Fast Magnetic Resonance Imaging Research Articles

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

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 3.0T cervical spine fast magnetic resonance imaging (MRI) images, compared with conventional images. The 3.0T 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. 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 197s through the DLR scheme. Our investigation establishes that 3.0T 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.

Feasibility and diagnostic accuracy of fast whole-body MRI in slightly to moderately injured trauma patients.

To determine the feasibility and diagnostic accuracy of fast whole-body magnetic resonance imaging (WB-MRI) compared to whole-body computed tomography (WB-CT) in detecting injuries of slightly to moderately injured trauma patients. In a prospective single-center approach, trauma patients from convenience sampling with an expected Abbreviated Injury Scale (AIS) score ≤ 3 at admission, received an indicated contrast-enhanced WB-CT (reference standard) and a plain WB-MRI (index test) voluntarily up to five days after trauma. Two radiologists, blinded to the WB-CT findings, evaluated the absence or presence of injuries with WB-MRI in four body regions: head, torso, axial skeleton, and upper extremity. Diagnostic accuracy was determined using sensitivity, specificity, positive predictive value, and negative predictive value by body region. Between June 2019 and July 2021, 40 patients were assessed for eligibility of whom 35 (median age (interquartile range): 50 (32.5) years; 26 men) received WB-MRI. Of 140 body regions (35 patients × 4 regions), 31 true positive, 6 false positive, 94 true negative, and 9 false negative findings were documented with WB-MRI. Thus, plain WB-MRI achieved a total sensitivity of 77.5% (95%-confidence interval (CI): (61.6-89.2%)), specificity of 94% (95%-CI: (87.4-97.8%)), and diagnostic accuracy of 89.3% (95%-CI: (82.9-93.9%)). Across the four regions sensitivity and specificity varied: head (66.7%/93.1%), torso (62.5%/96.3%), axial skeleton (91.3%/75%), upper extremity (33.3%/100%). Both radiologists showed substantial agreement on the WB-MRI reading (Cohen's Kappa: 0.66, 95%-CI: (0.51-0.81)). Regarding injury detection, WB-MRI is feasible in slightly to moderately injured trauma patients, especially in the axial skeleton. Besides offering a radiation-free approach, whole-body MRI detects injuries almost identically to whole-body CT in slightly to moderately injured trauma patients, who comprise a relevant share of all trauma patients. Whole-body MRI could offer radiation-free injury detection in slightly to moderately injured trauma patients. Whole-body MRI detected injuries almost identically compared to whole-body CT in this population. Whole-body MRI could be a radiation-free approach for slightly to moderately injured young trauma patients.

HFGN: High-Frequency residual Feature Guided Network for fast MRI reconstruction

Magnetic Resonance Imaging (MRI) is a valuable medical imaging technology, while it suffers from a long acquisition time. Various methods have been proposed to reconstruct sharp images from undersampled k-space data to reduce imaging time. However, these methods hardly reconstruct high-quality aliasing-free Magnetic Resonance (MR) images with clear structures, especially in high-frequency components. To address this problem, we propose a High-Frequency residual feature Guided Network (HFGN) for fast MRI reconstruction. HFGN uses a sub-network, High-Frequency Extraction Network (HFEN), to learn the difference between the U-Net reconstruction result and the ground truth, then uses the learned features to guide the reconstruction of the network. In the reconstruction network, we propose Residual Channel and Spatial Attention block (RCSA), which uses frequency domain and image domain convolution branching to learn the global and local features of the image simultaneously. The experiment results under different acceleration rates on different datasets demonstrate that our proposed method surpasses the existing state-of-the-art methods.

