSA, 1DLR, and 1NSA images. According to the subjective analysis, structure visibility, image noise, and overall image quality were significantly better for PDWI 1DLR than 1NSA images; moreover, the visibility of the meniscus and bone, image noise, and overall image quality were significantly better for 1DLR than 4NSA images. Fs-T2WI and T1WI 1DLR images showed no difference between 1DLR and 4NSA images.

CONCLUSION

Compared to PDWI 4NSA images, PDWI 1DLR images were of higher quality, while the quality of fs-T2WI and T1WI 1DLR images was similar to that of 4NSA images.

Comparative analysis of image quality and interchangeability between standard and deep learning-reconstructed T2-weighted spine MRI

RATIONALE AND OBJECTIVES

MRI reconstruction of undersampled data using a deep learning (DL) network has been recently performed as part of accelerated imaging. Herein, we compared DL-reconstructed T2-weighted image (T2-WI) to conventional T2-WI regarding image quality and degenerative lesion detection.

MATERIALS AND METHODS

Sixty-two patients underwent C-spine (n = 27) or L-spine (n = 35) MRIs, including conventional and DL-reconstructed T2-WI. Image quality was assessed with non-uniformity measurement and 4-scale grading of structural visibility. Three readers (R1, R2, R3) independently assessed the presence and types of degenerative lesions. Student t-test was used to compare non-uniformity measurements. Interprotocol and interobserver agreement of structural visibility was analyzed with Wilcoxon signed-rank test and weighted-κ values, respectively. The diagnostic equivalence of degenerative lesion detection between two protocols was assessed with interchangeability test.

RESULTS

The acquisition time of DL-reconstructed images was reduced to about 21-58% compared to conventional images. Non-uniformity measurement was insignificantly different between the two images (p-value = 0.17). All readers rated DL-reconstructed images as showing the same or superior structural visibility compared to conventional images. Significantly improved visibility was observed at disk margin of C-spine (R1, p < 0.001; R2, p = 0.04) and dorsal root ganglia (R1, p = 0.03; R3, p = 0.02) and facet joint (R1, p = 0.04; R2, p < 0.001; R3, p = 0.03) of L-spine. Interobserver agreements of image quality were variable in each structure. Clinical interchangeability between two protocols for degenerative lesion detection was verified showing <5% in the upper bounds of 95% confidence intervals of agreement rate differences.

CONCLUSIONS

DL-reconstructed T2-WI demonstrates comparable image quality and diagnostic performance with conventional T2-WI in spine imaging, with reduced acquisition time.

Thin-slice 2D MR Imaging of the Shoulder Joint Using Denoising Deep Learning Reconstruction Provides Higher Image Quality Than 3D MR Imaging

PURPOSE

This study was conducted to evaluate whether thin-slice 2D fat-saturated proton density-weighted images of the shoulder joint in three imaging planes combined with parallel imaging, partial Fourier technique, and denoising approach with deep learning-based reconstruction (dDLR) are more useful than 3D fat-saturated proton density multi-planar voxel images.

METHODS

Eighteen patients who underwent MRI of the shoulder joint at 3T were enrolled. The denoising effect of dDLR in 2D was evaluated using coefficient of variation (CV). Qualitative evaluation of anatomical structures, noise, and artifacts in 2D after dDLR and 3D was performed by two radiologists using a five-point Likert scale. All were analyzed statistically. Gwet's agreement coefficients were also calculated.

RESULTS

The CV of 2D after dDLR was significantly lower than that before dDLR (P < 0.05). Both radiologists rated 2D higher than 3D for all anatomical structures and noise (P < 0.05), except for artifacts. Both Gwet's agreement coefficients of anatomical structures, noise, and artifacts in 2D and 3D produced nearly perfect agreement between the two radiologists. The evaluation of 2D tended to be more reproducible than 3D.

CONCLUSION

2D with parallel imaging, partial Fourier technique, and dDLR was proved to be superior to 3D for depicting shoulder joint structures with lower noise.

Validation and Feasibility of Ultrafast Cervical Spine MRI Using a Deep Learning-Assisted 3D Iterative Image Enhancement System

Purpose

This study aimed to evaluate the feasibility of ultrafast (2 min) cervical spine MRI protocol using a deep learning-assisted 3D iterative image enhancement (DL-3DIIE) system, compared to a conventional MRI protocol (6 min 14s).

