Parallel MR imaging

Accelerated Musculoskeletal Magnetic Resonance Imaging

With a substantial growth in the use of musculoskeletal MRI, there has been a growing need to improve MRI workflow, and faster imaging has been suggested as one of the solutions for a more efficient examination process. Consequently, there have been considerable advances in accelerated MRI scanning methods. This article aims to review the basic principles and applications of accelerated musculoskeletal MRI techniques including widely used conventional acceleration methods, more advanced deep learning-based techniques, and new approaches to reduce scan time. Specifically, conventional accelerated MRI techniques, including parallel imaging, compressed sensing, and simultaneous multislice imaging, and deep learning-based accelerated MRI techniques, including undersampled MR image reconstruction, super-resolution imaging, artifact correction, and generation of unacquired contrast images, are discussed. Finally, new approaches to reduce scan time, including synthetic MRI, novel sequences, and new coil setups and designs, are also reviewed. We believe that a deep understanding of these fast MRI techniques and proper use of combined acceleration methods will synergistically improve scan time and MRI workflow in daily practice. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 1.

Enhanced image quality and lesion detection in FLAIR MRI of white matter hyperintensity through deep learning-based reconstruction

OBJECTIVE

To delve deeper into the study of degenerative diseases, it becomes imperative to investigate whether deep-learning reconstruction (DLR) can improve the evaluation of white matter hyperintensity (WMH) on 3.0T scanners, and compare its lesion detection capabilities with conventional reconstruction (CR).

METHODS

A total of 131 participants (mean age, 46 years ±17; 46 men) were included in the study. The images of these participants were evaluated by readers blinded to clinical data. Two readers independently assessed subjective image indicators on a 4-point scale. The severity of WMH was assessed by four raters using the Fazekas scale. To evaluate the relative detection capabilities of each method, we employed the Wilcoxon signed rank test to compare scores between the DLR and the CR group. Additionally, we assessed interrater reliability using weighted k statistics and intraclass correlation coefficient to test consistency among the raters.

RESULTS

In terms of subjective image scoring, the DLR group exhibited significantly better scores compared to the CR group (P < 0.001). Regarding the severity of WMH, the DL group demonstrated superior performance in detecting lesions. Majority readers agreed that the DL group provided clearer visualization of the lesions compared to the conventional group.

CONCLUSION

DLR exhibits notable advantages over CR, including subjective image quality, lesion detection sensitivity, and inter reader reliability.

Effect of MR head coil geometry on deep-learning-based MR image reconstruction

PURPOSE

To investigate whether parallel imaging-imposed geometric coil constraints can be relaxed when using a deep learning (DL)-based image reconstruction method as opposed to a traditional non-DL method.

THEORY AND METHODS

Traditional and DL-based MR image reconstruction approaches operate in fundamentally different ways: Traditional methods solve a system of equations derived from the image data whereas DL methods use data/target pairs to learn a generalizable reconstruction model. Two sets of head coil profiles were evaluated: (1) 8-channel and (2) 32-channel geometries. A DL model was compared to conjugate gradient SENSE (CG-SENSE) and L1-wavelet compressed sensing (CS) through quantitative metrics and visual assessment as coil overlap was increased.

RESULTS

Results were generally consistent between experiments. As coil overlap increased, there was a significant (p < 0.001) decrease in performance in most cases for all methods. The decrease was most pronounced for CG-SENSE, and the DL models significantly outperformed (p < 0.001) their non-DL counterparts in all scenarios. CS showed improved robustness to coil overlap and signal-to-noise ratio (SNR) versus CG-SENSE, but had quantitatively and visually poorer reconstructions characterized by blurriness as compared to DL. DL showed virtually no change in performance across SNR and very small changes across coil overlap.

CONCLUSION

The DL image reconstruction method produced images that were robust to coil overlap and of higher quality than CG-SENSE and CS. This suggests that geometric coil design constraints can be relaxed when using DL reconstruction methods.

Advanced MRI techniques in abdominal imaging

Magnetic resonance imaging (MRI) is a crucial modality for abdominal imaging evaluation of focal lesions and tissue properties. However, several obstacles, such as prolonged scan times, limitations in patients' breath-hold capacity, and contrast agent-associated artifacts, remain in abdominal MR images. Recent techniques, including parallel imaging, three-dimensional acquisition, compressed sensing, and deep learning, have been developed to reduce the scan time while ensuring acceptable image quality or to achieve higher resolution without extending the scan duration. Quantitative measurements using MRI techniques enable the noninvasive evaluation of specific materials. A comprehensive understanding of these advanced techniques is essential for accurate interpretation of MRI sequences. Herein, we therefore review advanced abdominal MRI techniques.

Dynamic MRI interpolation in temporal direction using an unsupervised generative model

PURPOSE

Cardiac cine magnetic resonance imaging (MRI) is an important tool in assessing dynamic heart function. However, this technique requires long acquisition time and long breath holds, which presents difficulties. The aim of this study is to propose an unsupervised neural network framework that can perform cardiac cine interpolation in time, so that we can increase the temporal resolution of cardiac cine without increasing acquisition time.

METHODS

In this study, a subject-specific unsupervised generative neural network is designed to perform temporal interpolation for cardiac cine MRI. The network takes in a 2D latent vector in which each element corresponds to one cardiac phase in the cardiac cycle and then the network outputs the cardiac cine images which are acquired on the scanner. After the training of the generative network, we can interpolate the 2D latent vector and input the interpolated latent vector into the network and the network will output the frame-interpolated cine images. The results of the proposed cine interpolation neural network (CINN) framework are compared quantitatively and qualitatively with other state-of-the-art methods, the ground truth training cine frames, and the ground truth frames removed from the original acquisition. Signal-to-noise ratio (SNR), structural similarity index measures (SSIM), peak signal-to-noise ratio (PSNR), strain analysis, as well as the sharpness calculated using the Tenengrad algorithm were used for image quality assessment.

RESULTS

As shown quantitatively and qualitatively, the proposed framework learns the generative task well and hence performs the temporal interpolation task well. Furthermore, both quantitative and qualitative comparison studies show the effectiveness of the proposed framework in cardiac cine interpolation in time.

CONCLUSION

The proposed generative model can effectively learn the generative task and perform high quality cardiac cine interpolation in time.

Accelerated 3D whole-heart non-contrast-enhanced mDIXON coronary MR angiography using deep learning-constrained compressed sensing reconstruction

OBJECTIVES

To investigate the feasibility of a deep learning-constrained compressed sensing (DL-CS) method in non-contrast-enhanced modified DIXON (mDIXON) coronary magnetic resonance angiography (MRA) and compare its diagnostic accuracy using coronary CT angiography (CCTA) as a reference standard.

METHODS

Ninety-nine participants were prospectively recruited for this study. Thirty healthy subjects (age range: 20-65 years; 50% female) underwent three non-contrast mDIXON-based coronary MRA sequences including DL-CS, CS, and conventional sequences. The three groups were compared based on the scan time, subjective image quality score, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). The remaining 69 patients suspected of coronary artery disease (CAD) (age range: 39-83 years; 51% female) underwent the DL-CS coronary MRA and its diagnostic performance was compared with that of CCTA.

RESULTS

The scan time for the DL-CS and CS sequences was notably shorter than that of the conventional sequence (9.6 ± 3.1 min vs 10.0 ± 3.4 min vs 13.0 ± 4.9 min; p < 0.001). The DL-CS sequence obtained the highest image quality score, mean SNR, and CNR compared to CS and conventional methods (all p < 0.001). Compared to CCTA, the accuracy, sensitivity, and specificity of DL-CS mDIXON coronary MRA per patient were 84.1%, 92.0%, and 79.5%; those per vessel were 90.3%, 82.6%, and 92.5%; and those per segment were 98.0%, 85.1%, and 98.0%, respectively.

CONCLUSION

The DL-CS mDIXON coronary MRA provided superior image quality and short scan time for visualizing coronary arteries in healthy individuals and demonstrated high diagnostic value compared to CCTA in CAD patients.

CRITICAL RELEVANCE STATEMENT

DL-CS resulted in improved image quality with an acceptable scan time, and demonstrated excellent diagnostic performance compared to CCTA, which could be an alternative to enhance the workflow of coronary MRA.

KEY POINTS

Current coronary MRA techniques are limited by scan time and the need for noise reduction. DL-CS reduced the scan time in coronary MR angiography. Deep learning achieved the highest image quality among the three methods. Deep learning-based coronary MR angiography demonstrated high performance compared to CT angiography.

Deep learning reconstructed T2-weighted Dixon imaging of the spine: Impact on acquisition time and image quality

PURPOSE

To assess the image quality and impact on acquisition time of a novel deep learning based T2 Dixon sequence (T2DL) of the spine.

METHODS

This prospective, single center study included n = 44 consecutive patients with a clinical indication for lumbar MRI at our university radiology department between September 2022 and March 2023. MRI examinations were performed on 1.5-T and 3-T scanners (MAGNETOM Aera and Vida; Siemens Healthineers, Erlangen, Germany) using dedicated spine coils. The MR study protocol consisted of our standard clinical protocol, including a T2 weighted standard Dixon sequence (T2std) and an additional T2DL acquisition. The latter used a conventional sampling pattern with a higher parallel acceleration factor. The individual contrasts acquired for Dixon water-fat separation were then reconstructed using a dedicated research application. After reconstruction of the contrast images from k-space data, a conventional water-fat separation was performed to provide derived water images. Two readers with 6 and 4 years of experience in interpreting MSK imaging, respectively, analyzed the images in a randomized fashion. Regarding overall image quality, banding artifacts, artifacts, sharpness, noise, and diagnostic confidence were analyzed using a 5-point Likert scale (from 1 = non-diagnostic to 5 = excellent image quality). Statistical analyses included the Wilcoxon signed-rank test and weighted Cohen's kappa statistics.