Reinforcement Learning and Transformer for Fast Magnetic Resonance Imaging Scan

Reinforcement Learning and Transformer for Fast Magnetic Resonance Imaging Scan

MRI reconstruction with enhanced self-similarity using graph convolutional network

BackgroundRecent Convolutional Neural Networks (CNNs) perform low-error reconstruction in fast Magnetic Resonance Imaging (MRI). Most of them convolve the image with kernels and successfully explore the local information. Nonetheless, the non-local image information, which is embedded among image patches relatively far from each other, may be lost due to the limitation of the receptive field of the convolution kernel. We aim to incorporate a graph to represent non-local information and improve the reconstructed images by using the Graph Convolutional Enhanced Self-Similarity (GCESS) network.MethodsFirst, the image is reconstructed into the graph to extract the non-local self-similarity in the image. Second, GCESS uses spatial convolution and graph convolution to process the information in the image, so that local and non-local information can be effectively utilized. The network strengthens the non-local similarity between similar image patches while reconstructing images, making the reconstruction of structure more reliable.ResultsExperimental results on in vivo knee and brain data demonstrate that the proposed method achieves better artifact suppression and detail preservation than state-of-the-art methods, both visually and quantitatively. Under 1D Cartesian sampling with 4 × acceleration (AF = 4), the PSNR of knee data reached 34.19 dB, 1.05 dB higher than that of the compared methods; the SSIM achieved 0.8994, 2% higher than the compared methods. Similar results were obtained for the reconstructed images under other sampling templates as demonstrated in our experiment.ConclusionsThe proposed method successfully constructs a hybrid graph convolution and spatial convolution network to reconstruct images. This method, through its training process, amplifies the non-local self-similarities, significantly benefiting the structural integrity of the reconstructed images. Experiments demonstrate that the proposed method outperforms the state-of-the-art reconstruction method in suppressing artifacts, as well as in preserving image details.

High-Frequency Space Diffusion Model for Accelerated MRI.

Diffusion models with continuous stochastic differential equations (SDEs) have shown superior performances in image generation. It can serve as a deep generative prior to solving the inverse problem in magnetic resonance (MR) reconstruction. However, low-frequency regions of k -space data are typically fully sampled in fast MR imaging, while existing diffusion models are performed throughout the entire image or k -space, inevitably introducing uncertainty in the reconstruction of low-frequency regions. Additionally, existing diffusion models often demand substantial iterations to converge, resulting in time-consuming reconstructions. To address these challenges, we propose a novel SDE tailored specifically for MR reconstruction with the diffusion process in high-frequency space (referred to as HFS-SDE). This approach ensures determinism in the fully sampled low-frequency regions and accelerates the sampling procedure of reverse diffusion. Experiments conducted on the publicly available fastMRI dataset demonstrate that the proposed HFS-SDE method outperforms traditional parallel imaging methods, supervised deep learning, and existing diffusion models in terms of reconstruction accuracy and stability. The fast convergence properties are also confirmed through theoretical and experimental validation. Our code and weights are available at https://github.com/Aboriginer/HFS-SDE.

An Intuitionistic Fuzzy C-Means and Local Information-Based DCT Filtering for Fast Brain MRI Segmentation.

Structural and photometric anomalies in the brain magnetic resonance images (MRIs) affect the segmentation performance. Moreover, a sudden change in intensity between two boundaries of the brain tissues makes it prone to data uncertainty, resulting in the misclassification of the pixels lying near the cluster boundaries. The discrete cosine transform (DCT) domain-based filtering is an effective way to deal with structural and photometric anomalies, while the intuitionistic fuzzy C-means (IFCM) clustering can handle the uncertainty using the intuitionistic fuzzy set (IFS) theory. In this background, we propose two novel approaches, namely, the DCT-based intuitionistic fuzzy C-means (DCT-IFCM) and the DCT-based local information IFCM (DCT-LIFCM), which effectively deal with the Rician and Gaussian noises and also handle the data uncertainty problem to provide high segmentation accuracy. The DCT-IFCM approach performs the histogram-based segmentation, while the DCT-LIFCM uses the pixel-wise computation to include the spatial information. Although the DCT-LIFCM delivers slightly better performance than the DCT-IFCM, the latter is very fast in providing equally high segmentation accuracy. An exhaustive performance analysis is provided to demonstrate the superior performance of the proposed algorithms compared with the state-of-the-art algorithms, including those based on the DCT-based filtering approach and the IFS theory.

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.

Knowledge-driven deep learning for fast MR imaging: Undersampled MR image reconstruction from supervised to un-supervised learning.

