3D Magnetic Resonance Imaging Research Articles

3D reconstruction of the uterus and automatic segmentation of the uterine cavity on 3D magnetic resonance imaging: A preliminary study

PurposeTo determine the differences in 3D shape features between septate uterus (SU) and normal uterus and to train a network to automatically delineate uterine cavity on 3D magnetic resonance imaging (MRI). MethodsA total of 43 patients (22 cases of partial septate uterus and 21 cases of complete septate uterus) were included in the experimental group. Nine volunteers were recruited as a control group. The uterine cavity (UC), myometrium (UM), and cervical canal of the uterus were segmented manually using ITK-SNAP software. The three-dimensional shape features of the UC and UM were extracted by using PyRadiomics. The recurrent saliency transformation network (RSTN) method was used to segment the UC. ResultsThe values of four 3D shape features were significantly lower in the control group than in the partial septate group and the complete septate group, while the values of two features were significantly higher (p < 0.05). The UCs of the three groups were significantly different in terms of flatness and sphericity. The values of six features were significantly lower in the UMs of the control group than in those of the partial septate group and the complete septate group (p < 0.05). After the deep learning networks were trained, the Dice similarity coefficient (DSC) scores of the four folds for different thresholds were all over 80 %. The average volume ratio between predictions and manual segmentation was 101.2 %. ConclusionsBased on 3D reconstruction, 3D shape features can be used to comprehensively evaluate septate uterus and provide a reference for subsequent research. The UC can be automatically segmented on 3D MRI using the RSTN method.

Brain Age Prediction Using 2D Projections Based on Higher-Order Statistical Moments and Eigenslices from 3D Magnetic Resonance Imaging Volumes.

Brain age prediction from 3D MRI volumes using deep learning has recently become a popular research topic, as brain age has been shown to be an important biomarker. Training deep networks can be very computationally demanding for large datasets like the U.K. Biobank (currently 29,035 subjects). In our previous work, it was demonstrated that using a few 2D projections (mean and standard deviation along three axes) instead of each full 3D volume leads to much faster training at the cost of a reduction in prediction accuracy. Here, we investigated if another set of 2D projections, based on higher-order statistical central moments and eigenslices, leads to a higher accuracy. Our results show that higher-order moments do not lead to a higher accuracy, but that eigenslices provide a small improvement. We also show that an ensemble of such models provides further improvement.

DIR3D: Cascaded Dual-Domain Inter-Scale Mutual Reinforcement 3D Network for highly accelerated 3D MR image reconstruction

Deep Learning has been successfully applied to reconstruct Magnetic Resonance (MR) images from undersampled k-space data to achieve the acceleration of MRI. However, most existing works focused on 2D MRI scans and perform reconstruction in a slice-by-slice manner due to the tremendous computation and memory cost of 3D MRI reconstruction, resulting in a blank in the research of 3D MRI acceleration. Providing more accurate and diagnostic information, 3D MRI requires excessively long scan time. To accelerate 3D MRI, in this work, we design a lightweight and powerful cascaded 3D network DIR3D utilizing a previously proposed computation-friendly data processing strategy. Specifically, we propose an efficient block called Dual-Domain Inter-Scale Mutual Reinforcement Block (DIRB) to fuse multi-scale features locally and globally with neglectable computation and memory costs, which enhances the representative ability of the network. To allow more flexibility, we further redesign the commonly used Data Consistency (DC) layer by introducing a learnable adaptor which enables the network to perform point-wise adaptive merge of the reconstructed and sampled k-space data while ensuring data consistency. We conduct comprehensive experiments on the Stanford MRIData and evaluate our DIR3D from multiple perspectives. When achieving the same acceleration factors, our proposed DIR3D consistently outperforms other state-of-the-art 2D methods at multiple subsampling masks, especially for highly undersampled data, which provides strong evidence for the superiority of our DIR3D for 3D MRI acceleration. Additionally, at the inference stage, our DIR3D can achieve a much higher reconstruction efficiency.

Improvement of 2D cine image quality using 3D priors and cycle generative adversarial network for low field MRI-guided radiation therapy.