RESULTS

Forty-four patients (mean age 53 years (±18), male sex: 39 %) were prospectively included. Thirty-one examinations were performed on 1.5 T and 13 examinations on 3 T scanners. A sequence was successfully acquired in all patients. The total acquisition time of T2DL was 93 s at 1.5-T and 86 s at 3-T, compared to 235 s, and 257 s, respectively for T2std (reduction of acquisition time: 60.4 % at 1.5-T, and 66.5 % at 3-T; p < 0.01). Overall image quality was rated equal for both sequences (median T2DL: 5[3 -5], and median T2std: 5 [2 -5]; p = 0.57). T2DL showed significantly reduced noise levels compared to T2std (5 [4 -5] versus 4 [3 -4]; p < 0.001). In addition, sharpness was rated to be significantly higher in T2DL (5 [4 -5] versus 4 [3 -5]; p < 0.001). Although T2DL displayed significantly more banding artifacts (5 [2 -5] versus 5 [4 -5]; p < 0.001), no significant impact on readers diagnostic confidence between sequences was noted (T2std: 5 [2 -5], and T2DL: 5 [3 -5]; p = 0.61). Substantial inter-reader and intrareader agreement was observed for T2DL overall image quality (κ: 0.77, and κ: 0.8, respectively).

CONCLUSION

T2DL is feasible, yields an image quality comparable to the reference standard while substantially reducing the acquisition time.

DIRECTION: Deep cascaded reconstruction residual-based feature modulation network for fast MRI reconstruction

Deep cascaded networks have been extensively studied and applied to accelerate Magnetic Resonance Imaging (MRI) and have shown promising results. Most existing works employ a large cascading number for the sake of superior performances. However, due to the lack of proper guidance, the reconstruction performance can easily reach a plateau and even face degradation if simply increasing the cascading number. In this paper, we aim to boost the reconstruction performance from a novel perspective by proposing a parallel architecture called DIRECTION that fully exploits the guiding value of the reconstruction residual of each subnetwork. Specifically, we introduce a novel Reconstruction Residual-Based Feature Modulation Mechanism (RRFMM) which utilizes the reconstruction residual of the previous subnetwork to guide the next subnetwork at the feature level. To achieve this, a Residual Attention Modulation Block (RAMB) is proposed to generate attention maps using multi-scale residual features to modulate the image features of the corresponding scales. Equipped with this strategy, each subnetwork within the cascaded network possesses its unique optimization objective and emphasis rather than blindly updating its parameters. To further boost the performance, we introduce the Cross-Stage Feature Reuse Connection (CSFRC) and the Reconstruction Dense Connection (RDC), which can reduce information loss and enhance representative ability. We conduct sufficient experiments and evaluate our method on the fastMRI knee dataset using multiple subsampling masks. Comprehensive experimental results show that our method can markedly boost the performance of cascaded networks and significantly outperforms other compared state-of-the-art methods quantitatively and qualitatively.

Modern acceleration in musculoskeletal MRI: applications, implications, and challenges

Magnetic resonance imaging (MRI) is crucial for accurately diagnosing a wide spectrum of musculoskeletal conditions due to its superior soft tissue contrast resolution. However, the long acquisition times of traditional two-dimensional (2D) and three-dimensional (3D) fast and turbo spin-echo (TSE) pulse sequences can limit patient access and comfort. Recent technical advancements have introduced acceleration techniques that significantly reduce MRI times for musculoskeletal examinations. Key acceleration methods include parallel imaging (PI), simultaneous multi-slice acquisition (SMS), and compressed sensing (CS), enabling up to eightfold faster scans while maintaining image quality, resolution, and safety standards. These innovations now allow for 3- to 6-fold accelerated clinical musculoskeletal MRI exams, reducing scan times to 4 to 6 min for joints and spine imaging. Evolving deep learning-based image reconstruction promises even faster scans without compromising quality. Current research indicates that combining acceleration techniques, deep learning image reconstruction, and superresolution algorithms will eventually facilitate tenfold accelerated musculoskeletal MRI in routine clinical practice. Such rapid MRI protocols can drastically reduce scan times by 80-90% compared to conventional methods. Implementing these rapid imaging protocols does impact workflow, indirect costs, and workload for MRI technologists and radiologists, which requires careful management. However, the shift from conventional to accelerated, deep learning-based MRI enhances the value of musculoskeletal MRI by improving patient access and comfort and promoting sustainable imaging practices. This article offers a comprehensive overview of the technical aspects, benefits, and challenges of modern accelerated musculoskeletal MRI, guiding radiologists and researchers in this evolving field.

Enhancing quality and speed in database-free neural network reconstructions of undersampled MRI with SCAMPI

PURPOSE

We present SCAMPI (Sparsity Constrained Application of deep Magnetic resonance Priors for Image reconstruction), an untrained deep Neural Network for MRI reconstruction without previous training on datasets. It expands the Deep Image Prior approach with a multidomain, sparsity-enforcing loss function to achieve higher image quality at a faster convergence speed than previously reported methods.

METHODS

Two-dimensional MRI data from the FastMRI dataset with Cartesian undersampling in phase-encoding direction were reconstructed for different acceleration rates for single coil and multicoil data.

RESULTS

The performance of our architecture was compared to state-of-the-art Compressed Sensing methods and ConvDecoder, another untrained Neural Network for two-dimensional MRI reconstruction. SCAMPI outperforms these by better reducing undersampling artifacts and yielding lower error metrics in multicoil imaging. In comparison to ConvDecoder, the U-Net architecture combined with an elaborated loss-function allows for much faster convergence at higher image quality. SCAMPI can reconstruct multicoil data without explicit knowledge of coil sensitivity profiles. Moreover, it is a novel tool for reconstructing undersampled single coil k-space data.

CONCLUSION

Our approach avoids overfitting to dataset features, that can occur in Neural Networks trained on databases, because the network parameters are tuned only on the reconstruction data. It allows better results and faster reconstruction than the baseline untrained Neural Network approach.

Ultrafast Brain MRI at 3 T for MS: Evaluation of a 51-Second Deep Learning-Enhanced T2-EPI-FLAIR Sequence

In neuroimaging, there is no equivalent alternative to magnetic resonance imaging (MRI). However, image acquisitions are generally time-consuming, which may limit utilization in some cases, e.g., in patients who cannot remain motionless for long or suffer from claustrophobia, or in the event of extensive waiting times. For multiple sclerosis (MS) patients, MRI plays a major role in drug therapy decision-making. The purpose of this study was to evaluate whether an ultrafast, T2-weighted (T2w), deep learning-enhanced (DL), echo-planar-imaging-based (EPI) fluid-attenuated inversion recovery (FLAIR) sequence (FLAIRUF) that has targeted neurological emergencies so far might even be an option to detect MS lesions of the brain compared to conventional FLAIR sequences. Therefore, 17 MS patients were enrolled prospectively in this exploratory study. Standard MRI protocols and ultrafast acquisitions were conducted at 3 tesla (T), including three-dimensional (3D)-FLAIR, turbo/fast spin-echo (TSE)-FLAIR, and FLAIRUF. Inflammatory lesions were grouped by size and location. Lesion conspicuity and image quality were rated on an ordinal five-point Likert scale, and lesion detection rates were calculated. Statistical analyses were performed to compare results. Altogether, 568 different lesions were found. Data indicated no significant differences in lesion detection (sensitivity and positive predictive value [PPV]) between FLAIRUF and axially reconstructed 3D-FLAIR (lesion size ≥3 mm × ≥2 mm) and no differences in sensitivity between FLAIRUF and TSE-FLAIR (lesion size ≥3 mm total). Lesion conspicuity in FLAIRUF was similar in all brain regions except for superior conspicuity in the occipital lobe and inferior conspicuity in the central brain regions. Further findings include location-dependent limitations of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) as well as artifacts such as spatial distortions in FLAIRUF. In conclusion, FLAIRUF could potentially be an expedient alternative to conventional methods for brain imaging in MS patients since the acquisition can be performed in a fraction of time while maintaining good image quality.

Impact of Emerging Deep Learning-Based MR Image Reconstruction Algorithms on Abdominal MRI Radiomic Features

OBJECTIVE

This study aims to evaluate, on one MRI vendor's platform, the impact of deep learning (DL)-based reconstruction techniques on MRI radiomic features compared to conventional image reconstruction techniques.

METHODS

Under IRB approval and informed consent, we prospectively collected undersampled coronal T2-weighted MR images of the abdomen (1.5 T; Philips Healthcare) from 17 pediatric and adult subjects and reconstructed them using a conventional image reconstruction technique (compressed sensitivity encoding [C-SENSE]) and two DL-based reconstruction techniques (SmartSpeed [Philips Healthcare, US FDA cleared] and SmartSpeed with Super Resolution [SmartSpeed-SuperRes, not US FDA cleared to date]). Eight regions of interest (ROIs) across organs/tissues (liver, spleen, kidney, pancreas, fat, and muscle) were manually placed. Eighty-six MRI radiomic features were then extracted. Pearson's correlation coefficients (PCCs) and intraclass correlation coefficients (ICCs) were calculated between (A) C-SENSE versus SmartSpeed, and (B) C-SENSE versus SmartSpeed-SuperRes. To quantify the impact from the perspective of the whole MR image, cross-ROI mean PCCs and ICCs were calculated for individual radiomic features. The impact of image reconstruction on individual radiomic features in different organs/tissues was evaluated using ANOVA analyses.