Deep learning (DL) has emerged as a leading approach in accelerating MRI. It employs deep neural networks to extract knowledge from available datasets and then applies the trained networks to reconstruct accurate images from limited measurements. Unlike natural image restoration problems, MRI involves physics-based imaging processes, unique data properties, and diverse imaging tasks. This domain knowledge needs to be integrated with data-driven approaches. Our review will introduce the significant challenges faced by such knowledge-driven DL approaches in the context of fast MRI along with several notable solutions, which include learning neural networks and addressing different imaging application scenarios. The traits and trends of these techniques have also been given which have shifted from supervised learning to semi-supervised learning, and finally, to unsupervised learning methods. In addition, MR vendors' choices of DL reconstruction have been provided along with some discussions on open questions and future directions, which are critical for the reliable imaging systems.

A Faithful Deep Sensitivity Estimation for Accelerated Magnetic Resonance Imaging.

Magnetic resonance imaging (MRI) is an essential diagnostic tool that suffers from prolonged scan time. To alleviate this limitation, advanced fast MRI technology attracts extensive research interests. Recent deep learning has shown its great potential in improving image quality and reconstruction speed. Faithful coil sensitivity estimation is vital for MRI reconstruction. However, most deep learning methods still rely on pre-estimated sensitivity maps and ignore their inaccuracy, resulting in the significant quality degradation of reconstructed images. In this work, we propose a Joint Deep Sensitivity estimation and Image reconstruction network, called JDSI. During the image artifacts removal, it gradually provides more faithful sensitivity maps with high-frequency information, leading to improved image reconstructions. To understand the behavior of the network, the mutual promotion of sensitivity estimation and image reconstruction is revealed through the visualization of network intermediate results. Results on in vivo datasets and radiologist reader study demonstrate that, for both calibration-based and calibrationless reconstruction, the proposed JDSI achieves the state-of-the-art performance visually and quantitatively, especially when the acceleration factor is high. Additionally, JDSI owns nice robustness to patients and autocalibration signals.

Utility of fast MRIs in pediatric elbow injuries

BackgroundPediatric elbow trauma presents a diagnostic challenge for clinicians. Radiographs may be insufficient in assessing the radiocapitellar alignment and advanced imaging or invasive procedures such as an intraoperative arthrogram may be indicated. The purpose of this study is to describe the application and utility of fast magnetic resonance imaging (MRI) in the diagnosis and management of traumatic elbow injuries in pediatric patients. MethodsWe reviewed pediatric patients who underwent a fast MRI of the elbow between 2014-2022. A fast MRI was defined as an MRI using rapid sequences, accelerated conventional sequences, or fewer conventional sequences than a standard exam. Imaging for chronic or non-traumatic injuries was excluded. We identified patient demographics, MRI scan times, and clinical course. ResultsTwenty-three patients (8 females and 15 males) with fast elbow MRI scans were identified. The mean age was 5 years (range 2-12 years, SD 2 years). All patients had radiographs and four had CT scans prior to MRI. The average scanning time was 14 minutes (SD 6 minutes). Only one patient required anesthesia. Twenty of the 23 patients had a fracture identified on elbow radiographs and 8 were Monteggia fracture-dislocations. Nine of these patients demonstrated subluxation of the radiocapitellar joint requiring operative management in 8 patients, and one additional patient underwent surgery for displaced radial neck fracture. Three patients sustained an elbow dislocation without fracture identified on radiographs; of these, one had persistent radiocapitellar subluxation on MRI requiring surgical management. A total of 13 patients (56.5%) did not require operative management based on fast MRI findings. Outcome data was available for 22 patients with mean follow up was 23.6 months. One patient had residual pain and 8 had some range of motion limitation at final follow-up. All patients had reduced elbow joint on follow-up radiographs. ConclusionsFast MRIs can assist with the clinical evaluation of acute elbow injury in pediatric patients with equivocal radiographic findings and particularly in those with possible radiocapitellar subluxation/dislocation. This novel imaging technique has the potential to change clinical management, decrease the need for unnecessary procedures, and prevent complications of missed injuries.

PETS-Nets: Joint Pose Estimation and Tissue Segmentation of Fetal Brains Using Anatomy-Guided Networks.