Patients and Methods

Fifty-one patients were recruited and underwent cervical spine MRI using conventional and ultrafast protocols. A DL-3DIIE system was applied to the ultrafast protocol to compensate for the spatial resolution and signal-to-noise ratio (SNR) of images. Two radiologists independently assessed and graded the quality of images from the dimensions of artifacts, boundary sharpness, visibility of lesions and overall image quality. We recorded the presence or absence of different pathologies. Moreover, we examined the interchangeability of the two protocols by computing the 95% confidence interval of the individual equivalence index, and also evaluated the inter-protocol intra-observer agreement using Cohen's weighted kappa.

Results

Ultrafast-DL-3DIIE images were significantly better than conventional ones for artifacts and equivalent for other qualitative features. The number of cases with different kinds of pathologies was indistinguishable based on the MR images from ultrafast-DL-3DIIE and conventional protocols. With the exception of disc degeneration, the 95% confidence interval for the individual equivalence index across all variables did not surpass 5%, suggesting that the two protocols are interchangeable. The kappa values of these evaluations by the two radiologists ranged from 0.65 to 0.88, indicating good-to-excellent agreement.

Conclusion

The DL-3DIIE system enables 67% spine MRI scan time reduction while obtaining at least equivalent image quality and diagnostic results compared to the conventional protocol, suggesting its potential for clinical utility.

Effect of Deep Learning Reconstruction on Evaluating Cervical Spinal Canal Stenosis With Computed Tomography

OBJECTIVE

Magnetic resonance imaging (MRI) is commonly used to evaluate cervical spinal canal stenosis; however, some patients are ineligible for MRI. We aimed to assess the effect of deep learning reconstruction (DLR) in evaluating cervical spinal canal stenosis using computed tomography (CT) compared with hybrid iterative reconstruction (hybrid IR).

METHODS

This retrospective study included 33 patients (16 male patients; mean age, 57.7 ± 18.4 years) who underwent cervical spine CT. Images were reconstructed using DLR and hybrid IR. In the quantitative analyses, noise was recorded by placing the regions of interest on the trapezius muscle. In the qualitative analyses, 2 radiologists evaluated the depiction of structures, image noise, overall image quality, and degree of cervical canal stenosis. We additionally evaluated the agreement between MRI and CT in 15 patients for whom preoperative cervical MRI was available.

RESULTS

Image noise was less with DLR than hybrid IR in the quantitative ( P ≤ 0.0395) and subjective analyses ( P ≤ 0.0023), and the depiction of most structures was improved ( P ≤ 0.0052), which resulted in better overall quality ( P ≤ 0.0118). Interobserver agreement in the assessment of spinal canal stenosis with DLR (0.7390; 95% confidence interval [CI], 0.7189-0.7592) was superior to that with hybrid IR (0.7038; 96% CI, 0.6846-0.7229). As for the agreement between MRI and CT, significant improvement was observed for 1 reader with DLR (0.7910; 96% CI, 0.7762-0.8057) than hybrid IR (0.7536; 96% CI, 0.7383-0.7688).

CONCLUSIONS

Deep learning reconstruction provided better quality cervical spine CT images in the evaluation of cervical spinal stenosis than hybrid IR.

Evaluation of late gadolinium enhancement cardiac MRI using deep learning reconstruction

BACKGROUND

Deep learning (DL)-based methods have been used to improve the imaging quality of magnetic resonance imaging (MRI) by denoising.

PURPOSE

To assess the effects of DL-based MR reconstruction (DLR) method on late gadolinium enhancement (LGE) image quality.

MATERIAL AND METHODS

A total of 85 patients who underwent cardiovascular magnetic resonance (CMR) examination, including LGE imaging using conventional construction and DLR with varying levels of noise reduction (NR) levels, were included. Both magnitude LGE (MLGE) and phase-sensitive LGE (PSLGE) images were reviewed independently by double-blinded observers who used a 5-point Likert scale for multiple measures regarding image quality. Meanwhile, the signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and edge sharpness of images were calculated and compared between conventional LGE imaging and DLR LGE imaging.

