Deep learning-based reconstruction enhances image quality and improves diagnosis in magnetic resonance imaging of the shoulder joint
Ontology highlight
ABSTRACT:
SUBMITTER: Liu Z
PROVIDER: S-EPMC11007508 | biostudies-literature | 2024 Mar
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:This paper describes an adaptive approach to regularizing model-based reconstructions in magnetic resonance imaging to account for local structure or image content. In conjunction with common models like wavelet and total variation sparsity, this content-aware regularization avoids oversmoothing or compromising image features while suppressing noise and incoherent aliasing from accelerated imaging. To evaluate this regularization approach, the experiments reconstruct images from single- and multi-channel, Cartesian and non-Cartesian, brain and cardiac data. These reconstructions combine common analysis-form regularizers and autocalibrating parallel imaging (when applicable). In most cases, the results show widespread improvement in structural similarity and peak-signal-to-error ratio relative to the fully sampled images. These results suggest that this content-aware regularization can preserve local image structures such as edges while providing denoising power superior to sparsity-promoting or sparsity-reweighted regularization.
| S-EPMC6102097 | biostudies-literature
Project description:Modern sequences for Magnetic Resonance Imaging (MRI) trade off scan time with computational challenges, resulting in ill-posed inverse problems and the requirement to account for more elaborated signal models. Various deep learning techniques have shown potential for image reconstruction from reduced data, outperforming compressed sensing, dictionary learning and other advanced techniques based on regularization, by characterization of the image manifold. In this work we suggest a framework for reducing a "neural" network to the bare minimum required by the MR physics, reducing the network depth and removing all non-linearities. The networks performed well both on benchmark simulated data and on arterial spin labeling perfusion imaging, showing clear images while preserving sensitivity to the minute signal changes. The results indicate that the deep learning framework plays a major role in MR image reconstruction, and suggest a concrete approach for probing into the contribution of additional elements.
| S-EPMC6925115 | biostudies-literature
Project description:ObjectivesTo compare the image quality and diagnostic performance of conventional motion-corrected periodically rotated overlapping parallel line with enhanced reconstruction (PROPELLER) MRI sequences with post-processed PROPELLER MRI sequences using deep learning-based (DL) reconstructions.MethodsIn this prospective study of 30 patients, conventional (19 min 18 s) and accelerated MRI sequences (7 min 16 s) using the PROPELLER technique were acquired. Accelerated sequences were post-processed using DL. The image quality and diagnostic confidence were qualitatively assessed by 2 readers using a 5-point Likert scale. Analysis of the pathological findings of cartilage, rotator cuff tendons and muscles, glenoid labrum and subacromial bursa was performed. Inter-reader agreement was calculated using Cohen's kappa statistic. Quantitative evaluation of image quality was measured using the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR).ResultsMean image quality and diagnostic confidence in evaluation of all shoulder structures were higher in DL sequences (p value = 0.01). Inter-reader agreement ranged between kappa values of 0.155 (assessment of the bursa) and 0.947 (assessment of the rotator cuff muscles). In 17 cases, thickening of the subacromial bursa of more than 2 mm was only visible in DL sequences. The pathologies of the other structures could be properly evaluated by conventional and DL sequences. Mean SNR (p value = 0.01) and CNR (p value = 0.02) were significantly higher for DL sequences.ConclusionsThe accelerated PROPELLER sequences with DL post-processing showed superior image quality and higher diagnostic confidence compared to the conventional PROPELLER sequences. Subacromial bursa can be thoroughly assessed in DL sequences, while the other structures of the shoulder joint can be assessed in conventional and DL sequences with a good agreement between sequences.Key points• MRI of the shoulder requires long scan times and can be hampered by motion artifacts. • Deep learning-based convolutional neural networks are used to reduce image noise and scan time while maintaining optimal image quality. The radial k-space acquisition technique (PROPELLER) can reduce the scan time and has potential to reduce motion artifacts. • DL sequences show a higher diagnostic confidence than conventional sequences and therefore are preferred for assessment of the subacromial bursa, while conventional and DL sequences show comparable performance in the evaluation of the shoulder joint.