RESULTS

According to cross-ROI mean PCCs, 50 out of 86 radiomic features were highly correlated (PCC, ≥0.8) between SmartSpeed and C-SENSE, whereas only 15 radiomic features were highly correlated between SmartSpeed-SuperRes and C-SENSE reconstructions. According to cross-ROI mean ICCs, 58 out of 86 radiomic features had high agreements (ICC ≥0.75) between SmartSpeed and C-SENSE, whereas only 9 radiomic features had high agreements between SmartSpeed-SuperRes and C-SENSE reconstructions. For SmartSpeed reconstruction, the psoas muscle ROI appeared to be impacted most with the lowest median (IQR) correlation of 0.57 (0.25). The circular liver ROI was impacted most by SmartSpeed-SuperRes (PCC, 0.60 [0.22]). ANOVA analyses suggest that the impact of DL reconstruction algorithms on radiomic features varies significantly among different organs/tissues (P < 0.001).

CONCLUSIONS

MRI radiomic features are significantly altered by DL-based reconstruction compared to a conventional reconstruction technique. The impact of DL reconstruction algorithms on radiomic features varies significantly between different organs/tissues.

Attention-Based MultiOffset Deep Learning Reconstruction of Chemical Exchange Saturation Transfer (AMO-CEST) MRI

One challenge of chemical exchange saturation transfer (CEST) magnetic resonance imaging (MRI) is the long scan time due to multiple acquisitions of images at different saturation frequency offsets. k-space under-sampling strategy is commonly used to accelerate MRI acquisition, while this could introduce artifacts and reduce signal-to-noise ratio (SNR). To accelerate CEST-MRI acquisition while maintaining suitable image quality, we proposed an attention-based multioffset deep learning reconstruction network (AMO-CEST) with a multiple radial k-space sampling strategy for CEST-MRI. The AMO-CEST also contains dilated convolution to enlarge the receptive field and data consistency module to preserve the sampled k-space data. We evaluated the proposed method on a mouse brain dataset containing 5760 CEST images acquired at a pre-clinical 3 T MRI scanner. Quantitative results demonstrated that AMO-CEST showed obvious improvement over zero-filling method with a PSNR enhancement of 11 dB, a SSIM enhancement of 0.15, and a NMSE decrease of [Formula: see text] in three acquisition orientations. Compared with other deep learning-based models, AMO-CEST showed visual and quantitative improvements in images from three different orientations. We also extracted molecular contrast maps, including the amide proton transfer (APT) and the relayed nuclear Overhauser enhancement (rNOE). The results demonstrated that the CEST contrast maps derived from the CEST images of AMO-CEST were comparable to those derived from the original high-resolution CEST images. The proposed AMO-CEST can efficiently reconstruct high-quality CEST images from under-sampled k-space data and thus has the potential to accelerate CEST-MRI acquisition.

Role of Magnetic Resonance Spectroscopy in Evaluating Choline Levels in Gallbladder Carcinoma: A Comprehensive Review

Gallbladder carcinoma (GBC) presents a significant clinical challenge due to its aggressive nature and often asymptomatic progression, resulting in late-stage diagnoses and a poor prognosis. Early detection and accurate staging are pivotal for improving patient outcomes, highlighting the critical role of advanced imaging techniques in oncological practice. Magnetic resonance spectroscopy (MRS) has emerged as a valuable non-invasive tool capable of assessing biochemical changes within tissues, including alterations in choline metabolism-a biomarker indicative of cell membrane turnover and proliferation. This review explores the application of MRS in evaluating choline levels in gallbladder carcinoma, synthesizing current literature to elucidate its potential in clinical settings. By analyzing studies investigating the correlation between choline levels detected via MRS and tumor characteristics, this review underscores MRS's role in enhancing diagnostic precision and guiding therapeutic decision-making. Moreover, it discusses the challenges and limitations associated with MRS in clinical practice alongside future research and technological advancement directions. Ultimately, integrating MRS into the diagnostic armamentarium for gallbladder carcinoma promises to improve early detection and treatment outcomes. This review provides insights into the evolving landscape of MRS in oncology, emphasizing its contribution to personalized medicine approaches aimed at optimizing patient care and management strategies for GBC.

Deep Learning Reconstruction of Accelerated MRI: False-Positive Cartilage Delamination Inserted in MRI Arthrography Under Traction

OBJECTIVES

The radiological imaging industry is developing and starting to offer a range of novel artificial intelligence software solutions for clinical radiology. Deep learning reconstruction of magnetic resonance imaging data seems to allow for the acceleration and undersampling of imaging data. Resulting reduced acquisition times would lead to greater machine utility and to greater cost-efficiency of machine operations.

MATERIALS AND METHODS

Our case shows images from magnetic resonance arthrography under traction of the right hip joint from a 30-year-old, otherwise healthy, male patient.

RESULTS

The undersampled image data when reconstructed by a deep learning tool can contain false-positive cartilage delamination and false-positive diffuse cartilage defects.

CONCLUSIONS

In the future, precision of this novel technology will have to be put to thorough testing. Bias of systems, in particular created by the choice of training data, will have to be part of those assessments.

Deep-learning-based super-resolution for accelerating chemical exchange saturation transfer MRI

Chemical exchange saturation transfer (CEST) MRI is a molecular imaging tool that provides physiological information about tissues, making it an invaluable tool for disease diagnosis and guided treatment. Its clinical application requires the acquisition of high-resolution images capable of accurately identifying subtle regional changes in vivo, while simultaneously maintaining a high level of spectral resolution. However, the acquisition of such high-resolution images is time consuming, presenting a challenge for practical implementation in clinical settings. Among several techniques that have been explored to reduce the acquisition time in MRI, deep-learning-based super-resolution (DLSR) is a promising approach to address this problem due to its adaptability to any acquisition sequence and hardware. However, its translation to CEST MRI has been hindered by the lack of the large CEST datasets required for network development. Thus, we aim to develop a DLSR method, named DLSR-CEST, to reduce the acquisition time for CEST MRI by reconstructing high-resolution images from fast low-resolution acquisitions. This is achieved by first pretraining the DLSR-CEST on human brain T1w and T2w images to initialize the weights of the network and then training the network on very small human and mouse brain CEST datasets to fine-tune the weights. Using the trained DLSR-CEST network, the reconstructed CEST source images exhibited improved spatial resolution in both peak signal-to-noise ratio and structural similarity index measure metrics at all downsampling factors (2-8). Moreover, amide CEST and relayed nuclear Overhauser effect maps extrapolated from the DLSR-CEST source images exhibited high spatial resolution and low normalized root mean square error, indicating a negligible loss in Z-spectrum information. Therefore, our DLSR-CEST demonstrated a robust reconstruction of high-resolution CEST source images from fast low-resolution acquisitions, thereby improving the spatial resolution and preserving most Z-spectrum information.

Imaging the Lung in ARDS: A Primer

Despite periodic changes in the clinical definition of ARDS, imaging of the lung remains a central component of its diagnostic identification. Several imaging modalities are available to the clinician to establish a diagnosis of the syndrome, monitor its clinical course, or assess the impact of treatment and management strategies. Each imaging modality provides unique insight into ARDS from structural and/or functional perspectives. This review will highlight several methods for lung imaging in ARDS, emphasizing basic operational and physical principles for the respiratory therapist. Advantages and disadvantages of each modality will be discussed in the context of their utility for clinical management and decision-making.

Growth-Associated Protein 43 and Tensor-Based Morphometry Indices in Mild Cognitive Impairment

Growth-associated protein 43 (GAP-43) is found in the axonal terminal of neurons in the limbic system, which is affected in people with Alzheimer's disease (AD). We assumed GAP-43 may contribute to AD progression and serve as a biomarker. So, in a two-year follow-up study, we assessed GAP-43 changes and whether they are correlated with tensor-based morphometry (TBM) findings in patients with mild cognitive impairment (MCI). We included MCI and cognitively normal (CN) people with available baseline and follow-up cerebrospinal fluid (CSF) GAP-43 and TBM findings from the ADNI database. We assessed the difference between the two groups and correlations in each group at each time point. CSF GAP-43 and TBM measures were similar in the two study groups in all time points, except for the accelerated anatomical region of interest (ROI) of CN subjects that were significantly greater than those of MCI. The only significant correlations with GAP-43 observed were those inverse correlations with accelerated and non-accelerated anatomical ROI in MCI subjects at baseline. Plus, all TBM metrics decreased significantly in all study groups during the follow-up in contrast to CSF GAP-43 levels. Our study revealed significant associations between CSF GAP-43 levels and TBM indices among people of the AD spectrum.

Deep learning for accelerated and robust MRI reconstruction

Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology. This review paper provides a comprehensive overview of recent advances in DL for MRI reconstruction, and focuses on various DL approaches and architectures designed to improve image quality, accelerate scans, and address data-related challenges. It explores end-to-end neural networks, pre-trained and generative models, and self-supervised methods, and highlights their contributions to overcoming traditional MRI limitations. It also discusses the role of DL in optimizing acquisition protocols, enhancing robustness against distribution shifts, and tackling biases. Drawing on the extensive literature and practical insights, it outlines current successes, limitations, and future directions for leveraging DL in MRI reconstruction, while emphasizing the potential of DL to significantly impact clinical imaging practices.

