A multi-scale residual network for accelerated radial MR parameter mapping.
Ontology highlight
ABSTRACT:
SUBMITTER: Fu Z
PROVIDER: S-EPMC7580302 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:To enable accurate magnetic resonance (MR) parameter mapping with accelerated data acquisition, utilizing recent advances in constrained imaging with sparse sampling.A new constrained reconstruction method based on low-rank and sparsity constraints is proposed to accelerate MR parameter mapping. More specifically, the proposed method simultaneously imposes low-rank and joint sparse structures on contrast-weighted image sequences within a unified mathematical formulation. With a pre-estimated subspace, this formulation results in a convex optimization problem, which is solved using an efficient numerical algorithm based on the alternating direction method of multipliers.To evaluate the performance of the proposed method, two application examples were considered: (i) T2 mapping of the human brain and (ii) T1 mapping of the rat brain. For each application, the proposed method was evaluated at both moderate and high acceleration levels. Additionally, the proposed method was compared with two state-of-the-art methods that only use a single low-rank or joint sparsity constraint. The results demonstrate that the proposed method can achieve accurate parameter estimation with both moderately and highly undersampled data. Although all methods performed fairly well with moderately undersampled data, the proposed method achieved much better performance (e.g., more accurate parameter values) than the other two methods with highly undersampled data.Simultaneously imposing low-rank and sparsity constraints can effectively improve the accuracy of fast MR parameter mapping with sparse sampling.
| S-EPMC4344441 | biostudies-literature
Project description:BackgroundT2 * mapping can characterize tumor hypoxia, which may be associated with resistance to therapy. Acquiring T2 * maps during MR-guided radiotherapy could inform treatment adaptation by, for example, escalating the dose to resistant sub-volumes.PurposeThe purpose of this work is to demonstrate the feasibility of the accelerated T2 * mapping technique using model-based image reconstruction with integrated trajectory auto-correction (TrACR) for MR-guided radiotherapy on an MR-Linear accelerator (MR-Linac).Materials and methodsThe proposed method was validated in a numerical phantom, where two T2 * mapping approaches (sequential and joint) were compared for different noise levels (0,0.1,0.5,1) and gradient delays ([1, -1] and [1, -2] in units of dwell time for x- and y-axis, respectively). Fully sampled k-space was retrospectively undersampled using two different undersampling patterns. Root mean square errors (RMSEs) were calculated between reconstructed T2 * maps and ground truth. In vivo data was acquired twice weekly in one prostate and one head and neck cancer patient undergoing treatment on a 1.5 T MR-Linac. Data were retrospectively undersampled and T2 * maps reconstructed, with and without trajectory corrections were compared.ResultsNumerical simulations demonstrated that, for all noise levels, T2 * maps reconstructed with a joint approach demonstrated less error compared to an uncorrected and sequential approach. For a noise level of 0.1, uniform undersampling and gradient delay [1, -1] (in units of dwell time for x- and y-axis, respectively), RMSEs for sequential and joint approaches were 13.01 and 9.32 ms, respectively, which reduced to 10.92 and 5.89 ms for a gradient delay of [1, 2]. Similarly, for alternate undersampling and gradient delay [1, -1], RMSEs for sequential and joint approaches were 9.80 and 8.90 ms, respectively, which reduced to 9.10 and 5.40 ms for gradient delay [1, 2]. For in vivo data, T2 * maps reconstructed with our proposed approach resulted in less artifacts and improved visual appearance compared to the uncorrected approach. For both prostate and head and neck cancer patients, T2 * maps reconstructed from different treatment fractions showed changes within the planning target volume (PTV).ConclusionUsing the proposed approach, a retrospective data-driven gradient delay correction can be performed, which is particularly relevant for hybrid devices, where full information on the machine configuration is not available for image reconstruction. T2 * maps were acquired in under 5 min and can be integrated into MR-guided radiotherapy treatment workflows, which minimizes patient burden and leaves time for additional imaging for online adaptive radiotherapy on an MR-Linac.
| S-EPMC10946747 | biostudies-literature
Project description:PURPOSE:To develop and evaluate a novel deep learning-based image reconstruction approach called MANTIS (Model-Augmented Neural neTwork with Incoherent k-space Sampling) for efficient MR parameter mapping. METHODS:MANTIS combines end-to-end convolutional neural network (CNN) mapping, incoherent k-space undersampling, and a physical model as a synergistic framework. The CNN mapping directly converts a series of undersampled images straight into MR parameter maps using supervised training. Signal model fidelity is enforced by adding a pathway between the undersampled k-space and estimated parameter maps to ensure that the parameter maps produced synthesized k-space consistent with the acquired undersampling measurements. The MANTIS framework was evaluated on the T2 mapping of the knee at different acceleration rates and was compared with 2 other CNN mapping methods and conventional sparsity-based iterative reconstruction approaches. Global quantitative assessment and regional T2 analysis for the cartilage and meniscus were performed to demonstrate the reconstruction performance of MANTIS. RESULTS:MANTIS achieved high-quality T2 mapping at both moderate (R = 5) and high (R = 8) acceleration rates. Compared to conventional reconstruction approaches that exploited image sparsity, MANTIS yielded lower errors (normalized root mean square error of 6.1% for R = 5 and 7.1% for R = 8) and higher similarity (structural similarity index of 86.2% at R = 5 and 82.1% at R = 8) to the reference in the T2 estimation. MANTIS also achieved superior performance compared to direct CNN mapping and a 2-step CNN method. CONCLUSION:The MANTIS framework, with a combination of end-to-end CNN mapping, signal model-augmented data consistency, and incoherent k-space sampling, is a promising approach for efficient and robust estimation of quantitative MR parameters.