RESULTS

Both MLGE and PSLGE with DLR at 50% and 75% noise reduction levels received significantly higher scores than conventional imaging for overall imaging quality (all P < 0.01). In addition, the SNR, CNR, and edge sharpness of all DLR LGE imaging are higher than conventional imaging (all P < 0.01). The highest subjective score and best image quality is obtained when the DLR noise reduction level is at 75%.

CONCLUSION

DLR reduced image noise while improving image contrast and sharpness in the cardiovascular LGE imaging.

Clinical Impact of Deep Learning Reconstruction in MRI

Deep learning has been recognized as a paradigm-shifting tool in radiology. Deep learning reconstruction (DLR) has recently emerged as a technology used in the image reconstruction process of MRI, which is an essential procedure in generating MR images. Denoising, which is the first DLR application to be realized in commercial MRI scanners, improves signal-to-noise ratio. When applied to lower magnetic field-strength scanners, the signal-to-noise ratio can be increased without extending the imaging time, and image quality is comparable to that of higher-field-strength scanners. Shorter imaging times decrease patient discomfort and reduce MRI scanner running costs. The incorporation of DLR into accelerated acquisition imaging techniques, such as parallel imaging or compressed sensing, shortens the reconstruction time. DLR is based on supervised learning using convolutional layers and is divided into the following three categories: image domain, k-space learning, and direct mapping types. Various studies have reported other derivatives of DLR, and several have shown the feasibility of DLR in clinical practice. Although DLR efficiently reduces Gaussian noise from MR images, denoising makes image artifacts more prominent, and a solution to this problem is desired. Depending on the training of the convolutional neural network, DLR may change the imaging features of lesions and obscure small lesions. Therefore, radiologists may need to adopt the habit of questioning whether any information has been lost on images that appear clean. ^©RSNA, 2023 Quiz questions for this article are available in the supplemental material.

Benign vs malignant vertebral compression fractures with MRI: a comparison between automatic deep learning network and radiologist's assessment

OBJECTIVE

To test the diagnostic performance of a deep-learning Two-Stream Compare and Contrast Network (TSCCN) model for differentiating benign and malignant vertebral compression fractures (VCFs) based on MRI.

METHODS

We tested a deep-learning system in 123 benign and 86 malignant VCFs. The median sagittal T1-weighted images (T1WI), T2-weighted images with fat suppression (T2WI-FS), and a combination of both (thereafter, T1WI/T2WI-FS) were used to validate TSCCN. The receiver operator characteristic (ROC) curve was analyzed to evaluate the performance of TSCCN. The accuracy, sensitivity, and specificity of TSCCN in differentiating benign and malignant VCFs were calculated and compared with radiologists' assessments. Intraclass correlation coefficients (ICCs) were tested to find intra- and inter-observer agreement of radiologists in differentiating malignant from benign VCFs.

RESULTS

The AUC of the ROC plots of TSCCN according to T1WI, T2WI-FS, and T1WI/T2WI-FS images were 99.2%, 91.7%, and 98.2%, respectively. The accuracy of T1W, T2WI-FS, and T1W/T2WI-FS based on TSCCN was 95.2%, 90.4%, and 96.2%, respectively, greater than that achieved by radiologists. Further, the specificity of T1W, T2WI-FS, and T1W/T2WI-FS based on TSCCN was higher at 98.4%, 94.3%, and 99.2% than that achieved by radiologists. The intra- and inter-observer agreements of radiologists were 0.79-0.85 and 0.79-0.80 for T1WI, 0.65-0.72 and 0.70-0.74 for T2WI-FS, and 0.83-0.88 and 0.83-0.84 for T1WI/T2WI-FS.

CONCLUSION

The TSCCN model showed better diagnostic performance than radiologists for automatically identifying benign or malignant VCFs, and is a potentially helpful tool for future clinical application.

CLINICAL RELEVANCE STATEMENT

TSCCN-assisted MRI has shown superior performance in distinguishing benign and malignant vertebral compression fractures compared to radiologists. This technology has the value to enhance diagnostic accuracy, sensitivity, and specificity. Further integration into clinical practice is required to optimize patient management.