Fetal Magnetic Resonance Imaging (MRI) is challenged by fetal movements and maternal breathing. Although fast MRI sequences allow artifact free acquisition of individual 2D slices, motion frequently occurs in the acquisition of spatially adjacent slices. Motion correction for each slice is thus critical for the reconstruction of 3D fetal brain MRI. In this paper, we propose a novel multi-task learning framework that adopts a coarse-to-fine strategy to jointly learn the pose estimation parameters for motion correction and tissue segmentation map of each slice in fetal MRI. Particularly, we design a regression-based segmentation loss as a deep supervision to learn anatomically more meaningful features for pose estimation and segmentation. In the coarse stage, a U-Net-like network learns the features shared for both tasks. In the refinement stage, to fully utilize the anatomical information, signed distance maps constructed from the coarse segmentation are introduced to guide the feature learning for both tasks. Finally, iterative incorporation of the signed distance maps further improves the performance of both regression and segmentation progressively. Experimental results of cross-validation across two different fetal datasets acquired with different scanners and imaging protocols demonstrate the effectiveness of the proposed method in reducing the pose estimation error and obtaining superior tissue segmentation results simultaneously, compared with state-of-the-art methods.

Emerging Trends in Magnetic Resonance Fingerprinting for Quantitative Biomedical Imaging Applications: A Review.

Magnetic resonance imaging (MRI) stands as a vital medical imaging technique, renowned for its ability to offer high-resolution images of the human body with remarkable soft-tissue contrast. This enables healthcare professionals to gain valuable insights into various aspects of the human body, including morphology, structural integrity, and physiological processes. Quantitative imaging provides compositional measurements of the human body, but, currently, either it takes a long scan time or is limited to low spatial resolutions. Undersampled k-space data acquisitions have significantly helped to reduce MRI scan time, while compressed sensing (CS) and deep learning (DL) reconstructions have mitigated the associated undersampling artifacts. Alternatively, magnetic resonance fingerprinting (MRF) provides an efficient and versatile framework to acquire and quantify multiple tissue properties simultaneously from a single fast MRI scan. The MRF framework involves four key aspects: (1) pulse sequence design; (2) rapid (undersampled) data acquisition; (3) encoding of tissue properties in MR signal evolutions or fingerprints; and (4) simultaneous recovery of multiple quantitative spatial maps. This paper provides an extensive literature review of the MRF framework, addressing the trends associated with these four key aspects. There are specific challenges in MRF for all ranges of magnetic field strengths and all body parts, which can present opportunities for further investigation. We aim to review the best practices in each key aspect of MRF, as well as for different applications, such as cardiac, brain, and musculoskeletal imaging, among others. A comprehensive review of these applications will enable us to assess future trends and their implications for the translation of MRF into these biomedical imaging applications.

IDDNet: a deep interactive dual-domain convolutional neural network with auxiliary modality for fast MRI reconstruction

Reconstructing a complete image accurately from an undersampled &lt;i&gt;k&lt;/i&gt;-space matrix is a viable approach for magnetic resonance imaging (MRI) acceleration. In recent years, numerous deep learning (DL)-based methods have been employed to improve MRI reconstruction. Among these methods, the cross-domain method has been proven to be effective. However, existing cross-domain reconstruction algorithms sequentially link the image domain and &lt;i&gt;k&lt;/i&gt;-space networks, disregarding the interplay between different domains, consequently leading to a deficiency in reconstruction accuracy. In this work, we propose a deep interactive dual-domain network (IDDNet) with an auxiliary modality for accelerating MRI reconstruction to effectively extract pertinent information from multiple MR domains and modalities. The IDDNet first extracts shallow features from low-resolution target modalities in the image domain to obtain visual representation information. In the following feature processing, a parallel interactive architecture with dual branches is designed to extract deep features from relevant information of dual domains simultaneously to avoid redundant priority priors in sequential links. Furthermore, the model uses additional information from the auxiliary modality to refine the structure and improve the reconstruction accuracy. Numerous experiments at different sampling masks and acceleration rates on the MICCAI BraTS 2019 brain and fastMRI knee datasets show that IDDNet achieves excellent accelerated MRI reconstruction performance.