Cine magnetic resonance (MR) images have been used for real-time MR guided radiation therapy (MRgRT). However, the onboard MR systems with low-field strength face the problem of limited image quality. To improve the quality of cine MR images in MRgRT using prior image information provided by the patient planning and positioning MR images. This study employed MR images from 18 pancreatic cancer patients who received MR-guided stereotactic body radiation therapy. Planning 3D MR images were acquired during the patient simulation, and positioning 3D MR images and 2D sagittal cine MR images were acquired before and during the beam delivery, respectively. A deep learning-based framework consisting of two cycle generative adversarial networks (CycleGAN), Denoising CycleGAN and Enhancement CycleGAN, was developed to establish the mapping between the 3D and 2D MR images. The Denoising CycleGAN was trained to first denoise the cine images using the time domain cine image series, and the Enhancement CycleGAN was trained to enhance the spatial resolution and contrast by taking advantage of the prior image information from the planning and positioning images. The denoising performance was assessed by signal-to-noise ratio (SNR), structural similarity index measure, peak SNR, blind/reference-less image spatial quality evaluator (BRISQUE), natural image quality evaluator, and perception-based image quality evaluator scores. The quality enhancement performance was assessed by the BRISQUE and physician visual scores. In addition, the target contouring was evaluated on the original and processed images. Significant differences were found for all evaluation metrics after Denoising CycleGAN processing. The BRISQUE and visual scores were also significantly improved after sequential Denoising and Enhancement CycleGAN processing. In target contouring evaluation, Dice similarity coefficient, centroid distance, Hausdorff distance, and average surface distance values were significantly improved on the enhanced images. The whole processing time was within 20ms for a typical input image size of 512 × 512. Taking advantage of the prior high-quality positioning and planning MR images, the deep learning-based framework enhanced the cine MR image quality significantly, leading to improved accuracy in automatic target contouring. With the merits of both high computational efficiency and considerable image quality enhancement, the proposed method may hold important clinical implication for real-time MRgRT.

Elmukashfi’s Protocol for Hippocampal Volumetry; 2022

There is a relation between many neuropsychiatric disorders and reduction in hippocampal volume. So, a protocol for researches in this area is highly needed. Study aimed to design and validate a protocol for hippocampal volumetry to facilitate manual segmentation of hippocampus region. It was a comparative study, carried at Diagnostic Imaging Clinic at Elmoalem Hospital; where 65 Sudanese individuals were surveyed in period (December 2021 –April 2022). Data was collected through master sheet for sociodemographic information, 3D magnetic resonance imaging for measuring hippocampus volume, and imaging acquisition. Software for measurements 3D slicer version (4.11) was used, where hippocampus is mapped by delineating its boundaries. Protocol was composed of mapping hippocampus. Mapping hippocampus: identify sagittal view, lateral fissure, temporal horn of lateral ventricle, hippocampus region, temporal and occipital horn of lateral ventricle, choroid plexus of lateral ventricle. Among these slides hippocampus has been delineated. Statistical Computing: Data was analyzed using SPSS version 23. Reliability test was performed by obtaining Cronbach’s alpha. Protocol considered reliable if value of Cronbach’s alpha is close to (+1). P-value ≤ 0.05 was considered statistically significant. Validation of Protocol: Calculation of hippocampus volume is valid as total volume correlates strongly with both right and left measurements (correlation coefficient 0.76 and 0.87 respectively and p-value &lt;0.001). Reliability test was 0.85; which was close to (+1). Conclusion and recommendation: This protocol represents a valid, reliable, and applicable method for measuring hippocampal volume. It could be a step to develop an international standard protocol for hippocampal volumetry.

Volumetric MRI with sparse sampling for MR-guided 3D motion tracking via sparse prior-augmented implicit neural representation learning.

