Dataset Information

Robust single-shot acquisition of high resolution whole brain ASL images by combining time-dependent 2D CAPIRINHA sampling with spatio-temporal TGV reconstruction.

ABSTRACT: For ASL perfusion imaging in clinical settings the current guidelines recommends pseudo-continuous arterial spin labeling with segmented 3D readout. This combination achieves the best signal to noise ratio with reasonable resolution but is prone to motion artifacts due to the segmented readout. Motion robust single-shot 3D acquisitions suffer from image blurring due to the T2 decay of the sampled signals during the long readout. To tackle this problem, we propose an accelerated 3D-GRASE sequence with a time-dependent 2D-CAIPIRINHA sampling pattern. This has several advantages: First, the single-shot echo trains are shortened by the acceleration factor; Second, the temporal incoherence between measurements is increased; And third, the coil sensitivity maps can be estimated directly from the averaged k-space data. To obtain improved perfusion images from the undersampled time series, we developed a variational image reconstruction approach employing spatio-temporal total-generalized-variation (TGV) regularization. The proposed ASL-TGV method reduced the total acquisition time, improved the motion robustness of 3D ASL data, and the image quality of the cerebral blood flow (CBF) maps compared to those by a standard segmented approach. An evaluation was performed on 5 healthy subjects including intentional movement for 2 subjects. Single-shot whole brain CBF-maps with high resolution 3.1?×?3.1?×?3 mm and image quality can be acquired in 1min 46sec. Additionally high quality CBF- and arterial transit time (ATT) -maps from single-shot multi-post-labeling delay (PLD) data can be gained with the proposed method. This method may improve the robustness of 3D ASL in clinical settings, and may be applied for perfusion fMRI.

SUBMITTER: Spann SM

PROVIDER: S-EPMC6980903 | biostudies-literature | 2020 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Robust single-shot acquisition of high resolution whole brain ASL images by combining time-dependent 2D CAPIRINHA sampling with spatio-temporal TGV reconstruction.

Spann Stefan M SM Shao Xingfeng X Wang Danny Jj DJ Aigner Christoph S CS Schloegl Matthias M Bredies Kristian K Stollberger Rudolf R

NeuroImage 20191109

For ASL perfusion imaging in clinical settings the current guidelines recommends pseudo-continuous arterial spin labeling with segmented 3D readout. This combination achieves the best signal to noise ratio with reasonable resolution but is prone to motion artifacts due to the segmented readout. Motion robust single-shot 3D acquisitions suffer from image blurring due to the T2 decay of the sampled signals during the long readout. To tackle this problem, we propose an accelerated 3D-GRASE sequence ...[more]

PMID: 31707191

Similar Datasets

Project description:BackgroundThe automated classification of histological images is crucial for the diagnosis of cancer. The limited availability of well-annotated datasets, especially for rare cancers, poses a significant challenge for deep learning methods due to the small number of relevant images. This has led to the development of few-shot learning approaches, which bear considerable clinical importance, as they are designed to overcome the challenges of data scarcity in deep learning for histological image classification. Traditional methods often ignore the challenges of intraclass diversity and interclass similarities in histological images. To address this, we propose a novel mutual reconstruction network model, aimed at meeting these challenges and improving the few-shot classification performance of histological images.MethodsThe key to our approach is the extraction of subtle and discriminative features. We introduce a feature enhancement module (FEM) and a mutual reconstruction module to increase differences between classes while reducing variance within classes. First, we extract features of support and query images using a feature extractor. These features are then processed by the FEM, which uses a self-attention mechanism for self-reconstruction of features, enhancing the learning of detailed features. These enhanced features are then input into the mutual reconstruction module. This module uses enhanced support features to reconstruct enhanced query features and vice versa. The classification of query samples is based on weighted calculations of the distances between query features and reconstructed query features and between support features and reconstructed support features.ResultsWe extensively evaluated our model using a specially created few-shot histological image dataset. The results showed that in a 5-way 10-shot setup, our model achieved an impressive accuracy of 92.09%. This is a 23.59% improvement in accuracy compared to the model-agnostic meta-learning (MAML) method, which does not focus on fine-grained attributes. In the more challenging, 5-way 1-shot setting, our model also performed well, demonstrating a 18.52% improvement over the ProtoNet, which does not address this challenge. Additional ablation studies indicated the effectiveness and complementary nature of each module and confirmed our method's ability to parse small differences between classes and large variations within classes in histological images. These findings strongly support the superiority of our proposed method in the few-shot classification of histological images.ConclusionsThe mutual reconstruction network provides outstanding performance in the few-shot classification of histological images, successfully overcoming the challenges of similarities between classes and diversity within classes. This marks a significant advancement in the automated classification of histological images.

Project description:Multiple echo-time arterial spin labelling (multi-TE ASL) offers estimation of blood-tissue exchange dynamics by probing the T2 relaxation of the labelled spins. In this study, we provide a recipe for robust assessment of exchange time (Texch) as a proxy measure of blood-brain barrier (BBB) integrity based on a test-retest analysis. This includes a novel scan protocol and an extension of the two-compartment model with an "intra-voxel transit time" (ITT) to address tissue transit effects. With the extended model, we intend to separate the underlying two distinct mechanisms of tissue transit and exchange. The performance of the extended model in comparison with the two-compartment model was evaluated in simulations. Multi-TE ASL sequence with two different bolus durations was used to acquire in vivo data (n = 10). Cerebral blood flow (CBF), arterial transit time (ATT) and Texch were fitted with the two models, and mean grey matter values were compared. Additionally, the extended model also extracted ITT parameter. The test-retest reliability of Texch was assessed for intra-session, inter-session and inter-visit pairs of measurements. Intra-class correlation coefficient (ICC) and within-subject coefficient of variance (CoV) for grey matter were computed to assess the precision of the method. Mean grey matter Texch and ITT values were found to be 227.9 ± 37.9 ms and 310.3 ± 52.9 ms, respectively. Texch estimated by the extended model was 32.6 ± 5.9% lower than the two-compartment model. A significant ICC was observed for all three measures of Texch reliability (P < 0.05). Texch intra-session CoV, inter-session CoV and inter-visit CoV were found to be 6.6%, 7.9%, and 8.4%, respectively. With the described improvements addressing intra-voxel transit effects, multi-TE ASL shows good reproducibility as a non-invasive measure of BBB permeability. These findings offer an encouraging step forward to apply this potential BBB permeability biomarker in clinical research.

Dataset Information

Robust single-shot acquisition of high resolution whole brain ASL images by combining time-dependent 2D CAPIRINHA sampling with spatio-temporal TGV reconstruction.

Publications

Robust single-shot acquisition of high resolution whole brain ASL images by combining time-dependent 2D CAPIRINHA sampling with spatio-temporal TGV reconstruction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets