Multi-contrast Magnetic Resonance Imaging Research Articles

Multi-parametric MRI for radiotherapy simulation.

Magnetic resonance imaging (MRI) has become an important imaging modality in the field of radiotherapy (RT) in the past decade, especially with the development of various novel MRI and image-guidance techniques. In this review article, we will describe recent developments and discuss the applications of multi-parametric MRI (mpMRI) in RT simulation. In this review, mpMRI refers to a general and loose definition which includes various multi-contrast MRI techniques. Specifically, we will focus on the implementation, challenges, and future directions of mpMRI techniques for RT simulation.

MRI image synthesis for fluid-attenuated inversion recovery and diffusion-weighted images with deep learning.

This study aims to synthesize fluid-attenuated inversion recovery (FLAIR) and diffusion-weighted images (DWI) with a deep conditional adversarial network from T1- and T2-weighted magnetic resonance imaging (MRI) images. A total of 1980 images of 102 patients were split into two datasets: 1470 (68 patients) in a training set and 510 (34 patients) in a test set. The prediction framework was based on a convolutional neural network with a generator and discriminator. T1-weighted, T2-weighted, and composite images were used as inputs. The digital imaging and communications in medicine (DICOM) images were converted to 8-bit red-green-blue images. The red and blue channels of the composite images were assigned to 8-bit grayscale pixel values in T1-weighted images, and the green channel was assigned to those in T2-weighted images. The prediction FLAIR and DWI images were of the same objects as the inputs. For the results, the prediction model with composite MRI input images in the DWI image showed the smallest relative mean absolute error (rMAE) and largest mutual information (MI), and that in the FLAIR image showed the largest relative mean-square error (rMSE), relative root-mean-square error (rRMSE), and peak signal-to-noise ratio (PSNR). For the FLAIR image, the prediction model with the T2-weighted MRI input images generated more accurate synthesis results than that with the T1-weighted inputs. The proposed image synthesis framework can improve the versatility and quality of multi-contrast MRI without extra scans. The composite input MRI image contributes to synthesizing the multi-contrast MRI image efficiently.

A Joint Group Sparsity-based deep learning for multi-contrast MRI reconstruction

Multi-contrast magnetic resonance imaging (MRI) can provide richer diagnosis information. The data acquisition time, however, is increased than single-contrast imaging. To reduce this time, k-space undersampling is an effective way but a smart reconstruction algorithm is required to remove undersampling image artifacts. Traditional algorithms commonly explore the similarity of multi-contrast images through joint sparsity. However, these algorithms are time-consuming due to the iterative process and require adjusting hyperparameters manually. Recently, data-driven deep learning successfully overcome these limitations but the reconstruction error still needs to be further reduced. Here, we propose a Joint Group Sparsity-based Network (JGSN) for multi-contrast MRI reconstruction, which unrolls the iterative process of the joint sparsity algorithm. The designed network includes data consistency modules, learnable sparse transform modules, and joint group sparsity constraint modules. In particular, weights of different contrasts in the transform module are shared to reduce network parameters without sacrificing the quality of reconstruction. The experiments were performed on the retrospective undersampled brain and knee data. Experimental results on in vivo brain data and knee data show that our method consistently outperforms the state-of-the-art methods under different sampling patterns.

Joint optimization of Cartesian sampling patterns and reconstruction for single‐contrast and multi‐contrast fast magnetic resonance imaging

Background and objectiveCompressed sensing (CS) has gained increased attention in magnetic resonance imaging (MRI), leveraging its efficacy to accelerate image acquisition. Incoherence measurement and non-linear reconstruction are the most crucial guarantees of accurate restoration. However, the loose link between measurement and reconstruction hinders the further improvement of reconstruction quality, i.e., the default sampling pattern is not adaptively tailored to the downstream reconstruction method. When single-contrast reconstruction (SCR) has been upgraded to its multi-contrast reconstruction (MCR) variant, the identical morphologic information as a priori source could be integrated into the reconstruction procedure. How to measure less and reconstruct effectively by using the shareable morphologic information of various contrast images is an attractive topic. MethodsAn adaptive sampling (AS) based end-to-end framework (ASSCR or ASMCR) is proposed to address this issue, which simultaneously optimizes sampling patterns and reconstruction from under-sampled data in SCR or MCR scenarios. Several deep probabilistic subsampling (DPS) modules are used in AS network to construct a sampling pattern generator. In SCR and MCR, a convolution block and a data consistency layer are iteratively applied in the reconstruction network. Specifically, the learned optimal sampling pattern output from the trained AS sub-net is used for under-sampling. Incoherence measurement for single-contrast images and the combination of sampling patterns for multi-contrast data are guided by the SCR/MCR sub-net. ResultsExperiments were conducted on two single-contrast and one multi-contrast public MRI datasets. Compared with several state-of-the-art reconstruction methods, SCR results show that a learned sampling pattern brings the quality of the reconstructed image closer to the fully-sampled reference. With the addition of different contrast images, under-sampled images with higher acceleration factors could be well recovered. ConclusionThe proposed method could improve the reconstruction quality of under-sampled images by using adaptive sampling patterns and learning-based reconstruction.

Undersampled Multi-Contrast MRI Reconstruction Based on Double-Domain Generative Adversarial Network.

Multi-contrast magnetic resonance imaging can provide comprehensive information for clinical diagnosis. However, multi-contrast imaging suffers from long acquisition time, which makes it inhibitive for daily clinical practice. Subsampling k-space is one of the main methods to speed up scan time. Missing k-space samples will lead to inevitable serious artifacts and noise. Considering the assumption that different contrast modalities share some mutual information, it may be possible to exploit this redundancy to accelerate multi-contrast imaging acquisition. Recently, generative adversarial network shows superior performance in image reconstruction and synthesis. Some studies based on k-space reconstruction also exhibit superior performance over conventional state-of-art method. In this study, we propose a cross-domain two-stage generative adversarial network for multi-contrast images reconstruction based on prior full-sampled contrast and undersampled information. The new approach integrates reconstruction and synthesis, which estimates and completes the missing k-space and then refines in image space. It takes one fully-sampled contrast modality data and highly undersampled data from several other modalities as input, and outputs high quality images for each contrast simultaneously. The network is trained and tested on a public brain dataset from healthy subjects. Quantitative comparisons against baseline clearly indicate that the proposed method can effectively reconstruct undersampled images. Even under high acceleration, the network still can recover texture details and reduce artifacts.

In vivo symmetric multi-contrast MRI brain templates and atlas for spontaneously hypertensive rats.

Spontaneously hypertensive rats (SHRs) are a valuable animal model of essential hypertension. The increasing use of SHRs in neuroimaging has generated an urgent demand for a template set that provides a reference for advanced data analysis. Structural T2-weighted magnetic resonance imaging (MRI), diffusion tensor imaging (DTI) and functional MRI scans that were used to build the template set were obtained from 8 SHRs longitudinally scanned in vivo at 10, 24 and 52weeks of age. These symmetric multi-contrast templates were constructed by iterative registration and averaging. The cortical atlas was derived from the Tohoku atlas, and the subcortical regions were manually delineated based on the templates. A set of SHR brain images named the Hebei Medical University rat brain template set (HRT) comprised 3D symmetric T2WI, raw T2-weighted signal with no added diffusion weighting (B0), fractional anisotropy (FA), mean diffusivity (MD) and blood oxygen level-dependent (BOLD) templates; tissue probability maps (TPMs) of gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF); and a whole-brain atlas with 163 labels. We quantitatively validated the template and characterized the longitudinal changes in brain morphology in different brain tissues as SHRs aged. To our knowledge, the HRT is the first MRI template set for SHRs. We believe that the HRT can serve as a beneficial tool for precise analysis of the SHR brain using structural and functional MRI, which can promote neuroimaging studies on essential hypertension.

Elevated Hemoglobin A1c Is Associated With Leaky Plaque Neovasculature as Detected by Dynamic Contrast-Enhanced Magnetic Resonance Imaging.