Volumetric reconstruction of magnetic resonance imaging (MRI) from sparse samples is desirable for 3D motion tracking and promises to improve magnetic resonance (MR)-guided radiation treatment precision. Data-driven sparse MRI reconstruction, however, requires large-scale training datasets for prior learning, which is time-consuming and challenging to acquire in clinical settings. To investigate volumetric reconstruction of MRI from sparse samples of two orthogonal slices aided by sparse priors of two static 3D MRI through implicit neural representation (NeRP) learning, in support of 3D motion tracking during MR-guided radiotherapy. A multi-layer perceptron network was trained to parameterize the NeRP model of a patient-specific MRI dataset, where the network takes 4D data coordinates of voxel locations and motion states as inputs and outputs corresponding voxel intensities. By first training the network to learn the NeRP of two static 3D MRI with different breathing motion states, prior information of patient breathing motion was embedded into network weights through optimization. The prior information was then augmented from two motion states to 31 motion states by querying the optimized network at interpolated and extrapolated motion state coordinates. Starting from the prior-augmented NeRP model as an initialization point, we further trained the network to fit sparse samples of two orthogonal MRI slices and the final volumetric reconstruction was obtained by querying the trained network at 3D spatial locations. We evaluated the proposed method using 5-min volumetric MRI time series with 340ms temporal resolution for seven abdominal patients with hepatocellular carcinoma, acquired using golden-angle radial MRI sequence and reconstructed through retrospective sorting. Two volumetric MRI with inhale and exhale states respectively were selected from the first 30s of the time series for prior embedding and augmentation. The remaining 4.5-min time series was used for volumetric reconstruction evaluation, where we retrospectively subsampled each MRI to two orthogonal slices and compared model-reconstructed images to ground truth images in terms of image quality and the capability of supporting 3D target motion tracking. Across the seven patients evaluated, the peak signal-to-noise-ratio between model-reconstructed and ground truth MR images was 38.02±2.60dB and the structure similarity index measure was 0.98±0.01. Throughout the 4.5-min time period, gross tumor volume (GTV) motion estimated by deforming a reference state MRI to model-reconstructed and ground truth MRI showed good consistency. The 95-percentile Hausdorff distance between GTV contours was 2.41±0.77mm, which is less than the voxel dimension. The mean GTV centroid position difference between ground truth and model estimation was less than 1mm in all three orthogonal directions. A prior-augmented NeRP model has been developed to reconstruct volumetric MRI from sparse samples of orthogonal cine slices. Only one exhale and one inhale 3D MRI were needed to train the model to learn prior information of patient breathing motion for sparse image reconstruction. The proposed model has the potential of supporting 3D motion tracking during MR-guided radiotherapy for improved treatment precision and promises a major simplification of the workflow by eliminating the need for large-scale training datasets.

Automatic Quantification of Normal Brain Gyrification Patterns and Changes in Fetuses with Polymicrogyria and Lissencephaly Based on MRI.

The current imaging assessment of fetal brain gyrification is performed qualitatively and subjectively using sonography and MR imaging. A few previous studies have suggested methods for quantification of fetal gyrification based on 3D reconstructed MR imaging, which requires unique data and is time-consuming. In this study, we aimed to develop an automatic pipeline for gyrification assessment based on routinely acquired fetal 2D MR imaging data, to quantify normal changes with gestation, and to measure differences in fetuses with lissencephaly and polymicrogyria compared with controls. We included coronal T2-weighted MR imaging data of 162 fetuses retrospectively collected from 2 clinical sites: 134 controls, 12 with lissencephaly, 13 with polymicrogyria, and 3 with suspected lissencephaly based on sonography, yet with normal MR imaging diagnoses. Following brain segmentation, 5 gyrification parameters were calculated separately for each hemisphere on the basis of the area and ratio between the contours of the cerebrum and its convex hull. Seven machine learning classifiers were evaluated to differentiate control fetuses and fetuses with lissencephaly or polymicrogyria. In control fetuses, all parameters changed significantly with gestational age (P < .05). Compared with controls, fetuses with lissencephaly showed significant reductions in all gyrification parameters (P ≤ .02). Similarly, significant reductions were detected for fetuses with polymicrogyria in several parameters (P ≤ .001). The 3 suspected fetuses showed normal gyrification values, supporting the MR imaging diagnosis. An XGBoost-linear algorithm achieved the best results for classification between fetuses with lissencephaly and control fetuses (n = 32), with an area under the curve of 0.90 and a recall of 0.83. Similarly, a random forest classifier showed the best performance for classification of fetuses with polymicrogyria and control fetuses (n = 33), with an area under the curve of 0.84 and a recall of 0.62. This study presents a pipeline for automatic quantification of fetal brain gyrification and provides normal developmental curves from a large cohort. Our method significantly differentiated fetuses with lissencephaly and polymicrogyria, demonstrating lower gyrification values. The method can aid radiologic assessment, highlight fetuses at risk, and may improve early identification of fetuses with cortical malformations.