Layer-specific fast strain-encoded cardiac magnetic resonance imaging aids in the identification and discrimination of acute myocardial injury: a prospective proof-of-concept study

Acute myocardial injury is a common diagnosis in the emergency department and differential diagnoses are numerous. Cardiac magnetic resonance (CMR) strain sequences, such as fast strain ENCoded (fSENC), are early predictors of myocardial function loss. This study assessed the potential diagnostic and prognostic benefits of a layer-specific approach. For this prospective study, patients in the emergency department fulfilling rule-in criteria for non-ST-elevation myocardial infarction (NSTEMI) received an ultra-fast fSENC CMR. Volunteers without cardiac diseases (controls) were recruited for comparison. Measurements were performed in a single heartbeat acquisition to measure global longitudinal strain (GLS) and segmental longitudinal strain and dysfunctional segments. The GLS was measured in two layers and a difference (GLSdifference =GLSepicardial -GLSendocardial) was calculated. The performance of those strain features was compared to standard care (physical examination, cardiac biomarkers, electrocardiogram). According to the final diagnosis after discharge, patients were divided into groups and followed up for 2years. A total of 114 participants, including 50 controls, were included. The 64 patients (51 male) were divided into a NSTEMI (25), myocarditis (16), and other myocardial injury group (23). GLS served as a potent predictor of myocardial injury (area under the curve (AUC) 91.8%). The GLSdifference provided an excellent diagnostic performance to identify a NSTEMI (AUC 83.2%), further improved by including dysfunctional segments (AUC 87.5%, p=0.01). An optimal test was achieved by adding fSENC to standard care (AUC 95.5%, sensitivity 96.0%, specificity 86.5%, p=0.03). No death occurred in 2years for patients with normal GLS and ≤5 dysfunctional segments, while three patients died that showed abnormal GLS or >5 dysfunctional segments. Layer-specific strain is a potential new marker with high diagnostic performance in the identification and differentiation of acute myocardial injuries.

Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution.

Super-resolving the magnetic resonance (MR) image of a target contrast under the guidance of the corresponding auxiliary contrast, which provides additional anatomical information, is a new and effective solution for fast MR imaging. However, current multi-contrast super-resolution (SR) methods tend to concatenate different contrasts directly, ignoring their relationships in different clues, e.g., in the high-and low-intensity regions. In this study, we propose a separable attention network (comprising high-intensity priority (HP) attention and low-intensity separation (LS) attention), named SANet. Our SANet could explore the areas of high-and low-intensity regions in the "forward" and "reverse" directions with the help of the auxiliary contrast while learning clearer anatomical structure and edge information for the SR of a target-contrast MR image. SANet provides three appealing benefits: First, it is the first model to explore a separable attention mechanism that uses the auxiliary contrast to predict the high-and low-intensity regions, diverting more attention to refining any uncertain details between these regions and correcting the fine areas in the reconstructed results. Second, a multistage integration module is proposed to learn the response of multi-contrast fusion at multiple stages, get the dependency between the fused representations, and boost their representation ability. Third, extensive experiments with various state-of-the-art multi-contrast SR methods on fastMRI and clinical in vivo datasets demonstrate the superiority of our model. The code is released at https://github.com/chunmeifeng/SANet.

DONet: Dual-Octave Network for Fast MR Image Reconstruction.

Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration has long been the subject of research. This is commonly achieved by obtaining multiple undersampled images, simultaneously, through parallel imaging. In this article, we propose the dual-octave network (DONet), which is capable of learning multiscale spatial-frequency features from both the real and imaginary components of MR data, for parallel fast MR image reconstruction. More specifically, our DONet consists of a series of dual-octave convolutions (Dual-OctConvs), which are connected in a dense manner for better reuse of features. In each Dual-OctConv, the input feature maps and convolutional kernels are first split into two components (i.e., real and imaginary) and then divided into four groups according to their spatial frequencies. Then, our Dual-OctConv conducts intragroup information updating and intergroup information exchange to aggregate the contextual information across different groups. Our framework provides three appealing benefits: 1) it encourages information interaction and fusion between the real and imaginary components at various spatial frequencies to achieve richer representational capacity; 2) the dense connections between the real and imaginary groups in each Dual-OctConv make the propagation of features more efficient by feature reuse; and 3) DONet enlarges the receptive field by learning multiple spatial-frequency features of both the real and imaginary components. Extensive experiments on two popular datasets (i.e., clinical knee and fastMRI), under different undersampling patterns and acceleration factors, demonstrate the superiority of our model in accelerated parallel MR image reconstruction.