Deep learning-based super-resolution of structural brain MRI at 1.5 T: application to quantitative volume measurement

OBJECTIVE

This study investigated the feasibility of using deep learning-based super-resolution (DL-SR) technique on low-resolution (LR) images to generate high-resolution (HR) MR images with the aim of scan time reduction. The efficacy of DL-SR was also assessed through the application of brain volume measurement (BVM).

MATERIALS AND METHODS

In vivo brain images acquired with 3D-T1W from various MRI scanners were utilized. For model training, LR images were generated by downsampling the original 1 mm-2 mm isotropic resolution images. Pairs of LR and HR images were used for training 3D residual dense net (RDN). For model testing, actual scanned 2 mm isotropic resolution 3D-T1W images with one-minute scan time were used. Normalized root-mean-square error (NRMSE), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) were used for model evaluation. The evaluation also included brain volume measurement, with assessments of subcortical brain regions.

RESULTS

The results showed that DL-SR model improved the quality of LR images compared with cubic interpolation, as indicated by NRMSE (24.22% vs 30.13%), PSNR (26.19 vs 24.65), and SSIM (0.96 vs 0.95). For volumetric assessments, there were no significant differences between DL-SR and actual HR images (p > 0.05, Pearson's correlation > 0.90) at seven subcortical regions.

DISCUSSION

The combination of LR MRI and DL-SR enables addressing prolonged scan time in 3D MRI scans while providing sufficient image quality without affecting brain volume measurement.

Multi-average high-acceleration modified volumetric interpolated breath-hold examination (VIBE) for free-breathing multiphase contrast-enhanced liver MRI: a comparative study with breath-hold VIBE

BACKGROUND

Breath-hold volumetric interpolated breath-hold examination (BH-VIBE) of multiphase contrast-enhanced liver magnetic resonance imaging (MPCE-LMRI) requires good cooperative individuals to comply with multiple breath-holds.

PURPOSE

To develop a free-breathing modified VIBE (FB-mVIBE) as a substitute of BH-VIBE in MPCE-LMRI.

MATERIAL AND METHODS

We modified VIBE with a high acceleration factor (2 × 2) and four averages to produce the mVIBE scan. A total of 90 individuals (40 men; mean age = 54.6 ± 10.0 years) who had received MPCE-LMRI as part of a voluntary health check-up for oncology survey were enrolled. Each participant was scanned in four phases (pre-contrast, arterial phase, venous phase, and delay phase), and each phase had two sequential scans. To encounter the timing effect of contrast enhancement, three scan orders were designed: BH-VIBE and FB-mVIBE (group A, n = 30); BH-VIBE and FB-VIBE (group B, n = 30); and FB-mVIBE and BH-VIBE (group C, n = 30). The comparisons included the objective measurements and 25 visual-score by two abdominal radiologists independently.

RESULTS

Consistency between raters was observed for all three sequences (intraclass correlation coefficient [ICC] = 0.741-0.829). For rater 1, the mean scores of FB-mVIBE (23.67 ± 1.32) were equal to those of BH-VIBE (23.83 ± 1.98) in groups C and B (P = 0.852). The mean scores of FB-mVIBE (22.07 ± 3.02), but significantly higher than those of FB-VIBE (14.7 ± 3.41) in groups A and B (P <0.001). Similar scores were found for rater 2. The objective measurement of FB-mVIBE were equal to or higher than BH-VIBE and markedly superior to FB-VIBE.

CONCLUSION

FB-mVIBE is a practical alternative to BH-VIBE for individuals who cannot cooperate with multiple breath-holds for MPCE-LMRI.

Improving the efficiency and accuracy of cardiovascular magnetic resonance with artificial intelligence-review of evidence and proposition of a roadmap to clinical translation

BACKGROUND

Cardiovascular magnetic resonance (CMR) is an important imaging modality for the assessment of heart disease; however, limitations of CMR include long exam times and high complexity compared to other cardiac imaging modalities. Recently advancements in artificial intelligence (AI) technology have shown great potential to address many CMR limitations. While the developments are remarkable, translation of AI-based methods into real-world CMR clinical practice remains at a nascent stage and much work lies ahead to realize the full potential of AI for CMR.

METHODS

Herein we review recent cutting-edge and representative examples demonstrating how AI can advance CMR in areas such as exam planning, accelerated image reconstruction, post-processing, quality control, classification and diagnosis.

RESULTS

These advances can be applied to speed up and simplify essentially every application including cine, strain, late gadolinium enhancement, parametric mapping, 3D whole heart, flow, perfusion and others. AI is a unique technology based on training models using data. Beyond reviewing the literature, this paper discusses important AI-specific issues in the context of CMR, including (1) properties and characteristics of datasets for training and validation, (2) previously published guidelines for reporting CMR AI research, (3) considerations around clinical deployment, (4) responsibilities of clinicians and the need for multi-disciplinary teams in the development and deployment of AI in CMR, (5) industry considerations, and (6) regulatory perspectives.

CONCLUSIONS

Understanding and consideration of all these factors will contribute to the effective and ethical deployment of AI to improve clinical CMR.

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.

Evaluation of deep-learning TSE images in clinical musculoskeletal imaging

In this study, we compared the fat-saturated (FS) and non-FS turbo spin echo (TSE) magnetic resonance imaging knee sequences reconstructed conventionally (conventional-TSE) against a deep learning-based reconstruction of accelerated TSE (DL-TSE) scans. A total of 232 conventional-TSE and DL-TSE image pairs were acquired for comparison. For each consenting patient, one of the clinically acquired conventional-TSE proton density-weighted sequences in the sagittal or coronal planes (FS and non-FS), or in the axial plane (non-FS), was repeated using a research DL-TSE sequence. The DL-TSE reconstruction resulted in an image resolution that increased by at least 45% and scan times that were up to 52% faster compared to the conventional TSE. All images were acquired on a MAGNETOM Vida 3T scanner (Siemens Healthineers AG, Erlangen, Germany). The reporting radiologists, blinded to the acquisition time, were requested to qualitatively compare the DL-TSE against the conventional-TSE reconstructions. Despite having a faster acquisition time, the DL-TSE was rated to depict smaller structures better for 139/232 (60%) cases, equivalent for 72/232 (31%) cases and worse for 21/232 (9%) cases compared to the conventional-TSE. Overall, the radiologists preferred the DL-TSE reconstruction in 124/232 (53%) cases and stated no preference, implying equivalence, for 65/232 (28%) cases. DL-TSE reconstructions enabled faster acquisition times while enhancing spatial resolution and preserving the image contrast. From these results, the DL-TSE provided added or comparable clinical value and utility in less time. DL-TSE offers the opportunity to further reduce the overall examination time and improve patient comfort with no loss in diagnostic accuracy.

Clinical feasibility of post-contrast accelerated 3D T1-Sampling Perfection with Application-optimized Contrasts using different flip angle Evolutions (SPACE) with iterative denoising for intracranial enhancing lesions: a retrospective study

BACKGROUND

Post-contrast T1-Sampling Perfection with Application-optimized Contrasts using different flip angle Evolutions (SPACE) is the preferred 3D T1 spin-echo sequence for evaluating brain metastases, regardless of the prolonged scan time.

PURPOSE

To evaluate the application of accelerated post-contrast T1-SPACE with iterative denoising (ID) for intracranial enhancing lesions in oncologic patients.

MATERIAL AND METHODS

For evaluation of intracranial lesions, 108 patients underwent standard and accelerated T1-SPACE during the same imaging session. Two neuroradiologists evaluated the overall image quality, artifacts, degree of enhancement, mean contrast-to-noise ratiolesion/parenchyma, and number of enhancing lesions for standard and accelerated T1-SPACE without ID.

RESULTS

Although there was a significant difference in the overall image quality and mean contrast-to-noise ratiolesion/parenchyma between standard and accelerated T1-SPACE without ID and accelerated SPACE with and without ID, there was no significant difference between standard and accelerated T1-SPACE with ID. Accelerated T1-SPACE showed more artifacts than standard T1-SPACE; however, accelerated T1-SPACE with ID showed significantly fewer artifacts than accelerated T1-SPACE without ID. Accelerated T1-SPACE without ID showed a significantly lower number of enhancing lesions than standard- and accelerated T1-SPACE with ID; however, there was no significant difference between standard and accelerated T1-SPACE with ID, regardless of lesion size.

CONCLUSION

Although accelerated T1-SPACE markedly decreased the scan time, it showed lower overall image quality and lesion detectability than the standard T1-SPACE. Application of ID to accelerated T1-SPACE resulted in comparable overall image quality and detection of enhancing lesions in brain parenchyma as standard T1-SPACE. Accelerated T1-SPACE with ID may be a promising replacement for standard T1-SPACE.

Deep learning denoising reconstruction enables faster T2-weighted FLAIR sequence acquisition with satisfactory image quality

INTRODUCTION

Deep learning reconstruction (DLR) technologies are the latest methods attempting to solve the enduring problem of reducing MRI acquisition times without compromising image quality. The clinical utility of this reconstruction technique is yet to be fully established. This study aims to assess whether a commercially available DLR technique applied to 2D T2-weighted FLAIR brain images allows a reduction in scan time, without compromising image quality and thus diagnostic accuracy.