Robust U-Net-Based Approach for Accurate Brain Tumor Segmentation Using Multimodal MRI Data

Detecting and quantifying the extent of brain tumors poses a formidable challenge in medical centers. Magnetic Resonance Imaging (MRI) has developed as a non-invasive brain cancers' primary diagnostic tool, offering the crucial advantage of avoiding ionizing radiation. Brain tumor manually segmented boundaries within 3D MRI volumes is an exceedingly time-intensive task, heavily reliant on operator expertise. Among brain tumors, gliomas stand out as the prevalent and highly malignant, significantly impacting patients' life expectancy, particularly at their highest grade. Recognizing the pressing need for a reliable, completely automatic segmentation technique to efficiently assess tumor extent, this study introduces a robust approach. A completely automated brain tumor segmentation method is proposed, leveraging U-Net-based deep convolutional networks. This approach underwent rigorous evaluation on the Multimodal Brain Tumor Image Segmentation BraTS-19 dataset a widely recognized medical image analysis dataset featuring multimodal MRI scans of brain tumors, including glioblastoma, anaplastic astrocytoma, and lower-grade glioma, coupled with corresponding manual tumor segmentations. This dataset serves as a pivotal resource for advancing automatic brain tumor segmentation techniques and assessing their performance using metrics like the Dice score, which achieved 92% for entire tumor. Cross-validation results affirm the efficiency and promise of our method in achieving accurate segmentation.

3D isotropic MRI of ankle: review of literature with comparison to 2D MRI.

The ankle joint has complex anatomy with different tissue structures and is commonly involved in traumatic injuries. Magnetic resonance imaging (MRI) is the primary imaging modality used to assess the soft tissue structures around the ankle joint including the ligaments, tendons, and articular cartilage. Two-dimensional (2D) fast spin echo/turbo spin echo (FSE/TSE) sequences are routinely used for ankle joint imaging. While the 2D sequences provide a good signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) with high spatial resolution, there are some limitations to their use owing to the thick slices, interslice gaps leading to partial volume effects, limited fluid contrast, and the need to acquire separate images in different orthogonal planes. The 3D MR imaging can overcome these limitations and recent advances have led to technical improvements that enable its widespread clinical use in acceptable time periods. The volume imaging renders the advantage of reconstructing into thin continuous slices with isotropic voxels enabling multiplanar reconstructions that helps in visualizing complex anatomy of the structure of interest throughout their course with improved sharpness, definition of anatomic variants, and fluid conspicuity of lesions and injuries. Recent advances have also reduced the acquisition time of the 3D datasets making it more efficient than 2D sequences. This article reviews the recent technical developments in the domain 3D MRI, compares imaging with 3D versus 2D sequences, and demonstrates the use-case scenarios with interesting cases, and benefits of 3D MRI in evaluating various ankle joint components and their lesions.

Joint learning framework of cross-modal synthesis and diagnosis for Alzheimer’s disease by mining underlying shared modality information

Alzheimer’s disease (AD) is one of the most common neurodegenerative disorders presenting irreversible progression of cognitive impairment. How to identify AD as early as possible is critical for intervention with potential preventive measures. Among various neuroimaging modalities used to diagnose AD, functional positron emission tomography (PET) has higher sensitivity than structural magnetic resonance imaging (MRI), but it is also costlier and often not available in many hospitals. How to leverage massive unpaired unlabeled PET to improve the diagnosis performance of AD from MRI becomes rather important. To address this challenge, this paper proposes a novel joint learning framework of unsupervised cross-modal synthesis and AD diagnosis by mining underlying shared modality information, improving the AD diagnosis from MRI while synthesizing more discriminative PET images. We mine underlying shared modality information in two aspects: diversifying modality information through the cross-modal synthesis network and locating critical diagnosis-related patterns through the AD diagnosis network. First, to diversify the modality information, we propose a novel unsupervised cross-modal synthesis network, which implements the inter-conversion between 3D PET and MRI in a single model modulated by the AdaIN module. Second, to locate shared critical diagnosis-related patterns, we propose an interpretable diagnosis network based on fully 2D convolutions, which takes either 3D synthesized PET or original MRI as input. Extensive experimental results on the ADNI dataset show that our framework can synthesize more realistic images, outperform the state-of-the-art AD diagnosis methods, and have better generalization on external AIBL and NACC datasets.