Self-Supervised Federated Learning for Fast MR Imaging

Self-Supervised Federated Learning for Fast MR Imaging

The value of 3D high-resolution IR-prepared fast spoiled gradient-recalled MRI in the diagnosis of meningeal carcinomatosis involving the cranial nerves

PurposeThe purpose of this study was to investigate the clinical utility of three-dimension (3D) high-resolution inversion recovery (IR)-prepared fast spoiled gradient-recalled (SPGR) magnetic resonance imaging (MRI) in the diagnosis of cranial nerve meningeal carcinomatosis (MC).MethodsA total of 114 patients with MC from January 2015 to March 2020 were enrolled and their MRIs were analyzed retrospectively. All patients underwent MRIs before being administered a contrast agent. Both a 2D conventional MRI sequence and a 3D IR-prepared fast SPGR high-resolution T1-weighted (BRAVO) scan sequence were measured after contrast agent administration. The characteristics of MC and the involved cranial nerves were then examined.ResultsAmong the 114 MC patients, 81 (71.05%) had cranial nerve enhancement on contrast-enhanced 3D-BRAVO imaging, while only 41 (35.96%) had image enhancement on conventional MRI. The contrast-enhanced 3D-BRAVO displayed stronger image contrast enhancement of the cranial nerves than the conventional MRI (P < 0.001). Furthermore, detection rates for the facial and auditory nerves, trigeminal nerve, oculomotor nerve, sublingual nerve, optic nerve, glossopharyngeal/vagal/accessory nerve, and abductor nerve on contrast-enhanced 3D-BRAVO imaging were 58.77%, 47.37%, 9.65%, 8.77%, 5.26%, 3.51%, and 0.88%, respectively. We found a statistically significant difference between the affected facial and auditory nerves, as well as the trigeminal nerve, oculomotor nerve, sublingual nerve, and optic nerve.ConclusionIn MC, contrast-enhanced 3D-BRAVO imaging displayed the cranial nerves more effectively than 2D conventional enhanced MRI. The facial, auditory, and trigeminal nerves are the primary nerves involved in MC, and improved scanning of these nerves would aid in the early detection and treatment of MC.

Two-and-a-half order score-based model for solving 3D ill-posed inverse problems

Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are crucial technologies in the field of medical imaging. Score-based models demonstrated effectiveness in addressing different inverse problems encountered in the field of CT and MRI, such as sparse-view CT and fast MRI reconstruction. However, these models face challenges in achieving accurate three dimensional (3D) volumetric reconstruction. The existing score-based models predominantly concentrate on reconstructing two-dimensional (2D) data distributions, resulting in inconsistencies between adjacent slices in the reconstructed 3D volumetric images. To overcome this limitation, we propose a novel two-and-a-half order score-based model (TOSM). During the training phase, our TOSM learns data distributions in 2D space, simplifying the training process compared to working directly on 3D volumes. However, during the reconstruction phase, the TOSM utilizes complementary scores along three directions (sagittal, coronal, and transaxial) to achieve a more precise reconstruction. The development of TOSM is built on robust theoretical principles, ensuring its reliability and efficacy. Through extensive experimentation on large-scale sparse-view CT and fast MRI datasets, our method achieved state-of-the-art (SOTA) results in solving 3D ill-posed inverse problems, averaging a 1.56 dB peak signal-to-noise ratio (PSNR) improvement over existing sparse-view CT reconstruction methods across 29 views and 0.87 dB PSNR improvement over existing fast MRI reconstruction methods with × 2 acceleration. In summary, TOSM significantly addresses the issue of inconsistency in 3D ill-posed problems by modeling the distribution of 3D data rather than 2D distribution which has achieved remarkable results in both CT and MRI reconstruction tasks.