METHODS

47 participants (24 male, mean age 55.9 ± 18.7 SD years, range 20-89 years) underwent routine, clinically indicated brain MRI studies in March 2022, that included a standard-of-care (SOC) T2-weighted FLAIR sequence, and an accelerated acquisition that was reconstructed using the DLR denoising product. Overall image quality, lesion conspicuity, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and artefacts for each sequence, and preferred sequence on direct comparison, were subjectively assessed by two readers.

RESULTS

There was a strong preference for SOC FLAIR sequence for overall image quality (P = 0.01) and head-to-head comparison (P < 0.001). No difference was observed for lesion conspicuity (P = 0.49), perceived SNR (P = 1.0), and perceived CNR (P = 0.84). There was no difference in motion (P = 0.57) nor Gibbs ringing (P = 0.86) artefacts. Phase ghosting (P = 0.038) and pseudolesions were significantly more frequent (P < 0.001) on DLR images.

CONCLUSION

DLR algorithm allowed faster FLAIR acquisition times with comparable image quality and lesion conspicuity. However, an increased incidence and severity of phase ghosting artefact and presence of pseudolesions using this technique may result in a reduction in reading speed, efficiency, and diagnostic confidence.

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.

Scan-Specific Self-Supervised Bayesian Deep Non-Linear Inversion for Undersampled MRI Reconstruction

Magnetic resonance imaging is subject to slow acquisition times due to the inherent limitations in data sampling. Recently, supervised deep learning has emerged as a promising technique for reconstructing sub-sampled MRI. However, supervised deep learning requires a large dataset of fully-sampled data. Although unsupervised or self-supervised deep learning methods have emerged to address the limitations of supervised deep learning approaches, they still require a database of images. In contrast, scan-specific deep learning methods learn and reconstruct using only the sub-sampled data from a single scan. Here, we introduce Scan-Specific Self-Supervised Bayesian Deep Non-Linear Inversion (DNLINV) that does not require an auto calibration scan region. DNLINV utilizes a Deep Image Prior-type generative modeling approach and relies on approximate Bayesian inference to regularize the deep convolutional neural network. We demonstrate our approach on several anatomies, contrasts, and sampling patterns and show improved performance over existing approaches in scan-specific calibrationless parallel imaging and compressed sensing.

Non-Cartesian 3D-SPARKLING vs Cartesian 3D-EPI encoding schemes for functional Magnetic Resonance Imaging at 7 Tesla

The quest for higher spatial and/or temporal resolution in functional MRI (fMRI) while preserving a sufficient temporal signal-to-noise ratio (tSNR) has generated a tremendous amount of methodological contributions in the last decade ranging from Cartesian vs. non-Cartesian readouts, 2D vs. 3D acquisition strategies, parallel imaging and/or compressed sensing (CS) accelerations and simultaneous multi-slice acquisitions to cite a few. In this paper, we investigate the use of a finely tuned version of 3D-SPARKLING. This is a non-Cartesian CS-based acquisition technique for high spatial resolution whole-brain fMRI. We compare it to state-of-the-art Cartesian 3D-EPI during both a retinotopic mapping paradigm and resting-state acquisitions at 1mm3 (isotropic spatial resolution). This study involves six healthy volunteers and both acquisition sequences were run on each individual in a randomly-balanced order across subjects. The performances of both acquisition techniques are compared to each other in regards to tSNR, sensitivity to the BOLD effect and spatial specificity. Our findings reveal that 3D-SPARKLING has a higher tSNR than 3D-EPI, an improved sensitivity to detect the BOLD contrast in the gray matter, and an improved spatial specificity. Compared to 3D-EPI, 3D-SPARKLING yields, on average, 7% more activated voxels in the gray matter relative to the total number of activated voxels.

Speeding Up and Improving Image Quality in Glioblastoma MRI Protocol by Deep Learning Image Reconstruction

A fully diagnostic MRI glioma protocol is key to monitoring therapy assessment but is time-consuming and especially challenging in critically ill and uncooperative patients. Artificial intelligence demonstrated promise in reducing scan time and improving image quality simultaneously. The purpose of this study was to investigate the diagnostic performance, the impact on acquisition acceleration, and the image quality of a deep learning optimized glioma protocol of the brain. Thirty-three patients with histologically confirmed glioblastoma underwent standardized brain tumor imaging according to the glioma consensus recommendations on a 3-Tesla MRI scanner. Conventional and deep learning-reconstructed (DLR) fluid-attenuated inversion recovery, and T2- and T1-weighted contrast-enhanced Turbo spin echo images with an improved in-plane resolution, i.e., super-resolution, were acquired. Two experienced neuroradiologists independently evaluated the image datasets for subjective image quality, diagnostic confidence, tumor conspicuity, noise levels, artifacts, and sharpness. In addition, the tumor volume was measured in the image datasets according to Response Assessment in Neuro-Oncology (RANO) 2.0, as well as compared between both imaging techniques, and various clinical-pathological parameters were determined. The average time saving of DLR sequences was 30% per MRI sequence. Simultaneously, DLR sequences showed superior overall image quality (all p < 0.001), improved tumor conspicuity and image sharpness (all p < 0.001, respectively), and less image noise (all p < 0.001), while maintaining diagnostic confidence (all p > 0.05), compared to conventional images. Regarding RANO 2.0, the volume of non-enhancing non-target lesions (p = 0.963), enhancing target lesions (p = 0.993), and enhancing non-target lesions (p = 0.951) did not differ between reconstruction types. The feasibility of the deep learning-optimized glioma protocol was demonstrated with a 30% reduction in acquisition time on average and an increased in-plane resolution. The evaluated DLR sequences improved subjective image quality and maintained diagnostic accuracy in tumor detection and tumor classification according to RANO 2.0.

Accelerated parallel magnetic resonance imaging with compressed sensing using structured sparsity

Purpose

We present a method that combines compressed sensing with parallel imaging that takes advantage of the structure of the sparsifying transformation.

Approach

Previous work has combined compressed sensing with parallel imaging using model-based reconstruction but without taking advantage of the structured sparsity. Blurry images for each coil are reconstructed from the fully sampled center region. The optimization problem of compressed sensing is modified to take these blurry images into account, and it is solved to estimate the missing details.

Results

Using data of brain, ankle, and shoulder anatomies, the combination of compressed sensing with structured sparsity and parallel imaging reconstructs an image with a lower relative error than does sparse SENSE or L1 ESPIRiT, which do not use structured sparsity.

Conclusions

Taking advantage of structured sparsity improves the image quality for a given amount of data as long as a fully sampled region centered on the zero frequency of the appropriate size is acquired.

Fast MRI Reconstruction Using Deep Learning-based Compressed Sensing: A Systematic Review

Magnetic resonance imaging (MRI) has revolutionized medical imaging, providing a non-invasive and highly detailed look into the human body. However, the long acquisition times of MRI present challenges, causing patient discomfort, motion artifacts, and limiting real-time applications. To address these challenges, researchers are exploring various techniques to reduce acquisition time and improve the overall efficiency of MRI. One such technique is compressed sensing (CS), which reduces data acquisition by leveraging image sparsity in transformed spaces. In recent years, deep learning (DL) has been integrated with CS-MRI, leading to a new framework that has seen remarkable growth. DL-based CS-MRI approaches are proving to be highly effective in accelerating MR imaging without compromising image quality. This review comprehensively examines DL-based CS-MRI techniques, focusing on their role in increasing MR imaging speed. We provide a detailed analysis of each category of DL-based CS-MRI including end-to-end, unroll optimization, self-supervised, and federated learning. Our systematic review highlights significant contributions and underscores the exciting potential of DL in CS-MRI. Additionally, our systematic review efficiently summarizes key results and trends in DL-based CS-MRI including quantitative metrics, the dataset used, acceleration factors, and the progress of and research interest in DL techniques over time. Finally, we discuss potential future directions and the importance of DL-based CS-MRI in the advancement of medical imaging. To facilitate further research in this area, we provide a GitHub repository that includes up-to-date DL-based CS-MRI publications and publicly available datasets - https://github.com/mosaf/Awesome-DL-based-CS-MRI.

Flexed elbow, abducted shoulder, forearm supinated (FABS) reconstruction from three-dimensional elbow MRI: diagnostic performance assessment in biceps head anatomy and pathology

AIM

To determine inter-reader analysis and diagnostic performance on digitally reconstructed virtual flexed, abducted, supinated (FABS) imaging from three-dimensional (3D) isotropic elbow magnetic resonance imaging (MRI).

MATERIALS AND METHODS

Six musculoskeletal radiologists independently evaluated elbow MRI images with virtual FABS reconstructions, blinded to clinical findings and final diagnoses. Each radiologist recorded a binary result as to whether the tendon was intact and if both heads were visible, along with a categorical value to the type of tear and extent of retraction in centimetres where applicable. Kappa and interclass correlation (ICC) were reported with 95% confidence intervals. Areas under the receiver operating curve (AUC) were reported.

RESULTS

FABS reconstructions were obtained successfully in all 48 cases. With respect to tendon intactness, visibility of both heads, and type of tear, the Kappa values were 0.66 (0.53-0.78), 0.24 (0.12-0.37), and 0.55 (0.43-0.66), respectively. For the extent of retraction, the ICC was 0.85 (0.79-0.91) when including the tendons with and without retraction and 0.78 (0.61-0.91) when only including tendons with retraction. For tear versus no tear, AUC values were 0.82 (0.74-0.89) to 0.96 (0.91-1.01).