Patients with diabetes have accelerated atherosclerosis progression, but the underlying mechanisms are not fully understood. Dynamic contrast-enhanced magnetic resonance imaging has allowed in vivo characterization of plaque neovasculature, which plays a critical role in plaque progression. We aimed to evaluate the impact of diabetes on carotid plaque neovasculature as assessed by dynamic contrast-enhanced magnetic resonance imaging. Patients with recent ischemic stroke and ipsilateral carotid plaque underwent multicontrast magnetic resonance imaging for characterizing plaque morphology and dynamic contrast-enhanced magnetic resonance imaging for pharmacokinetic parameters of plaque neovasculature, including transfer constant (Ktrans, reflecting flow, endothelial surface area, and permeability) and fractional plasma volume (νp). Sixty-five patients were enrolled, including 30 patients with diabetes (years since diagnosis: median 5.0 [interquartile range, [3.0-12.0]) and 35 patients without diabetes. Subjects with diabetes had a greater plaque burden and a higher prevalence of high-risk characteristics. Additionally, carotid plaques in the subjects with diabetes showed higher Ktrans than those in the subjects without diabetes (0.100±0.048 min-1 versus 0.067±0.042 min-1, P=0.005) but νp was numerically lower in the subjects with diabetes (5.2±3.7% versus 6.2±4.3%, P=0.31). The association of diabetes with high Ktrans (β=0.033, P=0.005) was independent of patient and plaque characteristics and remained largely intact after adjusting for serum lipids, glucose, or hs-CRP (high-sensitivity C-reactive protein). However, it became nonexistent after adjusting for hemoglobin A1c (β=-0.010, P=0.49). Dynamic contrast-enhanced magnetic resonance imaging of carotid plaques suggested that plaque neovasculature in patients with diabetes is leaky, indicating enhanced capability of bringing blood constituents and facilitating extravasation of inflammatory cells, erythrocytes, and plasma proteins. Leaky plaque neovasculature correlated with hemoglobin A1c and may play a role in accelerated atherosclerosis progression in diabetes.

Multi-Contrast Magnetic Resonance Imaging of Visual White Matter Pathways in Patients With Glaucoma.

PurposeGlaucoma is a disorder that involves visual field loss caused by retinal ganglion cell damage. Previous diffusion magnetic resonance imaging (dMRI) studies have demonstrated that retinal ganglion cell damage affects tissues in the optic tract (OT) and optic radiation (OR). However, because previous studies have used a simple diffusion tensor model to analyze dMRI data, the microstructural interpretation of white matter tissue changes remains uncertain. In this study, we used a multi-contrast MRI approach to further clarify the type of microstructural damage that occurs in patients with glaucoma.MethodsWe collected dMRI data from 17 patients with glaucoma and 30 controls using 3-tesla (3T) MRI. Using the dMRI data, we estimated three types of tissue property metrics: intracellular volume fraction (ICVF), orientation dispersion index (ODI), and isotropic volume fraction (IsoV). Quantitative T1 (qT1) data, which may be relatively specific to myelin, were collected from all subjects.ResultsIn the OT, all four metrics showed significant differences between the glaucoma and control groups. In the OR, only the ICVF showed significant between-group differences. ICVF was significantly correlated with qT1 in the OR of the glaucoma group, although qT1 did not show any abnormality at the group level.ConclusionsOur results suggest that, at the group level, tissue changes in OR caused by glaucoma might be explained by axonal damage, which is reflected in the intracellular diffusion signals, rather than myelin damage. The significant correlation between ICVF and qT1 suggests that myelin damage might also occur in a smaller number of severe cases.

Virtual mouse brain histology from multi-contrast MRI via deep learning.

1H MRI maps brain structure and function non-invasively through versatile contrasts that exploit inhomogeneity in tissue micro-environments. Inferring histopathological information from magnetic resonance imaging (MRI) findings, however, remains challenging due to absence of direct links between MRI signals and cellular structures. Here, we show that deep convolutional neural networks, developed using co-registered multi-contrast MRI and histological data of the mouse brain, can estimate histological staining intensity directly from MRI signals at each voxel. The results provide three-dimensional maps of axons and myelin with tissue contrasts that closely mimic target histology and enhanced sensitivity and specificity compared to conventional MRI markers. Furthermore, the relative contribution of each MRI contrast within the networks can be used to optimize multi-contrast MRI acquisition. We anticipate our method to be a starting point for translation of MRI results into easy-to-understand virtual histology for neurobiologists and provide resources for validating novel MRI techniques.

Deep learning-based convolutional neural network for intramodality brain MRI synthesis.