An attention 3DUNET and visual geometry group-19 based deep neural network for brain tumor segmentation and classification from MRI

There has been an abrupt increase in brain tumor (BT) related medical cases during the past ten years. The tenth most typical type of tumor affecting millions of people is the BT. The cure rate can, however, rise if it is found early. When evaluating BT diagnosis and treatment options, MRI is a crucial tool. However, segmenting the tumors from magnetic resonance (MR) images is complex. The advancement of deep learning (DL) has led to the development of numerous automatic segmentation and classification approaches. However, most need improvement since they are limited to 2D images. So, this article proposes a novel and optimal DL system for segmenting and classifying the BTs from 3D brain MR images. Preprocessing, segmentation, feature extraction, feature selection, and tumor classification are the main phases of the proposed work. Preprocessing, such as noise removal, is performed on the collected brain MR images using bilateral filtering. The tumor segmentation uses spatial and channel attention-based three-dimensional u-shaped network (SC3DUNet) to segment the tumor lesions from the preprocessed data. After that, the feature extraction is done based on dilated convolution-based visual geometry group-19 (DCVGG-19), making the classification task more manageable. The optimal features are selected from the extracted feature sets using diagonal linear uniform and tangent flight included butterfly optimization algorithm. Finally, the proposed system applies an optimal hyperparameters-based deep neural network to classify the tumor classes. The experiments conducted on the BraTS2020 dataset show that the suggested method can segment tumors and categorize them more accurately than the existing state-of-the-art mechanisms. Communicated by Ramaswamy H. Sarma

Using 3D MRI Bone Shape to Predict Pre-Osteoarthritis of the Knee 2 Years After Anterior Cruciate Ligament Reconstruction

Background: Anterior cruciate ligament (ACL) injury increases risks for osteoarthritis (OA), a poorly modifiable and disabling condition. Joint changes of potentially reversible pre-OA have been described just 2 years after ACL reconstruction (ACLR) when early bone shape changes have also been reported. Purpose: This study evaluates relationships between interlimb differences in tibiofemoral bone shape derived from statistical shape modeling (SSM) of magnetic resonance imaging (MRI) and participant factors on patient-reported outcomes 2 years after unilateral ACLR. Study Design: Cross-sectional study; Level of evidence, 3. Methods: SSM-derived tibiofemoral bone shape and subchondral bone area were assessed from bilateral knee MRI scans of 72 participants with unilateral ACLR (mean age, 34 ± 11 years; 32 women) and compared with a reference cohort of 398 older individuals without OA (mean age, 50 ± 3 years; 213 women). Multivariable logistic regression models examined relationships between participant and surgical factors with interlimb differences in bone shapes or subchondral bone areas. Relationships between patient-reported outcomes and the interlimb differences in bone shape and subchondral area were examined using similar models. Results: Bone shape scores and subchondral bone areas were greater (more OA-like) in ACLR knees than uninjured contralateral knees in every bone metric tested (P≤ .001). Interlimb differences in femur shape scores of participants with ACLR were 65% greater (P < .001) than those of the significantly older reference cohort. Taller height, medial meniscal tears, and decreasing age were associated with larger interlimb differences in shape scores and subchondral areas (P < .05). Bone–patellar tendon–bone (BPTB) autograft recipients demonstrated greater interlimb subchondral area differences compared with allograft recipients (P < .05). Interlimb differences for hamstring autograft recipients did not differ from those with BPTB or allograft. Greater interlimb differences in medial femur subchondral areas were associated with worse patient-reported Knee injury and Osteoarthritis Outcome Score Symptoms (R = 0.27; P = .040). Conclusion: Even in the absence of radiographic OA, just 2 years after unilateral ACLR patients showed greater bone shape scores and subchondral areas consistent with pre-OA in their ACLR knees. Furthermore, greater medial femur bone areas were weakly associated with worse symptoms. Patients who are younger, are taller, have meniscal tears, or have BPTB grafts may be at increased risk for bony asymmetries 2 years after ACLR.