| S-EPMC7144418 | biostudies-literature
Project description:Accurate segmentation of perivascular spaces (PVSs) is an important step for quantitative study of PVS morphology. However, since PVSs are the thin tubular structures with relatively low contrast and also the number of PVSs is often large, it is challenging and time-consuming for manual delineation of PVSs. Although several automatic/semi-automatic methods, especially the traditional learning-based approaches, have been proposed for segmentation of 3D PVSs, their performance often depends on the hand-crafted image features, as well as sophisticated preprocessing operations prior to segmentation (e.g., specially defined regions-of-interest (ROIs)). In this paper, a novel fully convolutional neural network (FCN) with no requirement of any specified hand-crafted features and ROIs is proposed for efficient segmentation of PVSs. Particularly, the original T2-weighted 7T magnetic resonance (MR) images are first filtered via a non-local Haar-transform-based line singularity representation method to enhance the thin tubular structures. Both the original and enhanced MR images are used as multi-channel inputs to complementarily provide detailed image information and enhanced tubular structural information for the localization of PVSs. Multi-scale features are then automatically learned to characterize the spatial associations between PVSs and adjacent brain tissues. Finally, the produced PVS probability maps are recursively loaded into the network as an additional channel of inputs to provide the auxiliary contextual information for further refining the segmentation results. The proposed multi-channel multi-scale FCN has been evaluated on the 7T brain MR images scanned from 20 subjects. The experimental results show its superior performance compared with several state-of-the-art methods.
| S-EPMC6430123 | biostudies-literature
Project description:Using quantitative multi-parameter mapping (MPM), studies can investigate clinically relevant microstructural changes with high reliability over time and across subjects and sites. However, long acquisition times (20 min for the standard 1-mm isotropic protocol) limit its translational potential. This study aimed to evaluate the sensitivity gain of a fast 1.6-mm isotropic MPM protocol including post-processing optimized for longitudinal clinical studies. 6 healthy volunteers (35±7 years old; 3 female) were scanned at 3T to acquire the following whole-brain MPM maps with 1.6 mm isotropic resolution: proton density (PD), magnetization transfer saturation (MT), longitudinal relaxation rate (R1), and transverse relaxation rate (R2*). MPM maps were generated using two RF transmit field (B1+) correction methods: (1) using an acquired B1+ map and (2) using a data-driven approach. Maps were generated with and without Gibb's ringing correction. The intra-/inter-subject coefficient of variation (CoV) of all maps in the gray and white matter, as well as in all anatomical regions of a fine-grained brain atlas, were compared between the different post-processing methods using Student's t-test. The intra-subject stability of the 1.6-mm MPM protocol is 2-3 times higher than for the standard 1-mm sequence and can be achieved in less than half the scan duration. Intra-subject variability for all four maps in white matter ranged from 1.2-5.3% and in gray matter from 1.8 to 9.2%. Bias-field correction using an acquired B1+ map significantly improved intra-subject variability of PD and R1 in the gray (42%) and white matter (54%) and correcting the raw images for the effect of Gibb's ringing further improved intra-subject variability in all maps in the gray (11%) and white matter (10%). Combining Gibb's ringing correction and bias field correction using acquired B1+ maps provides excellent stability of the 7-min MPM sequence with 1.6 mm resolution suitable for the clinical routine.
| S-EPMC7750476 | biostudies-literature
Project description:PURPOSE:Diffusion spectrum imaging (DSI) provides us non-invasively and robustly with anatomical details of brain microstructure. To achieve sufficient angular resolution, DSI requires a large number of q-space samples, leading to long acquisition times. This need is mitigated here by combining the beneficial properties of Radial q-space sampling for DSI with a Multi-Echo Stimulated Echo Sequence (MESTIM). METHODS:Full 2D k-spaces for each of several q-space samples, along the same radially outward line in q-space, are acquired in one readout train with one spin and three stimulated echoes. RF flip angles are carefully chosen to distribute spin magnetization over the echoes and the DSI reconstruction is adapted to account for differences in diffusion time among echoes. RESULTS:Individual datasets and bootstrapped reproducibility analysis demonstrate image quality and SNR of the more-than-twofold-accelerated RDSI MESTIM sequence. Orientation distribution functions (ODF) and tractography results benefit from the longer diffusion times of the latter echoes in the echo train. CONCLUSION:A MESTIM sequence can be used to shorten RDSI acquisition times significantly without loss of image or ODF quality. Further acceleration is possible by combination with simultaneous multi-slice techniques. Magn Reson Med 79:306-316, 2018. © 2017 International Society for Magnetic Resonance in Medicine.