CONCLUSION

Digital reconstruction of FABS positioning is feasible and allows good assessment of individual tendon head tears and retraction with high diagnostic performance.

Effect of Deep Learning Reconstruction on Respiratory-triggered T2-weighted MR Imaging of the Liver: A Comparison between the Single-shot Fast Spin-echo and Fast Spin-echo Sequences

PURPOSE

To compare the effects of deep learning reconstruction (DLR) on respiratory-triggered T2-weighted MRI of the liver between single-shot fast spin-echo (SSFSE) and fast spin-echo (FSE) sequences.

METHODS

Respiratory-triggered fat-suppressed liver T2-weighted MRI was obtained with the FSE and SSFSE sequences at the same spatial resolution in 55 patients. Conventional reconstruction (CR) and DLR were applied to each sequence, and the SNR and liver-to-lesion contrast were measured on FSE-CR, FSE-DLR, SSFSE-CR, and SSFSE-DLR images. Image quality was independently assessed by three radiologists. The results of the qualitative and quantitative analyses were compared among the four types of images using repeated-measures analysis of variance or Friedman's test for normally and non-normally distributed data, respectively, and a visual grading characteristics (VGC) analysis was performed to evaluate the image quality improvement by DLR on the FSE and SSFSE sequences.

RESULTS

The liver SNR was lowest on SSFSE-CR and highest on FSE-DLR and SSFSE-DLR (P < 0.01). The liver-to-lesion contrast did not differ significantly among the four types of images. Qualitatively, noise scores were worst on SSFSE-CR but best on SSFSE-DLR because DLR significantly reduced noise (P < 0.01). In contrast, artifact scores were worst both on FSE-CR and FSE-DLR (P < 0.01) because DLR did not reduce the artifacts. Lesion conspicuity was significantly improved by DLR compared with CR in the SSFSE (P < 0.01) but not in FSE sequences for all readers. Overall image quality was significantly improved by DLR compared with CR for all readers in the SSFSE (P < 0.01) but only one reader in the FSE (P < 0.01). The mean area under the VGC curve values for the FSE-DLR and SSFSE-DLR sequences were 0.65 and 0.94, respectively.

CONCLUSION

In liver T2-weighted MRI, DLR produced more marked improvements in image quality in SSFSE than in FSE.

Hepatobiliary phase imaging in cirrhotic patients using compressed sensing and controlled aliasing in parallel imaging results in higher acceleration

OBJECTIVE

We aimed to compare the image quality and focal lesion detection ability of hepatobiliary phase (HBP) images obtained using compressed sensing (CS) and controlled aliasing in parallel imaging results in higher acceleration (CAIPIRINHA) in patients with liver cirrhosis.

MATERIALS AND METHODS

We retrospectively included 244 gadoxetic acid-enhanced liver MRI from 244 patients with cirrhosis obtained by two HBP images using CS and CAIPIRINHA from July 2020 to December 2020. The optimized resolution and scan time for CS-HBP and CAIPIRINHA-HBP were 0.9 × 0.9 × 1.5 mm3 and 15 s and 1.3 × 1.3 × 3 mm3 and 16 s, respectively. We compared the image quality between the two sets of images in 244 patients and focal lesion (n = 294) analyses for 112 patients.

RESULTS

CS-HBP showed comparable overall image quality (3.7 ± 0.9 vs. 3.6 ± 0.8, p = 0.680), superior liver edge sharpness (3.9 ± 0.6 vs. 3.6 ± 0.5, p < 0.001), and fewer respiratory motion artifacts (4.0 ± 0.7 vs. 3.8 ± 0.5, p < 0.001), but higher non-respiratory artifacts (3.4 ± 0.7 vs. 3.6 ± 0.6, p < 0.001) and subjective image noise (3.5 ± 0.8 vs. 3.6 ± 0.7, p = 0.014) than CAIPIRINHA-HBP. CS-HBP showed a higher signal-to-noise ratio in the liver than CAIPIRINHA-HBP (20.9 ± 9.0 vs. 18.9 ± 7.1, p = 0.008). The pooled sensitivity, specificity, and AUC were 90.0%, 77.5%, and 0.84 for CS-HBP and 73.5%, 82.4%, and 0.78 for CAIPIRINHA-HBP, respectively.

CONCLUSIONS

CS-HBP showed better focal lesion detection ability, comparable overall image quality, and fewer respiratory motion artifacts, but higher non-respiratory artifacts and noise compared to CAIPIRINHA-HBP. Thus, CS-HBP could be recommended for liver MRI in patients with cirrhosis to improve diagnostic performance.

CLINICAL RELEVANCE STATEMENT

Thin-slice CS-HBP may be useful for detecting sub-centimeter hepatocellular carcinoma in cirrhotic patients with Child-Pugh classification A while maintaining comparable subjective image quality.

KEY POINTS

• Compared with controlled aliasing in parallel imaging results in higher acceleration, compressed sensing hepatobiliary phase yielded thinner slices and shorter scan time at a higher accelerating factor. • Compressed sensing hepatobiliary phase showed comparable overall image quality, superior liver edge sharpness, and fewer respiratory motion artifacts, but higher non-respiratory artifacts and subjective image noise than controlled aliasing in parallel imaging results in higher acceleration-hepatobiliary phase. • Compressed sensing hepatobiliary phase can detect sub-centimeter hepatocellular carcinoma in cirrhotic patients with Child-Pugh classification A.

DTI-MR fingerprinting for rapid high-resolution whole-brain T1 , T2 , proton density, ADC, and fractional anisotropy mapping

PURPOSE

This study aims to develop a high-efficiency and high-resolution 3D imaging approach for simultaneous mapping of multiple key tissue parameters for routine brain imaging, including T1 , T2 , proton density (PD), ADC, and fractional anisotropy (FA). The proposed method is intended for pushing routine clinical brain imaging from weighted imaging to quantitative imaging and can also be particularly useful for diffusion-relaxometry studies, which typically suffer from lengthy acquisition time.

METHODS

To address challenges associated with diffusion weighting, such as shot-to-shot phase variation and low SNR, we integrated several innovative data acquisition and reconstruction techniques. Specifically, we used M1-compensated diffusion gradients, cardiac gating, and navigators to mitigate phase variations caused by cardiac motion. We also introduced a data-driven pre-pulse gradient to cancel out eddy currents induced by diffusion gradients. Additionally, to enhance image quality within a limited acquisition time, we proposed a data-sharing joint reconstruction approach coupled with a corresponding sequence design.

RESULTS

The phantom and in vivo studies indicated that the T1 and T2 values measured by the proposed method are consistent with a conventional MR fingerprinting sequence and the diffusion results (including diffusivity, ADC, and FA) are consistent with the spin-echo EPI DWI sequence.

CONCLUSION

The proposed method can achieve whole-brain T1 , T2 , diffusivity, ADC, and FA maps at 1-mm isotropic resolution within 10 min, providing a powerful tool for investigating the microstructural properties of brain tissue, with potential applications in clinical and research settings.

Radiomic feature reliability of amide proton transfer-weighted MR images acquired with compressed sensing at 3T

Compressed sensing (CS) is a novel technique for MRI acceleration. The purpose of this paper was to assess the effects of CS on the radiomic features extracted from amide proton transfer-weighted (APTw) images. Brain tumor MRI data of 40 scans were studied. Standard images using sensitivity encoding (SENSE) with an acceleration factor (AF) of 2 were used as the gold standard, and APTw images using SENSE with CS (CS-SENSE) with an AF of 4 were assessed. Regions of interest (ROIs), including normal tissue, edema, liquefactive necrosis, and tumor, were manually drawn, and the effects of CS-SENSE on radiomics were assessed for each ROI category. An intraclass correlation coefficient (ICC) was first calculated for each feature extracted from APTw images with SENSE and CS-SENSE for all ROIs. Different filters were applied to the original images, and the effects of these filters on the ICCs were further compared between APTw images with SENSE and CS-SENSE. Feature deviations were also provided for a more comprehensive evaluation of the effects of CS-SENSE on radiomic features. The ROI-based comparison showed that most radiomic features extracted from CS-SENSE-APTw images and SENSE-APTw images had moderate or greater reliabilities (ICC ≥ 0.5) for all four ROIs and all eight image sets with different filters. Tumor showed significantly higher ICCs than normal tissue, edema, and liquefactive necrosis. Compared to the original images, filters (such as Exponential or Square) may improve the reliability of radiomic features extracted from CS-SENSE-APTw and SENSE-APTw images.

Deep learning-accelerated image reconstruction in back pain-MRI imaging: reduction of acquisition time and improvement of image quality

INTRODUCTION

Low back pain is a global health issue causing disability and missed work days. Commonly used MRI scans including T1-weighted and T2-weighted images provide detailed information of the spine and surrounding tissues. Artificial intelligence showed promise in improving image quality and simultaneously reducing scan time. This study evaluates the performance of deep learning (DL)-based T2 turbo spin-echo (TSE, T2DLR) and T1 TSE (T1DLR) in lumbar spine imaging regarding acquisition time, image quality, artifact resistance, and diagnostic confidence.