PurposeThe existence of multicontrast magnetic resonance (MR) images increases the level of clinical information available for the diagnosis and treatment of brain cancer patients. However, acquiring the complete set of multicontrast MR images is not always practically feasible. In this study, we developed a state‐of‐the‐art deep learning convolutional neural network (CNN) for image‐to‐image translation across three standards MRI contrasts for the brain.MethodsBRATS’2018 MRI dataset of 477 patients clinically diagnosed with glioma brain cancer was used in this study, with each patient having T1‐weighted (T1), T2‐weighted (T2), and FLAIR contrasts. It was randomly split into 64%, 16%, and 20% as training, validation, and test set, respectively. We developed a U‐Net model to learn the nonlinear mapping of a source image contrast to a target image contrast across three MRI contrasts. The model was trained and validated with 2D paired MR images using a mean‐squared error (MSE) cost function, Adam optimizer with 0.001 learning rate, and 120 epochs with a batch size of 32. The generated synthetic‐MR images were evaluated against the ground‐truth images by computing the MSE, mean absolute error (MAE), peak signal‐to‐noise ratio (PSNR), and structural similarity index (SSIM).ResultsThe generated synthetic‐MR images with our model were nearly indistinguishable from the real images on the testing dataset for all translations, except synthetic FLAIR images had slightly lower quality and exhibited loss of details. The range of average PSNR, MSE, MAE, and SSIM values over the six translations were 29.44–33.25 dB, 0.0005–0.0012, 0.0086–0.0149, and 0.932–0.946, respectively. Our results were as good as the best‐reported results by other deep learning models on BRATS datasets.ConclusionsOur U‐Net model exhibited that it can accurately perform image‐to‐image translation across brain MRI contrasts. It could hold great promise for clinical use for improved clinical decision‐making and better diagnosis of brain cancer patients due to the availability of multicontrast MRIs. This approach may be clinically relevant and setting a significant step to efficiently fill a gap of absent MR sequences without additional scanning.

Combined acquisition of diffusion and T2*-weighted measurements using simultaneous multi-contrast magnetic resonance imaging

ObjectIn this work, we present a technique called simultaneous multi-contrast imaging (SMC) to acquire multiple contrasts within a single measurement. Simultaneous multi-slice imaging (SMS) shortens scan time by allowing the repetition time (TR) to be reduced for a given number of slices. SMC imaging preserves TR, while combining different scan types into a single acquisition. This technique offers new opportunities in clinical protocols where examination time is a critical factor and multiple image contrasts must be acquired.Materials and methodsHigh-resolution, navigator-corrected, diffusion-weighted imaging was performed simultaneously with T2*-weighted acquisition at 3 T in a phantom and in five healthy subjects using an adapted readout-segmented EPI sequence (rs-EPI).ResultsThe results demonstrated that simultaneous acquisition of two contrasts (here diffusion-weighted imaging and T2*-weighting) with SMC imaging is feasible with robust separation of contrasts and minimal effect on image quality.DiscussionThe simultaneous acquisition of multiple contrasts reduces the overall examination time and there is an inherent registration between contrasts. By using the results of this study to control saturation effects in SMC, the method enables rapid acquisition of distortion-matched and well-registered diffusion-weighted and T2*-weighted imaging, which could support rapid diagnosis and treatment of acute stroke.

3D Neural Networks for Visceral and Subcutaneous Adipose Tissue Segmentation using Volumetric Multi-Contrast MRI.

Individuals with obesity have larger amounts of visceral (VAT) and subcutaneous adipose tissue (SAT) in their body, increasing the risk for cardiometabolic diseases. The reference standard to quantify SAT and VAT uses manual annotations of magnetic resonance images (MRI), which requires expert knowledge and is time-consuming. Although there have been studies investigating deep learning-based methods for automated SAT and VAT segmentation, the performance for VAT remains suboptimal (Dice scores of 0.43 to 0.89). Previous work had key limitations of not fully considering the multi-contrast information from MRI and the 3D anatomical context, which are critical for addressing the complex spatially varying structure of VAT. An additional challenge is the imbalance between the number and distribution of pixels representing SAT/VAT. This work proposes a network based on 3D U-Net that utilizes the full field-of-view volumetric T1-weighted, water, and fat images from dual-echo Dixon MRI as the multi-channel input to automatically segment SAT and VAT in adults with overweight/obesity. In addition, this work extends the 3D U-Net to a new Attention-based Competitive Dense 3D U-Net (ACD 3D U-Net) trained with a class frequency-balancing Dice loss (FBDL). In an initial testing dataset, the proposed 3D U-Net and ACD 3D U-Net with FBDL achieved 3D Dice scores of (mean ± standard deviation) 0.99 ±0.01 and 0.99±0.01 for SAT, and 0.95±0.04 and 0.96 ±0.04 for VAT, respectively, compared to manual annotations. The proposed 3D networks had rapid inference time (<60 ms/slice) and can enable automated segmentation of SAT and VAT.Clinical relevance- This work developed 3D neural networks to automatically, accurately, and rapidly segment visceral and subcutaneous adipose tissue on MRI, which can help to characterize the risk for cardiometabolic diseases such as diabetes, elevated glucose levels, and hypertension.