Retracted: Using Convolutional Neural Networks for Segmentation of Multiple Sclerosis Lesions in 3D Magnetic Resonance Imaging

Retracted: Using Convolutional Neural Networks for Segmentation of Multiple Sclerosis Lesions in 3D Magnetic Resonance Imaging

Reconstruction of shoulder MRI using deep learning and compressed sensing: a validation study on healthy volunteers

BackgroundTo investigate the potential of combining compressed sensing (CS) and deep learning (DL) for accelerated two-dimensional (2D) and three-dimensional (3D) magnetic resonance imaging (MRI) of the shoulder.MethodsTwenty healthy volunteers were examined using at 3-T scanner with a fat-saturated, coronal, 2D proton density-weighted sequence with four acceleration levels (2.3, 4, 6, and 8) and a 3D sequence with three acceleration levels (8, 10, and 13), all accelerated with CS and reconstructed using the conventional algorithm and a new DL-based algorithm (CS-AI). Subjective image quality was evaluated by two blinded readers using 6 criteria on a 5-point Likert scale (overall impression, artifacts, and delineation of the subscapularis tendon, bone, acromioclavicular joint, and glenoid labrum). Objective image quality was measured by calculating signal-to-noise-ratio, contrast-to-noise-ratio, and a structural similarity index measure. All reconstructions were compared to the clinical standard (CS 2D acceleration factor 2.3; CS 3D acceleration factor 8). Additionally, subjective and objective image quality were compared between CS and CS-AI with the same acceleration levels.ResultsBoth 2D and 3D sequences reconstructed with CS-AI achieved on average significantly better subjective and objective image quality compared to sequences reconstructed with CS with the same acceleration factor (p ≤ 0.011). Comparing CS-AI to the reference sequences showed that 4-fold acceleration for 2D sequences and 13-fold acceleration for 3D sequences without significant loss of quality (p ≥ 0.058).ConclusionsFor MRI of the shoulder at 3 T, a DL-based algorithm allowed additional acceleration of acquisition times compared to the conventional approach.Relevance statementThe combination of deep-learning and compressed sensing hold the potential for further scan time reduction in 2D and 3D imaging of the shoulder while providing overall better objective and subjective image quality compared to the conventional approach.Trial registrationDRKS00024156.Key points• Combination of compressed sensing and deep learning improved image quality and allows for significant acceleration of shoulder MRI.• Deep learning-based algorithm achieved better subjective and objective image quality than conventional compressed sensing.• For shoulder MRI at 3 T, 40% faster image acquisition for 2D sequences and 38% faster image acquisition for 3D sequences may be possible.Graphical

Time-series visual explainability for Alzheimer’s disease progression detection for smart healthcare

Artificial intelligence (AI)-based diagnostic systems provide less error-prone and safer support to clinicians, enhancing the medical decision-making process. This study presents a smart and reliable healthcare framework for detecting Alzheimer's disease (AD) progression. Early detection of AD before the onset of clinical symptoms is the most crucial step in starting timely treatment. To predict the conversion of cognitively normal patients to those with AD, three-dimensional (3D) magnetic resonance imaging (MRI) whole-brain neuroimaging methods have been extensively studied. However, depending on the 3D volume, this method is computationally expensive. To solve this problem, we used an approximate rank pooling method originally designed for video action recognition with a 3D MRI volume to obtain a compressed representation of multiple two-dimensional (2D) MRI slices. This study proposes a hybrid multimodal CNN-Bi-LSTM deep model for AD progression detection, in which the resulting dynamic 2D images are fused with cognitive features. Moreover, a novel explainable AI approach is proposed to provide visual explanations using the resulting longitudinal 2D dynamic images. Temporal explanations were provided by visualizing the affected brain regions captured using longitudinal 2D MRIs. By utilizing a sample of 1,692 subjects with multimodal data from the Alzheimer’s Disease Neuroimaging Initiative dataset, our method was assessed using a 10-fold cross-validation process. The model achieved an area under the receiver operating characteristics curve (AUC) of 94% using longitudinal 2D three-time-step dynamic image data. The fusion of 2D dynamic images with cognitive features enhanced the performance by 2% in terms of the AUC. Patients who gradually develop AD, show changes in various brain regions. For such patients, our system highlights the critical role of the hippocampus, medial amygdala, caudal hippocampus, and lateral amygdala at the initial time steps. In the late stages of AD, the system detects abnormalities in extra brain regions such as the medial temporal gyrus, superior temporal gyrus, fusiform gyrus, and caudal hippocampus; indicating that patients have completely progressed to AD.