| S-EPMC9935676 | biostudies-literature
Project description:Fast and accurate reconstruction of magnetic resonance (MR) images from under-sampled data is important in many clinical applications. In recent years, deep learning-based methods have been shown to produce superior performance on MR image reconstruction. However, these methods require large amounts of data which is difficult to collect and share due to the high cost of acquisition and medical data privacy regulations. In order to overcome this challenge, we propose a federated learning (FL) based solution in which we take advantage of the MR data available at different institutions while preserving patients' privacy. However, the generalizability of models trained with the FL setting can still be suboptimal due to domain shift, which results from the data collected at multiple institutions with different sensors, disease types, and acquisition protocols, etc. With the motivation of circumventing this challenge, we propose a cross-site modeling for MR image reconstruction in which the learned intermediate latent features among different source sites are aligned with the distribution of the latent features at the target site. Extensive experiments are conducted to provide various insights about FL for MR image reconstruction. Experimental results demonstrate that the proposed framework is a promising direction to utilize multi-institutional data without compromising patients' privacy for achieving improved MR image reconstruction. Our code is available at https://github.com/guopengf/FL-MRCM.
| S-EPMC9017654 | biostudies-literature
Project description:ObjectivesThe objective of this study is to prospectively assess the effectiveness of shoulder magnetic resonance (MR) arthrograms with positional manoeuvres in detecting posterior synovial folds.MethodsTwo radiologists independently assessed all axial MR arthrograms in internal rotation, neutral position, and external rotation for the presence of a posterior synovial fold. The diagnostic performances of the MR arthrograms were then compared, with results validated through arthroscopy.ResultsArthroscopy was performed on 81 of the 150 patients included in the study. A posterior synovial fold was identified arthroscopically in eleven of these patients. Measurements of the posterior synovial fold obtained in external rotation and the neutral position of the arm showed a significant correlation with arthroscopic results (p < 0.05). For detecting the posterior synovial fold with arthroscopic correlation, the sensitivity and specificity values for observer 1 and observer 2 were 100-81.4% and 100-88.6%, respectively, for MR arthrograms in the neutral position; 100-52.9% and 100-62.9% for MR arthrograms in external rotation; and 100-95.7% and 81.8-98.6% for MR arthrograms in internal rotation. There was a fair agreement for MR arthrography in external rotation for detecting posterior synovial folds, while MR arthrograms in internal rotation and neutral position showed near-perfect and significant interobserver agreement.ConclusionThe rotational positions of the humeral neck during MR arthrographic examination can influence the diagnostic specificity and sensitivity of axial MR arthrograms in detecting the posterior synovial fold.Clinical relevance statementThe posterior synovial fold can mimic a posterior labral detachment. Therefore, its correct identification is crucial in order to avoid unnecessary surgical procedures.Key pointsMovement of the shoulder may introduce variability in MR arthrography appearance. Rotation of the humeral neck during MR arthrography can affect diagnoses in posterior synovial fold detection. Given that posterior synovial folds can imitate posterior labral detachment, their correct identification is crucial to avoid unnecessary surgical procedures.