Unsupervised anomaly detection in MR images using multicontrast information.

Anomaly detection in magnetic resonance imaging (MRI) is to distinguish the relevant biomarkers of diseases from those of normal tissues. In this paper, an unsupervised algorithm is proposed for pixel-level anomaly detection in multicontrast MRI. A deep neural network is developed, which uses only normal MR images as training data. The network has the two stages of feature generation and density estimation. For feature generation, relevant features are extracted from multicontrast MR images by performing contrast translation and dimension reduction. For density estimation, the distributions of the extracted features are estimated by using Gaussian mixture model (GMM). The two processes are trained to estimate normative distributions well presenting large normal datasets. In test phases, the proposed method can detect anomalies by measuring log-likelihood that a test sample belongs to the estimated normative distributions. The proposed method and its variants were applied to detect glioblastoma and ischemic stroke lesion. Comparison studies with six previous anomaly detection algorithms demonstrated that the proposed method achieved relevant improvements in quantitative and qualitative evaluations. Ablation studies by removing each module from the proposed framework validated the effectiveness of each proposed module. The proposed deep learning framework is an effective tool to detect anomalies in multicontrast MRI. The unsupervised approaches would have great potentials in detecting various lesions where annotated lesion data collection is limited.

Detection of Advanced Lesions of Atherosclerosis in Carotid Arteries Using 3-Dimensional Motion-Sensitized Driven-Equilibrium Prepared Rapid Gradient Echo (3D-MERGE) Magnetic Resonance Imaging as a Screening Tool.

Two-dimensional high-resolution multicontrast magnetic resonance imaging (2D-MC MRI) is currently the most reliable and reproducible noninvasive carotid vessel wall imaging technique. However, the long scan time required for 2D-MC MRI restricts its practical clinical application. Alternatively, 3-dimensional motion-sensitized driven-equilibrium prepared rapid gradient echo (3D-MERGE) vessel wall MRI can provide high isotropic resolution with extensive coverage in two minutes. In this study, we sought to prove that 3D-MERGE alone can serve as a screening tool to identify advanced carotid lesions. Two hundred twenty-seven subjects suspected of recent ischemic stroke or transient ischemic attack were imaged using 2D-MC MRI with an imaging time of 30 minutes, then with 3D-MERGE with an imaging time of 2 minutes, on 3T-MRI scanners. Two experienced reviewers interpreted plaque components using 2D-MC MRI as the reference standard and categorized plaques using a modified American Heart Association lesion classification for MRI. Plaques of American Heart Association type IV and above were classified as advanced. Arteries of American Heart Association types I to II and III were categorized as normal or with early lesions, respectively. One radiologist independently reviewed only 3D-MERGE and labeled the plaques as advanced if they had a wall thickness of >2 mm with high or low signal intensity compared with the adjacent sternocleidomastoid muscle. Sensitivity, specificity, and accuracy for 3D-MERGE were calculated. Four hundred forty-nine arteries from 227 participants (mean age 61.2 years old, 64% male) were included in the analysis. Sensitivity, specificity, and accuracy for identification of advanced lesions on 3D-MERGE were 95.0% (95% CI, 91.8-97.2), 86.9% (95% CI, 81.4-92.0), 93.8% (95% CI, 91.1-95.8), respectively. 3D-MERGE can accurately identify advanced carotid atherosclerotic plaques in patients suspected of stroke or transient ischemic attack. It has a more extensive coverage and higher sensitivity and specificity for advanced plaque detection with a much shorter acquisition time than 2D-MC MRI. URL: https://www.clinicaltrials.gov; Unique identifier: NCT02017756.