Hyperperfusion of bilateral amygdala in patients with chronic migraine: an arterial spin-labeled magnetic resonance imaging study

BackgroundAmygdala, an essential element of the limbic system, has served as an important structure in pain modulation. There is still a lack of clarity about altered cerebral perfusion of amygdala in migraine. This study aimed to investigate the perfusion variances of bilateral amygdala in episodic migraine (EM) and chronic migraine (CM) using multi-delay pseudo-continuous arterial spin-labeled magnetic resonance imaging (pCASL-MRI).MethodsTwenty-six patients with EM, 55 patients with CM (33 CM with medication overuse headache (MOH)), and 26 age- and sex-matched healthy controls (HCs) were included. All participants underwent 3D multi-delay pCASL MR imaging to obtain cerebral perfusion data, including arrival-time-corrected cerebral blood flow (CBF) and arterial cerebral blood volume (aCBV). The CBF and aCBV values in the bilateral amygdala were compared among the three groups. Correlation analyses between cerebral perfusion parameters and clinical variables were performed.ResultsCompared with HC participants, patients with CM were found to have increased CBF and aCBV values in the left amygdala, as well as increased CBF values in the right amygdala (all P < 0.05). There were no significant differences of CBF and aCBV values in the bilateral amygdala between the HC and EM groups, the EM and CM groups, as well as the CM without and with MOH groups (all P > 0.05). In patients with CM, the increased perfusion parameters of bilateral amygdala were positively correlated with MIDAS score after adjustments for age, sex, and body mass index (BMI).ConclusionHyperperfusion of bilateral amygdala might provide potential hemodynamics evidence in the neurolimbic pain network of CM.

Ultra-fast multi-parametric 4D-MRI image reconstruction for real-time applications using a downsampling-invariant deformable registration (D2R) model

Background and purposeMotion estimation from severely downsampled 4D-MRI is essential for real-time imaging and tumor tracking. This simulation study developed a novel deep learning model for simultaneous MR image reconstruction and motion estimation, named the Downsampling-Invariant Deformable Registration (D2R) model. Materials and methodsForty-three patients undergoing radiotherapy for liver tumors were recruited for model training and internal validation. Five prospective patients from another center were recruited for external validation. Patients received 4D-MRI scans and 3D MRI scans. The 4D-MRI was retrospectively down-sampled to simulate real-time acquisition. Motion estimation was performed using the proposed D2R model. The accuracy and robustness of the proposed D2R model and baseline methods, including Demons, Elastix, the parametric total variation (pTV) algorithm, and VoxelMorph, were compared. High-quality (HQ) 4D-MR images were also constructed using the D2R model for real-time imaging feasibility verification. The image quality and motion accuracy of the constructed HQ 4D-MRI were evaluated. ResultsThe D2R model showed significantly superior and robust registration performance than all the baseline methods at downsampling factors up to 500. HQ T1-weighted and T2-weighted 4D-MR images were also successfully constructed with significantly improved image quality, sub-voxel level motion error, and real-time efficiency. External validation demonstrated the robustness and generalizability of the technique. ConclusionIn this study, we developed a novel D2R model for deformation estimation of downsampled 4D-MR images. HQ 4D-MR images were successfully constructed using the D2R model. This model may expand the clinical implementation of 4D-MRI for real-time motion management during liver cancer treatment.