| S-EPMC11782312 | biostudies-literature
Project description:Background and purposePhysiological motion impacts the dose delivered to tumours and vital organs in external beam radiotherapy and particularly in particle therapy. The excellent soft-tissue demarcation of 4D magnetic resonance imaging (4D-MRI) could inform on intra-fractional motion, but long image reconstruction times hinder its use in online treatment adaptation. Here we employ techniques from high-performance computing to reduce 4D-MRI reconstruction times below two minutes to facilitate their use in MR-guided radiotherapy.Material and methodsFour patients with pancreatic adenocarcinoma were scanned with a radial stack-of-stars gradient echo sequence on a 1.5T MR-Linac. Fast parallelised open-source implementations of the extra-dimensional golden-angle radial sparse parallel algorithm were developed for central processing unit (CPU) and graphics processing unit (GPU) architectures. We assessed the impact of architecture, oversampling and respiratory binning strategy on 4D-MRI reconstruction time and compared images using the structural similarity (SSIM) index against a MATLAB reference implementation. Scaling and bottlenecks for the different architectures were studied using multi-GPU systems.ResultsAll reconstructed 4D-MRI were identical to the reference implementation (SSIM > 0.99). Images reconstructed with overlapping respiratory bins were sharper at the cost of longer reconstruction times. The CPU + GPU implementation was over 17 times faster than the reference implementation, reconstructing images in 60 ± 1 s and hyper-scaled using multiple GPUs.ConclusionRespiratory-resolved 4D-MRI reconstruction times can be reduced using high-performance computing methods for online workflows in MR-guided radiotherapy with potential applications in particle therapy.
| S-EPMC10474606 | biostudies-literature
Project description:IntroductionHigh-resolution whole-heart coronary magnetic resonance angiography (CMRA) often suffers from unreasonably long scan times, rendering imaging acceleration highly desirable. Traditional reconstruction methods used in CMRA rely on either hand-crafted priors or supervised learning models. Although the latter often yield superior reconstruction quality, they require a large amount of training data and memory resources, and may encounter generalization issues when dealing with out-of-distribution datasets.MethodsTo address these challenges, we introduce an unsupervised reconstruction method that combines deep image prior (DIP) with compressed sensing (CS) to accelerate 3D CMRA. This method incorporates a slice-by-slice DIP reconstruction and 3D total variation (TV) regularization, enabling high-quality reconstruction under a significant acceleration while enforcing continuity in the slice direction. We evaluated our method by comparing it to iterative SENSE, CS-TV, CS-wavelet, and other DIP-based variants, using both retrospectively and prospectively undersampled datasets.ResultsThe results demonstrate the superiority of our 3D DIP-CS approach, which improved the reconstruction accuracy relative to the other approaches across both datasets. Ablation studies further reveal the benefits of combining DIP with 3D TV regularization, which leads to significant improvements of image quality over pure DIP-based methods. Evaluation of vessel sharpness and image quality scores shows that DIP-CS improves the quality of reformatted coronary arteries.DiscussionThe proposed method enables scan-specific reconstruction of high-quality 3D CMRA from a five-minute acquisition, without relying on fully-sampled training data or placing a heavy burden on memory resources.
| S-EPMC11424428 | biostudies-literature
Project description:ObjectivesTo evaluate the feasibility of combining compressed sense (CS) with a newly developed deep learning-based algorithm (CS-AI) using convolutional neural networks to accelerate 2D MRI of the knee.MethodsIn this prospective study, 20 healthy volunteers were scanned with a 3T MRI scanner. All subjects received a fat-saturated sagittal 2D proton density reference sequence without acceleration and four additional acquisitions with different acceleration levels: 2, 3, 4 and 6. All sequences were reconstructed with the conventional CS and a new CS-AI algorithm. Two independent, blinded readers rated all images by seven criteria (overall image impression, visible artifacts, delineation of anterior ligament, posterior ligament, menisci, cartilage, and bone) using a 5-point Likert scale. Signal- and contrast-to-noise ratios were calculated. Subjective ratings and quantitative metrics were compared between CS and CS-AI with similar acceleration levels and between all CS/CS-AI images and the non-accelerated reference sequence. Friedman and Dunn´s multiple comparison tests were used for subjective, ANOVA and the Tukey Kramer test for quantitative metrics.ResultsConventional CS images at the lowest acceleration level (CS2) were already rated significantly lower than reference for 6/7 criteria. CS-AI images maintained similar image quality to the reference up to CS-AI three for all criteria, which would allow for a reduction in scan time of 64% with unchanged image quality compared to the unaccelerated sequence. SNR and CNR were significantly higher for all CS-AI reconstructions compared to CS (all p < 0.05).ConclusionsAI-based image reconstruction showed higher image quality than CS for 2D knee imaging. Its implementation in the clinical routine yields the potential for faster MRI acquisition but needs further validation in non-healthy study subjects.Advances in knowledgeCombining compressed SENSE with a newly developed deep learning-based algorithm using convolutional neural networks allows a 64% reduction in scan time for 2D imaging of the knee. Implementation of the new deep learning-based algorithm in clinical routine in near future should enable better image quality/resolution with constant scan time, or reduced acquisition times while maintaining diagnostic quality.