Towards lower-dose PET using physics-based uncertainty-aware multimodal learning with robustness to out-of-distribution data

Radiation exposure in positron emission tomography (PET) imaging limits its usage in the studies of radiation-sensitive populations, e.g., pregnant women, children, and adults that require longitudinal imaging. Reducing the PET radiotracer dose or acquisition time reduces photon counts, which can deteriorate image quality. Recent deep-neural-network (DNN) based methods for image-to-image translation enable the mapping of low-quality PET images (acquired using substantially reduced dose), coupled with the associated magnetic resonance imaging (MRI) images, to high-quality PET images. However, such DNN methods focus on applications involving test data that match the statistical characteristics of the training data very closely and give little attention to evaluating the performance of these DNNs on new out-of-distribution (OOD) acquisitions. We propose a novel DNN formulation that models the (i) underlying sinogram-based physics of the PET imaging system and (ii) the uncertainty in the DNN output through the per-voxel heteroscedasticity of the residuals between the predicted and the high-quality reference images. Our sinogram-based uncertainty-aware DNN framework, namely, suDNN, estimates a standard-dose PET image using multimodal input in the form of (i) a low-dose/low-count PET image and (ii) the corresponding multi-contrast MRI images, leading to improved robustness of suDNN to OOD acquisitions. Results on in vivo simultaneous PET-MRI, and various forms of OOD data in PET-MRI, show the benefits of suDNN over the current state of the art, quantitatively and qualitatively.

Optimizing multicontrast MRI reconstruction with shareable feature aggregation and selection.

This paper proposes a new method for optimizing feature sharing in deep neural network-based, rapid, multicontrast magnetic resonance imaging (MC-MRI). Using the shareable information of MC images for accelerated MC-MRI reconstruction, current algorithms stack the MC images or features without optimizing the sharing protocols, leading to suboptimal reconstruction results. In this paper, we propose a novel feature aggregation and selection scheme in a deep neural network to better leverage the MC features and improve the reconstruction results. First, we propose to extract and use the shareable information by mapping the MC images into multiresolution feature maps with multilevel layers of the neural network. In this way, the extracted features capture complementary image properties, including local patterns from the shallow layers and semantic information from the deep layers. Then, an explicit selection module is designed to compile the extracted features optimally. That is, larger weights are learned to incorporate the constructive, shareable features; and smaller weights are assigned to the unshareable information. We conduct comparative studies on publicly available T2-weighted and T2-weighted fluid attenuated inversion recovery brain images, and the results show that the proposed network consistently outperforms existing algorithms. In addition, the proposed method can recover the images with high fidelity under 16 times acceleration. The ablation studies are conducted to evaluate the effectiveness of the proposed feature aggregation and selection mechanism. The results and the visualization of the weighted features show that the proposed method does effectively improve the usage of the useful features and suppress useless information, leading to overall enhanced reconstruction results. Additionally, the selection module can zero-out repeated and redundant features and improve network efficiency.

Synthesis of brain tumor multicontrast MR images for improved data augmentation.

Medical image analysis using deep neural networks has been actively studied. For accurate training of deep neural networks, the learning data should be sufficient and have good quality and generalized characteristics. However, in medical images, it is difficult to acquire sufficient patient data because of the difficulty of patient recruitment, the burden of annotation of lesions by experts, and the invasion of patients' privacy. In comparison, the medical images of healthy volunteers can be easily acquired. To resolve this data bias problem, the proposed method synthesizes brain tumor images from normal brain images. Our method can synthesize a huge number of brain tumor multicontrast MR images from numerous healthy brain multicontrast MR images and various concentric circles. Because tumors have complex characteristics, the proposed method simplifies them into concentric circles that are easily controllable. Then, it converts the concentric circles into various realistic tumor masks through deep neural networks. The tumor masks are used to synthesize realistic brain tumor images from normal brain images. We performed a qualitative and quantitative analysis to assess the usefulness of augmented data from the proposed method. Data augmentation by the proposed method provided significant improvements to tumor segmentation compared with other GAN-based methods. Intuitive experimental results are available online at https://github.com/KSH0660/BrainTumor. The proposed method can control the grade tumor masks by the concentric circles, and synthesize realistic brain tumor multicontrast MR images. In terms of data augmentation, the proposed method can successfully synthesize brain tumor images that can be used to train tumor segmentation networks or other deep neural networks.