MATERIAL AND METHODS

This retrospective monocentric study included 60 patients with lower back pain who underwent lumbar spinal MRI between February and April 2023. MRI parameters and DL reconstruction (DLR) techniques were utilized to acquire images. Two neuroradiologists independently evaluated image datasets based on various parameters using a 4-point Likert scale.

RESULTS

Accelerated imaging showed significantly less image noise and artifacts, as well as better image sharpness, compared to standard imaging. Overall image quality and diagnostic confidence were higher in accelerated imaging. Relevant disk herniations and spinal fractures were detected in both DLR and conventional images. Both readers favored accelerated imaging in the majority of examinations. The lumbar spine examination time was cut by 61% in accelerated imaging compared to standard imaging.

CONCLUSION

In conclusion, the utilization of deep learning-based image reconstruction techniques in lumbar spinal imaging resulted in significant time savings of up to 61% compared to standard imaging, while also improving image quality and diagnostic confidence. These findings highlight the potential of these techniques to enhance efficiency and accuracy in clinical practice for patients with lower back pain.

Advanced Abdominal MRI Techniques and Problem-Solving Strategies

MRI plays an important role in abdominal imaging because of its ability to detect and characterize focal lesions. However, MRI examinations have several challenges, such as comparatively long scan times and motion management through breath-holding maneuvers. Techniques for reducing scan time with acceptable image quality, such as parallel imaging, compressed sensing, and cutting-edge deep learning techniques, have been developed to enable problem-solving strategies. Additionally, free-breathing techniques for dynamic contrast-enhanced imaging, such as extra-dimensional-volumetric interpolated breath-hold examination, golden-angle radial sparse parallel, and liver acceleration volume acquisition Star, can help patients with severe dyspnea or those under sedation to undergo abdominal MRI. We aimed to present various advanced abdominal MRI techniques for reducing the scan time while maintaining image quality and free-breathing techniques for dynamic imaging and illustrate cases using the techniques mentioned above. A review of these advanced techniques can assist in the appropriate interpretation of sequences.

Evaluation of Compressed SENSE on Image Quality and Reduction of MRI Acquisition Time: A Clinical Validation Study

RATIONALE AND OBJECTIVES

To evaluate the effect of compressed SENSE (CS) in clinical settings on scan time reduction and image quality.

MATERIALS AND METHODS

Ninety-five magnetic resonance imaging (MRI) scans from different anatomical regions were acquired, consisting of a standard protocol sequence (SS) and sequence accelerated with CS. Anonymized paired sequences were randomly displayed and rated by six blinded subspecialty radiologists. Side-by-side evaluation on perceived sharpness, perceived signal-to-noise-ratio (SNR), lesion conspicuity, and artifacts were compared and scored on a five-point Likert scale, and individual image quality was evaluated on a four-point Likert scale.

RESULTS

CS reduced overall scan time by 32% while maintaining acceptable MRI quality for all regions. The largest time savings were seen in the spine (mean = 68 seconds, 44% reduction) followed by the brain (mean = 86 seconds, 37% reduction). The sequence with maximum time savings was intracranial 3D-time-of-flight magnetic resonance angiography (202 seconds, 56% reduction). CS was mildly inferior to SS on perceived sharpness, perceived SNR, and lesion conspicuity (mean scores = 2.32-2.96, P < .001 [1: SS superior; 3: equivalent; 5: CS superior]). CS was equivalent to SS for joint and body scans on overall image quality (CS = 3.02-3.37, SS = 3.04-3.68, P > .05, [1: lowest quality and 4: highest quality]). The overall image quality of CS was slightly less for brain and spine scans (mean CS = 2.79-3.05, mean SS = 3.13-3.43, P = .021) but still diagnostic. Good overall clinical acceptance for CS (88%) was noted with full clinical acceptance for body scans (100%) and high acceptance for other regions (68%-95%).

CONCLUSION

CS significantly reduced MR acquisition time while maintaining acceptable image quality. The implementation of CS may improve departmental workflows and enhance patient care.

Functional Magnetic Resonance Imaging of the Amygdala and Subregions at 3 Tesla: A Scoping Review

The amygdalae are a pair of small brain structures, each of which is composed of three main subregions and whose function is implicated in neuropsychiatric conditions. Functional Magnetic Resonance Imaging (fMRI) has been utilized extensively in investigation of amygdala activation and functional connectivity (FC) with most clinical research sites now utilizing 3 Tesla (3T) MR systems. However, accurate imaging and analysis remains challenging not just due to the small size of the amygdala, but also its location deep in the temporal lobe. Selection of imaging parameters can significantly impact data quality with implications for the accuracy of study results and validity of conclusions. Wide variation exists in acquisition protocols with spatial resolution of some protocols suboptimal for accurate assessment of the amygdala as a whole, and for measuring activation and FC of the three main subregions, each of which contains multiple nuclei with specialized roles. The primary objective of this scoping review is to provide a broad overview of 3T fMRI protocols in use to image the activation and FC of the amygdala with particular reference to spatial resolution. The secondary objective is to provide context for a discussion culminating in recommendations for a standardized protocol for imaging activation of the amygdala and its subregions. As the advantages of big data and protocol harmonization in imaging become more apparent so, too, do the disadvantages of data heterogeneity. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Utility of Echo Planar Imaging With Compressed Sensing-Sensitivity Encoding (EPICS) for the Evaluation of the Head and Neck Region

Purpose This study aimed to compare the image quality between echo planar imaging (EPI) with compressed sensing-sensitivity encoding (EPICS)-based diffusion-weighted imaging (DWI) and conventional parallel imaging (PI)-based DWI of the head and neck. Materials and methods Ten healthy volunteers participated in this study. EPICS-DWI was acquired based on an axial spin-echo EPI sequence with EPICS acceleration factors of 2, 3, and 4, respectively. Conventional PI-DWI was acquired using the same acceleration factors (i.e., 2, 3, and 4). Quantitative assessment was performed by measuring the signal-to-noise ratio (SNR) and apparent diffusion coefficient (ADC) in a circular region of interest (ROI) on the parotid and submandibular glands. For qualitative evaluation, a three-point visual grading system was used to assess the (1) overall image quality and (2) degree of image distortion. Results In the quantitative assessment, the SNR of the parotid gland in EPICS-DWI was significantly higher than that of PI-DWI in acceleration factors of 3 and 4 (p<0.05). In a comparison of ADC values, significant differences were not observed between EPICS-DWI and PI-DWI. In the qualitative assessment, the overall image quality of EPICS-DWI was significantly higher than that of PI-DWI for acceleration factors 3 and 4 (p<0.05). The degree of image distortion was significantly larger in EPICS-DWI with an acceleration factor of 2 than that of 3 or 4 (p<0.01, respectively). Conclusion Under the appropriate parameter setting, EPICS-DWI demonstrated higher SNR and better overall image quality for head and neck imaging than PI-DWI, without increasing image distortion.

A Systematic Review and Identification of the Challenges of Deep Learning Techniques for Undersampled Magnetic Resonance Image Reconstruction

Deep learning (DL) in magnetic resonance imaging (MRI) shows excellent performance in image reconstruction from undersampled k-space data. Artifact-free and high-quality MRI reconstruction is essential for ensuring accurate diagnosis, supporting clinical decision-making, enhancing patient safety, facilitating efficient workflows, and contributing to the validity of research studies and clinical trials. Recently, deep learning has demonstrated several advantages over conventional MRI reconstruction methods. Conventional methods rely on manual feature engineering to capture complex patterns and are usually computationally demanding due to their iterative nature. Conversely, DL methods use neural networks with hundreds of thousands of parameters and automatically learn relevant features and representations directly from the data. Nevertheless, there are some limitations to DL-based techniques concerning MRI reconstruction tasks, such as the need for large, labeled datasets, the possibility of overfitting, and the complexity of model training. Researchers are striving to develop DL models that are more efficient, adaptable, and capable of providing valuable information for medical practitioners. We provide a comprehensive overview of the current developments and clinical uses by focusing on state-of-the-art DL architectures and tools used in MRI reconstruction. This study has three objectives. Our main objective is to describe how various DL designs have changed over time and talk about cutting-edge tactics, including their advantages and disadvantages. Hence, data pre- and post-processing approaches are assessed using publicly available MRI datasets and source codes. Secondly, this work aims to provide an extensive overview of the ongoing research on transformers and deep convolutional neural networks for rapid MRI reconstruction. Thirdly, we discuss several network training strategies, like supervised, unsupervised, transfer learning, and federated learning for rapid and efficient MRI reconstruction. Consequently, this article provides significant resources for future improvement of MRI data pre-processing and fast image reconstruction.

Technical Note: Novel imaging method to obtain gray matter-attenuated inversion recovery image using low-field magnetic resonance imaging systems

INTRODUCTION

The double inversion recovery (DIR) technique suppresses two types of tissue signals with different T1 values by applying two inversion recovery (IR) pulses with different inversion times (TI). In contrast, the double tissue suppression with multi-echo acquisition and single TI combining HIRE (DOMUST-HIRE) method, is a technique enabling the white-matter-attenuated inversion recovery (WAIR) images by setting one inversion time (TI) in a sequence based on the multi-echo method and subtracting the second echo image from the first echo image. Here, we propose a new sequence that can provide the gray-matter-attenuated inversion recovery image based on the DOMUST-HIRE method.

METHODS

In this small clinical study, we performed determination of optimal TI and physical evaluation by imaging a subject's head with T1WI and our proposed method for GAIR images.