| S-EPMC5623607 | biostudies-literature
Project description:We designed an end-to-end dual-branch residual network architecture that inputs a low-resolution (LR) depth map and a corresponding high-resolution (HR) color image separately into the two branches, and outputs an HR depth map through a multi-scale, channel-wise feature extraction, interaction, and upsampling. Each branch of this network contains several residual levels at different scales, and each level comprises multiple residual groups composed of several residual blocks. A short-skip connection in every residual block and a long-skip connection in each residual group or level allow for low-frequency information to be bypassed while the main network focuses on learning high-frequency information. High-frequency information learned by each residual block in the color image branch is input into the corresponding residual block in the depth map branch, and this kind of channel-wise feature supplement and fusion can not only help the depth map branch to alleviate blur in details like edges, but also introduce some depth artifacts to feature maps. To avoid the above introduced artifacts, the channel interaction fuses the feature maps using weights referring to the channel attention mechanism. The parallel multi-scale network architecture with channel interaction for feature guidance is the main contribution of our work and experiments show that our proposed method had a better performance in terms of accuracy compared with other methods.
| S-EPMC7146598 | biostudies-literature
Project description:Peridotite carbonation represents a critical step within the long-term carbon cycle by sequestering volatile CO2 in solid carbonate. This has been proposed as one potential pathway to mitigate the effects of greenhouse gas release. Most of our current understanding of reaction mechanisms is based on hand specimen and laboratory-scale analyses. Linking laboratory-scale observations to field scale processes remains challenging. Here we present the first geophysical characterization of serpentinite carbonation across scales ranging from km to sub-mm by combining aeromagnetic observations, outcrop- and thin section-scale magnetic mapping. At all scales, magnetic anomalies coherently change across reaction fronts separating assemblages indicative of incipient, intermittent, and final reaction progress. The abundance of magnetic minerals correlates with reaction progress, causing amplitude and wavelength variations in associated magnetic anomalies. This correlation represents a foundation for characterizing the extent and degree of in situ ultramafic rock carbonation in space and time.
| S-EPMC5709373 | biostudies-other
Project description:We propose a novel multi-level dilated residual neural network, an extension of the classical U-Net architecture, for biomedical image segmentation. U-Net is the most popular deep neural architecture for biomedical image segmentation, however, despite being state-of-the-art, the model has a few limitations. In this study, we suggest replacing convolutional blocks of the classical U-Net with multi-level dilated residual blocks, resulting in enhanced learning capability. We also propose to incorporate a non-linear multi-level residual blocks into skip connections to reduce the semantic gap and to restore the information lost when concatenating features from encoder to decoder units. We evaluate the proposed approach on five publicly available biomedical datasets with different imaging modalities, including electron microscopy, magnetic resonance imaging, histopathology, and dermoscopy, each with its own segmentation challenges. The proposed approach consistently outperforms the classical U-Net by 2%, 3%, 6%, 8%, and 14% relative improvements in dice coefficient, respectively for magnetic resonance imaging, dermoscopy, histopathology, cell nuclei microscopy, and electron microscopy modalities. The visual assessments of the segmentation results further show that the proposed approach is robust against outliers and preserves better continuity in boundaries compared to the classical U-Net and its variant, MultiResUNet.
| S-EPMC8266898 | biostudies-literature
Project description:In this paper, we demonstrate the feasibility and performance of deep residual neural networks for volumetric segmentation of irreversibly damaged brain tissue lesions on T1-weighted MRI scans for chronic stroke patients. A total of 239 T1-weighted MRI scans of chronic ischemic stroke patients from a public dataset were retrospectively analyzed by 3D deep convolutional segmentation models with residual learning, using a novel zoom-in&out strategy. Dice similarity coefficient (DSC), average symmetric surface distance (ASSD), and Hausdorff distance (HD) of the identified lesions were measured by using manual tracing of lesions as the reference standard. Bootstrapping was employed for all metrics to estimate 95% confidence intervals. The models were assessed on a test set of 31 scans. The average DSC was 0.64 (0.51-0.76) with a median of 0.78. ASSD and HD were 3.6 mm (1.7-6.2 mm) and 20.4 mm (10.0-33.3 mm), respectively. The latest deep learning architecture and techniques were applied with 3D segmentation on MRI scans and demonstrated effectiveness for volumetric segmentation of chronic ischemic stroke lesions.
| S-EPMC7281812 | biostudies-literature