| S-EPMC10230385 | biostudies-literature
Project description:BackgroundTo investigate image quality and agreement of derived cardiac function parameters in a novel joint image reconstruction and segmentation approach based on disentangled representation learning, enabling real-time cardiac cine imaging during free-breathing.MethodsA multi-tasking neural network architecture, incorporating disentangled representation learning, was trained using simulated examinations based on data from a public repository along with cardiovascular magnetic resonance (CMR) scans specifically acquired for model development. An exploratory feasibility study evaluated the method on undersampled real-time acquisitions using an in-house developed spiral balanced steady-state free precession pulse sequence in eight healthy participants and five patients with intermittent atrial fibrillation. Images and predicted left ventricle segmentations were compared to the reference standard of electrocardiography (ECG)-gated segmented Cartesian cine with repeated breath-holds and corresponding manual segmentation.ResultsOn a 5-point Likert scale, image quality of the real-time breath-hold approach and Cartesian cine was comparable in healthy participants (RT-BH: 1.99 ± 0.98, Cartesian: 1.94 ± 0.86, p = 0.052), but slightly inferior in free-breathing (RT-FB: 2.40 ± 0.98, p < 0.001). In patients with arrhythmia, both real-time approaches demonstrated favorable image quality (RT-BH: 2.10 ± 1.28, p < 0.001, RT-FB: 2.40 ± 1.13, p < 0.01, Cartesian: 2.68 ± 1.13). Intra-observer reliability was good (intraclass correlation coefficient = 0.77, 95% confidence interval [0.75, 0.79], p < 0.001). In functional analysis, a positive bias was observed for ejection fractions derived from the proposed model compared to the clinical reference standard (RT-BH mean: 58.5 ± 5.6%, bias: +3.47%, 95% confidence interval [-0.86, 7.79%], RT-FB mean: 57.9 ± 10.6%, bias: +1.45%, [-3.02, 5.91%], Cartesian mean: 54.9 ± 6.7%).ConclusionThe introduced real-time CMR imaging technique enables high-quality cardiac cine data acquisitions in 1-2 min, eliminating the need for ECG gating and breath-holds. This approach offers a promising alternative to the current clinical practice of segmented acquisition, with shorter scan times, improved patient comfort, and increased robustness to arrhythmia and patient non-compliance.
| S-EPMC11874730 | biostudies-literature
Project description:Deep learning has been used to improve photoacoustic (PA) image reconstruction. One major challenge is that errors cannot be quantified to validate predictions when ground truth is unknown. Validation is key to quantitative applications, especially using limited-bandwidth ultrasonic linear detector arrays. Here, we propose a hybrid Bayesian convolutional neural network (Hybrid-BCNN) to jointly predict PA image and segmentation with error (uncertainty) predictions. Each output pixel represents a probability distribution where error can be quantified. The Hybrid-BCNN was trained with simulated PA data and applied to both simulations and experiments. Due to the sparsity of PA images, segmentation focuses Hybrid-BCNN on minimizing the loss function in regions with PA signals for better predictions. The results show that accurate PA segmentations and images are obtained, and error predictions are highly statistically correlated to actual errors. To leverage error predictions, confidence processing created PA images above a specific confidence level.
| S-EPMC11424948 | biostudies-literature