KEY POINTS

• The Two-Stream Compare and Contrast Network (TSCCN) model showed better diagnostic performance than radiologists for identifying benign vs malignant vertebral compression fractures. • The processing of TSCCN is fast and stable, better than the subjective evaluation by radiologists in diagnosing vertebral compression fractures. • The TSCCN model provides options for developing a fully automated, streamlined artificial intelligence diagnostic tool.

Acceleration of knee magnetic resonance imaging using a combination of compressed sensing and commercially available deep learning reconstruction: a preliminary study

PURPOSE

To evaluate whether deep learning reconstruction (DLR) accelerates the acquisition of 1.5-T magnetic resonance imaging (MRI) knee data without image deterioration.

MATERIALS AND METHODS

Twenty-one healthy volunteers underwent MRI of the right knee on a 1.5-T MRI scanner. Proton-density-weighted images with one or four numbers of signal averages (NSAs) were obtained via compressed sensing, and DLR was applied to the images with 1 NSA to obtain 1NSA-DLR images. The 1NSA-DLR and 4NSA images were compared objectively (by deriving the signal-to-noise ratios of the lateral and the medial menisci and the contrast-to-noise ratios of the lateral and the medial menisci and articular cartilages) and subjectively (in terms of the visibility of the anterior cruciate ligament, the medial collateral ligament, the medial and lateral menisci, and bone) and in terms of image noise, artifacts, and overall diagnostic acceptability. The paired t-test and Wilcoxon signed-rank test were used for statistical analyses.

RESULTS

The 1NSA-DLR images were obtained within 100 s. The signal-to-noise ratios (lateral: 3.27 ± 0.30 vs. 1.90 ± 0.13, medial: 2.71 ± 0.24 vs. 1.80 ± 0.15, both p < 0.001) and contrast-to-noise ratios (lateral: 2.61 ± 0.51 vs. 2.18 ± 0.58, medial 2.19 ± 0.32 vs. 1.97 ± 0.36, both p < 0.001) were significantly higher for 1NSA-DLR than 4NSA images. Subjectively, all anatomical structures (except bone) were significantly clearer on the 1NSA-DLR than on the 4NSA images. Also, in the former images, the noise was lower, and the overall diagnostic acceptability was higher.

CONCLUSION

Compared with the 4NSA images, the 1NSA-DLR images exhibited less noise, higher overall image quality, and allowed more precise visualization of the menisci and ligaments.

Deep learning reconstruction for the evaluation of neuroforaminal stenosis using 1.5T cervical spine MRI: comparison with 3T MRI without deep learning reconstruction

PURPOSE

To compare image quality and interobserver agreement in evaluations of neuroforaminal stenosis between 1.5T cervical spine magnetic resonance imaging (MRI) with deep learning reconstruction (DLR) and 3T MRI without DLR.

METHODS

In this prospective study, 21 volunteers (mean age: 42.4 ± 11.9 years; 17 males) underwent cervical spine T2-weighted sagittal 1.5T and 3T MRI on the same day. The 1.5T and 3T MRI data were used to reconstruct images with (1.5T-DLR) and without (3T-nonDLR) DLR, respectively. Regions of interest were marked on the spinal cord to calculate non-uniformity (NU; standard deviation/signal intensity × 100), as an indicator of image noise. Two blinded radiologists evaluated the images in terms of the depiction of structures, artifacts, noise, overall image quality, and neuroforaminal stenosis. The NU value and the subjective image quality scores were compared between 1.5T-DLR and 3T-nonDLR using the Wilcoxon signed-rank test. Interobserver agreement in evaluations of neuroforaminal stenosis for 1.5T-DLR and 3T-nonDLR was evaluated using Cohen's weighted kappa analysis.

RESULTS

The NU value for 1.5T-DLR was 8.4, which was significantly better than that for 3T-nonDLR (10.3; p < 0.001). Subjective image scores were significantly better for 1.5T-DLR than 3T-nonDLR images (p < 0.037). Interobserver agreement (95% confidence intervals) in the evaluations of neuroforaminal stenosis was significantly superior for 1.5T-DLR (0.920 [0.916-0.924]) than 3T-nonDLR (0.894 [0.889-0.898]).

CONCLUSION

By using DLR, image quality and interobserver agreement in evaluations of neuroforaminal stenosis on 1.5T cervical spine MRI could be improved compared to 3T MRI without DLR.