Showing papers in "Magnetic Resonance Imaging in 2020"

TL;DR: DeepcomplexMRI as discussed by the authors proposes a multi-channel image reconstruction method, named DeepcomplexMRI, to accelerate parallel MR imaging with residual complex convolutional neural network, which takes advantage of the availability of a large number of existing multichannel groudtruth images and uses them as target data to train the deep residual convolution neural network offline.

TL;DR: The historical evolution of some major changes in radiology are traced as background to how Artificial intelligence may also be embraced into practice.

TL;DR: A DL-based ASL MRI denoising algorithm (DL-ASL) that was constructed using convolutional neural networks with dilated convolution and wide activation residual blocks to explicitly take the inter-voxel correlations into account, and preserve spatial resolution of input image during model learning is proposed and validated.

TL;DR: A novel “free-running” (non-ECG triggered) cMRF framework for simultaneous myocardial T1 and T2 mapping and cardiac Cine imaging in a single scan is proposed and evaluated.

TL;DR: Assessment of the CNR for the enhanced T1W image (T1WE) showed a significantly better contrast between gray matter and white matter than conventional T 1W images in both patients with Parkinson's disease and healthy controls.

TL;DR: A non invasive method to detect the prostate cancer grade (the so-called Gleason score) by computing radiomic biomarkers from magnetic resonance images and predicts whether the cancer is suitable for the surgery treatment basing on the pathologist and surgeon suggestions.

TL;DR: The proposed 2D deep learning-based method describes the uncertain regions of pancreatic MRI images based on shadowed sets theory and outperforms the state-of-the-art methods in terms of the Dice similarity coefficient.

TL;DR: It is demonstrated that PD with 4D flow MRI is clinically feasible in BAV patients and provides an additional physiologic description of valve-related hemodynamic obstruction.

TL;DR: The DRN-DCMB model significantly improved the overall image quality, reduced the severity of the motion artifacts, and improved the image sharpness, while kept the image contrast.

TL;DR: The Gd-CQDs@N-Fe3O4 nanoparticles combining two synergetic imaging modalities showed great potential in FI/MRI dual-modal imaging for a more complementary and accurate detection.

TL;DR: The proposed MS-VNN enables 5-fold and 9-fold undersampled CMRA acquisitions with comparable image quality that the corresponding fully-sampled scan, and achieves higher image quality than CS and VNN reconstructions.

TL;DR: This work evaluated the concatenation of two-element U-nets, termed the W-net, operating in k-space (K) and image (I) domains, for multi-channel magnetic resonance (MR) image reconstruction and indicated that networks that operate solely in the image domain were better when independently processing individual channels of multi-Channel data.

TL;DR: It is demonstrated that MR imaging-based radiomic analysis of brain metastases in patients with primary lung cancer may be used to classify mutation status, and this approach may be useful for devising treatment strategies and informing prognosis.

TL;DR: It is feasible to use the convolutional neural network algorithm to predict NAC response in patients using a multi-institution dataset and a 5-fold cross validation was used for performance evaluation.

TL;DR: MR imaging shows that exosomes labeled with FTH1 can be visualized in vitro and in vivo, and can be utilized as a tool for the study of the role of exosome under different conditions.

TL;DR: A volumetric hierarchical deep residual convolutional neural network, referred to as T-Net, to provide a data-driven end-to-end mapping from sparsely sampled magnetic resonance (MR) image acquisition to fully sampled MR images, where cartilage MR images were acquired using an Ultra-short TE sequence and retrospectively undersampled using pseudo-random Cartesian and radial acquisition schemes.

TL;DR: The feasibility of using a multi atlas approach for localizing thalamic substructures in clinically acquired MR volumes is suggested and may have a direct impact on surgeries such as Deep Brain Stimulation procedures that require the implantation of stimulating electrodes in specificThalamic nuclei.

TL;DR: VASARI features in combination with clinical and radiomic features from the enhancing tumour show promise for predicting OS with a high accuracy in patients with glioblastoma from pre-operative volumetric CE-T1WI.

TL;DR: This review aims to give a comprehensive overview of previous efforts on the design concept of multi-tuned coils, predominantly for brain applications, with particular focus on the single or multiple design structures and emerging technologies.

TL;DR: A review article summarizes the large number of MRI-based investigations on knee joints under mechanical loading which have been reported in the literature including the corresponding MRI measures, the MRI-compatible devices employed, and potential challenges due to the limitations of clinical MRI sequences.

TL;DR: Experimental results under synthetic, complex-valued and clinical MR brain images demonstrate great potential of the proposed network with substantially improved quantitative measures and visual inspections.

TL;DR: A novel motion aligned locally low rank tensor (MALLRT) model for dynamic MRI reconstruction that achieved substantially better image reconstruction quality in terms of both signal to error ratio (SER) and structural similarity index (SSIM) metrics, and visual perception in preserving spatial details and capturing temporal variations.

TL;DR: Best performance for segmented tissue volumes was obtained with all four image contrasts as the input, and comparable performance was attainable with FLAIR only as theinput, albeit with a moderate increase in FPR for small lesions.

TL;DR: Pretreatment D, Ktrans, Ve and stage were independent prognostic factors for cervical cancer and the predictive capacity of multi-parametric MRI was superior to individual MRI parameters.

TL;DR: The proposed Knowledge-driven Feature Learning and Integration framework is a domain knowledge and deep network ensemble, which can extract sufficient and effective features from each sub-sequence for a comprehensive diagnosis of breast cancer.

TL;DR: HerMES and MEGA-PRESS offer similar reliabilities for measuring GABA, while MGA-PRESS at TE = 120 ms is more reliable for measuring GSH relative to HERMES relative to TE’s 80’ms.

TL;DR: Initial results of 10.5 T static field exposure indicate that cognitive performance is not compromised at isocenter, subjects experience increased eye movement at isOCenter, and subjects experience small changes in vital signs but no field-induced increase in blood pressure.

TL;DR: An end-to-end deep learning technique, named S-Net, to correct the susceptibility artifacts the reversed-PE image pair, which accelerates the medical image processing pipelines and makes the real-time correction for MRI scanners feasible.

TL;DR: In this paper, texture features were extracted from all prescribed areas and MS lesions and used as input into Support Vector Machine (SVM) models to differentiate between the following: NAWM 0 vs ROISC0, NAWM0 vs NAWM6-12 vs L6 -12, ROIS0 vs L0, ROis0 vs LR 0, L0 vs R0, LR 0 vs LR 6-12, LR 6 -12 and ROIS 0 vs RISC 0.

TL;DR: NCMRL is a non-invasive imaging technique that is suitable for the evaluation of patients affected by lipedema and lipolymphedema, helping in the differential diagnosis.