T1-weighted and T2-weighted MRI image synthesis with convolutional generative adversarial networks.

The objective of this study was to propose an optimal input image quality for a conditional generative adversarial network (GAN) in T1-weighted and T2-weighted magnetic resonance imaging (MRI) images. A total of 2,024 images scanned from 2017 to 2018 in 104 patients were used. The prediction framework of T1-weighted to T2-weighted MRI images and T2-weighted to T1-weighted MRI images were created with GAN. Two image sizes (512 × 512 and 256 × 256) and two grayscale level conversion method (simple and adaptive) were used for the input images. The images were converted from 16-bit to 8-bit by dividing with 256 levels in a simple conversion method. For the adaptive conversion method, the unused levels were eliminated in 16-bit images, which were converted to 8-bit images by dividing with the value obtained after dividing the maximum pixel value with 256. The relative mean absolute error (rMAE ) was 0.15 for T1-weighted to T2-weighted MRI images and 0.17 for T2-weighted to T1-weighted MRI images with an adaptive conversion method, which was the smallest. Moreover, the adaptive conversion method has a smallest mean square error (rMSE) and root mean square error (rRMSE), and the largest peak signal-to-noise ratio (PSNR) and mutual information (MI). The computation time depended on the image size. Input resolution and image size affect the accuracy of prediction. The proposed model and approach of prediction framework can help improve the versatility and quality of multi-contrast MRI tests without the need for prolonged examinations.

Temporal trajectory of brain tissue property changes induced by electroconvulsive therapy

BackgroundAfter more than eight decades of electroconvulsive therapy (ECT) for pharmaco-resistant depression, the mechanisms governing its anti-depressant effects remain poorly understood. Computational anatomy studies using longitudinal T1-weighted magnetic resonance imaging (MRI) data have demonstrated ECT effects on hippocampus volume and cortical thickness, but they lack the interpretational specificity about underlying neurobiological processes. MethodsWe sought to fill in the gap of knowledge by acquiring quantitative MRI indicative for brain's myelin, iron and tissue water content at multiple time-points before, during and after ECT treatment. We adapted established tools for longitudinal spatial registration of MRI data to the relaxometry-based multi-parameter maps aiming to preserve the initial total signal amount and introduced a dedicated multivariate analytical framework. ResultsThe whole-brain voxel-based analysis based on a multivariate general linear model showed that there is no brain tissue oedema contributing to the predicted ECT-induced hippocampus volume increase neither in the short, nor in the long-term observations. Improvements in depression symptom severity over time were associated with changes in both volume estimates and brain tissue properties expanding beyond mesial temporal lobe structures to anterior cingulate cortex, precuneus and striatum. ConclusionThe obtained results stemming from multi-contrast MRI quantitative data provided a fingerprint of ECT-induced brain tissue changes over time that are contrasted against the background of established morphometry findings. The introduced data processing and statistical testing algorithms provided a reliable analytical framework for longitudinal multi-parameter brain maps. The results, particularly the evidence of lack of ECT impact on brain tissue water, should be considered preliminary considering the small sample size of the study.

Cascaded residual U-net for fully automatic segmentation of 3D carotid artery in high-resolution multi-contrast MR images

Accurate and automatic carotid artery segmentation for magnetic resonance (MR) images is eagerly expected, which can greatly assist a comprehensive study of atherosclerosis and accelerate the translation. Although many efforts have been made, identification of the inner lumen and outer wall in diseased vessels is still a challenging task due to complex vascular deformation, blurred wall boundary, and confusing componential expression. In this paper, we introduce a novel fully automatic 3D framework for simultaneously segmenting the carotid artery from high-resolution multi-contrast MR sequences based on deep learning. First, an optimal channel fitting structure is designed for identity mapping, and a novel 3D residual U-net is used as a basic network. Second, high-resolution MR images are trained using both patch-level and global-level strategies, and the two pre-segmentation results are optimized based on structural characteristics. Third, the optimized pre-segmentation results are cascaded with the patch-cropped MR volume data and trained to segment the carotid lumen and wall. Extensive experiments demonstrate the proposed method outperforms the state-of-the-art 3D Unet-based segmentation models.