Geometric distortions in clinical MRI sequences for radiotherapy: insights gained from a multicenter investigation

Background As magnetic resonance imaging (MRI) becomes increasingly integrated into radiotherapy (RT) for enhanced treatment planning and adaptation, the inherent geometric distortion in acquired MR images pose a potential challenge to treatment accuracy. This study aimed to evaluate the geometric distortion levels in the clinical MRI protocols used across Danish RT centers and discuss influence of specific sequence parameters. Based on the variety in geometric performance across centers, we assess if harmonization of MRI sequences is a relevant measure. Materials and methods Nine centers participated with 12 MRI scanners and MRI-Linacs (MRL). Using a travelling phantom approach, a reference MRI sequence was used to assess variation in baseline distortion level between scanners. The phantom was also scanned with local clinical MRI sequences for brain, head/neck (H/N), abdomen, and pelvis. The influence of echo time, receiver bandwidth, image weighting, and 2D/3D acquisition was investigated. Results We found a large variation in geometric accuracy across 93 clinical sequences examined, exceeding the baseline variation found between MRI scanners (σ = 0.22 mm), except for abdominal sequences where the variation was lower. Brain and abdominal sequences showed lowest distortion levels ([0.22, 2.26] mm), and a large variation in performance was found for H/N and pelvic sequences ([0.19, 4.07] mm). Post hoc analyses revealed that distortion levels decreased with increasing bandwidth and a less clear increase in distortion levels with increasing echo time. 3D MRI sequences had lower distortion levels than 2D (median of 1.10 and 2.10 mm, respectively), and in DWI sequences, the echo-planar imaging read-out resulted in highest distortion levels. Conclusion There is a large variation in the geometric distortion levels of clinical MRI sequences across Danish RT centers, and between anatomical sites. The large variation observed makes harmonization of MRI sequences across institutions and adoption of practices from well-performing anatomical sites, a relevant measure within RT.

Morphological analysis of three-dimensional MR images of patellofemoral joints in asymptomatic subjects

The existing methods for analyzing patellofemoral (PF) osteoarthritis (OA) are limited. Our purpose was to clarify the frequency, localization, and morphological progression of PFOA by observing three-dimensional (3D) magnetic resonance (MR) images from a cohort population. The subjects were 561 patients aged 30–79 years from the Kanagawa Knee Study who had not visited a hospital for more than three consecutive months for knee symptoms. MR images of the PF joints, separated into the medial and lateral types, were presented in order of the highest to lowest patella cartilage area ratios. Cartilage defects in the patella were detected in 37 subjects (6.6%). Medial lesions (4.6%) were significantly more frequent than lateral lesions (2.0%) (p < 0.01). For both medial and lateral lesions, the patellar cartilage defects were divided into confined and unconfined types. The 3D MR images of the PF joint showed that the patellar cartilage defect occurred along each ridge of the femoral trochlea. The 3D MR images revealed a 6.6% prevalence of patellar cartilage defects, higher in the medial than lateral regions. The 3D MR images can easily determine PF morphology and cartilage defect location, making them useful in understanding the pathophysiology and etiology of PFOA.

Effects of MRI scanner manufacturers in classification tasks with deep learning models

Deep learning has become a leading subset of machine learning and has been successfully employed in diverse areas, ranging from natural language processing to medical image analysis. In medical imaging, researchers have progressively turned towards multi-center neuroimaging studies to address complex questions in neuroscience, leveraging larger sample sizes and aiming to enhance the accuracy of deep learning models. However, variations in image pixel/voxel characteristics can arise between centers due to factors including differences in magnetic resonance imaging scanners. Such variations create challenges, particularly inconsistent performance in machine learning-based approaches, often referred to as domain shift, where the trained models fail to achieve satisfactory or improved results when confronted with dissimilar test data. This study analyzes the performance of multiple disease classification tasks using multi-center MRI data obtained from three widely used scanner manufacturers (GE, Philips, and Siemens) across several deep learning-based networks. Furthermore, we investigate the efficacy of mitigating scanner vendor effects using ComBat-based harmonization techniques when applied to multi-center datasets of 3D structural MR images. Our experimental results reveal a substantial decline in classification performance when models trained on one type of scanner manufacturer are tested with data from different manufacturers. Moreover, despite applying ComBat-based harmonization, the harmonized images do not demonstrate any noticeable performance enhancement for disease classification tasks.