RESULTS

Our proposed method could increase the contrast ratio and the contrast-to-noise ratio between white matter (WM) and gray matter (GM), whereas the signal-to-noise ratio WM and GM decreased than with T1WI method.

CONCLUSIONS

Our proposed method can be used to suppress GM and CSF signals.

IMPLICATIONS FOR PRACTICE

The use of our proposed method in low-field MRI systems could provide GAIR image.

New Theory and Faster Computations for Subspace-Based Sensitivity Map Estimation in Multichannel MRI

Sensitivity map estimation is important in many multichannel MRI applications. Subspace-based sensitivity map estimation methods like ESPIRiT are popular and perform well, though can be computationally expensive and their theoretical principles can be nontrivial to understand. In the first part of this work, we present a novel theoretical derivation of subspace-based sensitivity map estimation based on a linear-predictability/structured low-rank modeling perspective. This results in an estimation approach that is equivalent to ESPIRiT, but with distinct theory that may be more intuitive for some readers. In the second part of this work, we propose and evaluate a set of computational acceleration approaches (collectively known as PISCO) that can enable substantial improvements in computation time (up to  ∼ 100× in the examples we show) and memory for subspace-based sensitivity map estimation.

Deep Learning Accelerated Image Reconstruction of Fluid-Attenuated Inversion Recovery Sequence in Brain Imaging: Reduction of Acquisition Time and Improvement of Image Quality

RATIONALE AND OBJECTIVES

Fluid-attenuated inversion recovery (FLAIR) imaging is playing an increasingly significant role in the detection of brain metastases with a concomitant increase in the number of magnetic resonance imaging (MRI) examinations. Therefore, the purpose of this study was to investigate the impact on image quality and diagnostic confidence of an innovative deep learning-based accelerated FLAIR (FLAIRDLR) sequence of the brain compared to conventional (standard) FLAIR (FLAIRS) imaging.

MATERIALS AND METHODS

Seventy consecutive patients with staging cerebral MRIs were retrospectively enrolled in this single-center study. The FLAIRDLR was conducted using the same MRI acquisition parameters as the FLAIRS sequence, except for a higher acceleration factor for parallel imaging (from 2 to 4), which resulted in a shorter acquisition time of 1:39 minute instead of 2:40 minutes (-38%). Two specialized neuroradiologists evaluated the imaging datasets using a Likert scale that ranged from 1 to 4, with 4 indicating the best score for the following parameters: sharpness, lesion demarcation, artifacts, overall image quality, and diagnostic confidence. Additionally, the image preference of the readers and the interreader agreement were assessed.

RESULTS

The average age of the patients was 63 ± 11years. FLAIRDLR exhibited significantly less image noise than FLAIRS, with P-values of< .001 and< .05, respectively. The sharpness of the images and the ability to detect lesions were rated higher in FLAIRDLR, with a median score of 4 compared to a median score of 3 in FLAIRS (P-values of<.001 for both readers). In terms of overall image quality, FLAIRDLR was rated superior to FLAIRS, with a median score of 4 vs 3 (P-values of<.001 for both readers). Both readers preferred FLAIRDLR in 68/70 cases.

CONCLUSION

The feasibility of deep learning FLAIR brain imaging was shown with additional 38% reduction in examination time compared to standard FLAIR imaging. Furthermore, this technique has shown improvement in image quality, noise reduction, and lesion demarcation.

Standardized brain tumor imaging protocols for clinical trials: current recommendations and tips for integration

Standardized MRI acquisition protocols are crucial for reducing the measurement and interpretation variability associated with response assessment in brain tumor clinical trials. The main challenge is that standardized protocols should ensure high image quality while maximizing the number of institutions meeting the acquisition requirements. In recent years, extensive effort has been made by consensus groups to propose different "ideal" and "minimum requirements" brain tumor imaging protocols (BTIPs) for gliomas, brain metastases (BM), and primary central nervous system lymphomas (PCSNL). In clinical practice, BTIPs for clinical trials can be easily integrated with additional MRI sequences that may be desired for clinical patient management at individual sites. In this review, we summarize the general concepts behind the choice and timing of sequences included in the current recommended BTIPs, we provide a comparative overview, and discuss tips and caveats to integrate additional clinical or research sequences while preserving the recommended BTIPs. Finally, we also reflect on potential future directions for brain tumor imaging in clinical trials.

A deep unrolled neural network for real-time MRI-guided brain intervention

Accurate navigation and targeting are critical for neurological interventions including biopsy and deep brain stimulation. Real-time image guidance further improves surgical planning and MRI is ideally suited for both pre- and intra-operative imaging. However, balancing spatial and temporal resolution is a major challenge for real-time interventional MRI (i-MRI). Here, we proposed a deep unrolled neural network, dubbed as LSFP-Net, for real-time i-MRI reconstruction. By integrating LSFP-Net and a custom-designed, MR-compatible interventional device into a 3 T MRI scanner, a real-time MRI-guided brain intervention system is proposed. The performance of the system was evaluated using phantom and cadaver studies. 2D/3D real-time i-MRI was achieved with temporal resolutions of 80/732.8 ms, latencies of 0.4/3.66 s including data communication, processing and reconstruction time, and in-plane spatial resolution of 1 × 1 mm2. The results demonstrated that the proposed method enables real-time monitoring of the remote-controlled brain intervention, and showed the potential to be readily integrated into diagnostic scanners for image-guided neurosurgery.

Accelerated submillimeter wave-encoded magnetic resonance imaging via deep untrained neural network

BACKGROUND

Wave gradient encoding can adequately utilize coil sensitivity profiles to facilitate higher accelerations in parallel magnetic resonance imaging (pMRI). However, there are limitations in mainstream pMRI and a few deep learning (DL) methods for recovering missing data under wave encoding framework: the former is prone to introduce errors from the auto-calibration signals (ACS) signal acquisition and is time-consuming, while the latter requires a large amount of training data.

PURPOSE

To tackle the above issues, an untrained neural network (UNN) model incorporating wave-encoded physical properties and deep generative model, named WDGM, was proposed with additional ACS- and training data-free.

METHODS

Generally, the proposed method can provide powerful missing data interpolation capability using the wave physical encoding framework and designed UNN to characterize the MR image (k-space data) priors. Specifically, the MRI reconstruction combining physical wave encoding and elaborate UNN is modeled as a generalized minimization problem. The designation of UNN is driven by the coil sensitivity maps (CSM) smoothness and k-space linear predictability. And then, the iterative paradigm to recover the full k-space signal is determined by the projected gradient descent, and the complex computation is unrolled to the network with optimized parameters by the optimizer. Simulated wave encoding and in vivo experiments are exploited to demonstrate the feasibility of the proposed method. The best quantitative metrics RMSE/SSIM/PSNR of 0.0413, 0.9514, and 37.4862 gave competitive results in all experiments with at least six-fold acceleration, respectively.

RESULTS

In vivo experiments of human brains and knees showed that the proposed method can achieve comparable reconstruction quality and even has superiority relative to the comparison, especially at a high resolution of 0.67 mm and fewer ACS. In addition, the proposed method has a higher computational efficiency achieving a computation time of 9.6 s/per slice.

CONCLUSIONS

The model proposed in this work addresses two limitations of MRI reconstruction in the wave encoding framework. The first is to eliminate the need for ACS signal acquisition to perform the time-consuming calibration process and to avoid errors such as motion during the acquisition procedure. Furthermore, the proposed method has clinical application friendly without the need to prepare large training datasets, which is difficult in the clinical. All results of the proposed method demonstrate more confidence in both quantitative and qualitative metrics. In addition, the proposed method can achieve higher computational efficiency.

DENOISING DIFFUSION MRI: CONSIDERATIONS AND IMPLICATIONS FOR ANALYSIS

Development of diffusion MRI (dMRI) denoising approaches has experienced considerable growth over the last years. As noise can inherently reduce accuracy and precision in measurements, its effects have been well characterised both in terms of uncertainty increase in dMRI-derived features and in terms of biases caused by the noise floor, the smallest measurable signal given the noise level. However, gaps in our knowledge still exist in objectively characterising dMRI denoising approaches in terms of both of these effects and assessing their efficacy. In this work, we reconsider what a denoising method should and should not do and we accordingly define criteria to characterise the performance. We propose a comprehensive set of evaluations, including i) benefits in improving signal quality and reducing noise variance, ii) gains in reducing biases and the noise floor and improving, iii) preservation of spatial resolution, iv) agreement of denoised data against a gold standard, v) gains in downstream parameter estimation (precision and accuracy), vi) efficacy in enabling noise-prone applications, such as ultra-high-resolution imaging. We further provide newly acquired complex datasets (magnitude and phase) with multiple repeats that sample different SNR regimes to highlight performance differences under different scenarios. Without loss of generality, we subsequently apply a number of exemplar patch-based denoising algorithms to these datasets, including Non-Local Means, Marchenko-Pastur PCA (MPPCA) in the magnitude and complex domain and NORDIC, and compare them with respect to the above criteria and against a gold standard complex average of multiple repeats. We demonstrate that all tested denoising approaches reduce noise-related variance, but not always biases from the elevated noise floor. They all induce a spatial resolution penalty, but its extent can vary depending on the method and the implementation. Some denoising approaches agree with the gold standard more than others and we demonstrate challenges in even defining such a standard. Overall, we show that dMRI denoising performed in the complex domain is advantageous to magnitude domain denoising with respect to all the above criteria.