Conference Paper

Resolving to super resolution multi-dimensional diffusion imaging (Super-MUDI)

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Abstract #0103 2021 ISMRM & SMRT Annual Meeting & Exhibition, 15-20 May 2021 in Vancouver, BC, Canada. Resolving to super resolution multi-dimensional diffusion imaging (Super-MUDI) Vishwesh Nath1, Marco Pizzolato2,3, Marco Palombo4, Noemi Gyori4, Kurt G Schilling5, Colin Hansen6, Qi Yang6, Praitayini Kanakaraj6, Bennett A Landman6, Soumick Chatterjee7, Alessandro Sciarra7, Max Duennwald7, Steffen Oeltze-Jafra7, Andreas Nuernberger7, Oliver Speck7, Tomasz Pieciak 8, Marcin Baranek8, Kamil Bartocha8, Dominika Ciupek8, Fabian Bogusz8, Azam Hamidinekoo9, Maryam Afzali 10, Harry Lin4, Danny C Alexander4, Haoyu Lan11, Farshid Sepehrband11, Zifei Liang12, Tung-Yeh Wu13, Ching-Wei Su13, Qian-Hua Wu13, Zi-You Liu13, Yi-Ping Chao13, Enes Albay14, Gozde Unal14, Dmytro Pylypenko13, Xinyu Ye13, Fan Zhang15, and Jana Hutter16 1NVIDIA Corporation, Bethesda, MD, United States, 2Department of Applied Mathematics and Computer Science, Technical University of Denmark, Kongens Lyngby, Denmark, 3École polytechnique fédérale de Lausanne (EPFL), Lausanne, Switzerland, 4CMIC, University College London, London, United Kingdom, 5Institute of Imaging Science, Vanterbilt University, Nashville, TN, United States, 6Department of Computer Science, Vanterbilt University, Nashville, TN, United States, 7Otto von Guericke University, Magdeburg, Germany, 8AGH University of Science and Technology, Krakow, Poland, 9Institute of Cancer Research, London, United Kingdom, 10CUBRIC, Cardiff University, Cardiff, United Kingdom, 11University of Southern California, Los Angeles, CA, United States, 12NYU Langone, New York, NY, United States, 13Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University, Beijing, China, 14Istanbul Technical University, Istanbul, Turkey, 15Harvard Medical School, Boston, MA, United States, 16Centre for Medical Engineering, King's College London, London, United Kingdom Diffusion-weighted magnetic resonance imaging (DW-MRI) is a critical modality that allows characterization of microstructure of the nervous tissue in the human brain. Recent multi-parametric acquisitions expand parameter space to b-values, gradient directions, inversion and echo times. The required long scanning time could be shortened by acquiring at lower resolutions while superesolving the images during post-processing. This work embodies the evaluation of an open challenge where the objective was to upsample multi dimensional data encoding simultaneously T1, T2* and diffusion contrast to the natively acquired voxel resolution from two different down-sampled sets of the data (isotropic down-sampled and anisotropic down-sampled).

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... We propose a deep learning-based method with an endto-end pipeline that learns the mapping of a low resolution 3D MRI to its high resolution counterpart. This is unlike the method proposed by Lin et al. [7] for the same problem, which was not end-to-end, but won second place in the SuperMUDI challenge for MRI super-resolution [16]. ...
... The Super-resolution of Multi-Dimensional Diffusion MRI (Super MUDI) dataset [16] contains the data of four healthy human subjects with ages range between 19 and 46 years. For each subject 1,344 MRI volumes are provided. ...
... Our dataset contains 23 T1 volumes and the corresponding FLAIR volumes of 23 subjects from the dataset [17], and 250 diffusion volumes randomly selected from Super MUDI dataset [16]. As our dataset was very imbalanced, we trained the network using class-balanced softmax cross-entropy loss [18], described as follows: ...
Conference Paper
Full-text available
Capturing high-resolution magnetic resonance (MR) images is a time consuming process, which makes it unsuitable for medical emergencies and pediatric patients. Low-resolution MR imaging, by contrast, is faster than its high-resolution counterpart, but it compromises on fine details necessary for a more precise diagnosis. Super-resolution (SR), when applied to low-resolution MR images, can help increase their utility by synthetically generating high-resolution images with little additional time. In this paper, we present an SR technique for MR images that is based on generative adversarial networks (GANs), which have proven to be quite useful in producing sharp-looking details in SR. We introduce a conditional GAN with perceptual loss, which is conditioned upon the input low-resolution image, which improves the performance for isotropic and anisotropic MRI super-resolution. Clinical Relevance- MR image super-resolution has the potential for improving image acquisition speed to save the time of the clinicians, while guaranteeing high-quality images.
... Coupé et al proposed a super resolution method for diffusion weighted imaging that outperforms traditional methods like trilinear and B-spline interpolation, and showed the potential of their method by illustrating fiber tracking quality in a deterministic tractography experiment with super-resolved images that decrease voxel dimensions from 1.2 mm isotropic to 0.6 mm isotropic and 0.4 mm isotropic and relies on a b0 [29]. Super resolution in dMRI has taken off as a subject of interest in the last half-decade as the topic of the "Resolving to super resolution multi-dimensional diffusion imaging" (Super MUDI) Challenge at MICCAI 2021 [30]. Before implementing super-resolution techniques on dMRI datasets, there is a need to establish if the common problems in connectome harmonization are due to a lack of information that needs to be solved with a super-resolution approach or a fixable issue in the tractography process. ...
Preprint
Full-text available
To date, there has been no comprehensive study characterizing the effect of diffusion-weighted magnetic resonance imaging voxel resolution on the resulting connectome for high resolution subject data. Similarity in results improved with higher resolution, even after initial down-sampling. To ensure robust tractography and connectomes, resample data to 1 mm isotropic resolution.
... 6 Nagyanyómnak 1 Introduction 27 Albay, G. Unal, D. Pylypenko, X. Ye, F. Zhang, J. Hutter (2021). "Resolving to super resolution multi-dimensional di↵usion imaging (Super-MUDI)". ...
Thesis
Today, a plethora of model-based diffusion MRI (dMRI) techniques exist that aim to provide quantitative metrics of cellular-scale tissue properties. In the brain, many of these techniques focus on cylindrical projections such as axons and dendrites. Capturing additional tissue features is challenging, as conventional dMRI measurements have limited sensitivity to different cellular components, and modelling cellular architecture is not trivial in heterogeneous tissues such as grey matter. Additionally, fitting complex non-linear models with traditional techniques can be time-consuming and prone to local minima, which hampers their widespread use. In this thesis, we harness recent advances in measurement technology and modelling efforts to tackle these challenges. We probe the utility of B-tensor encoding, a technique that offers additional sensitivity to tissue microstructure compared to conventional measurements, and observe that B-tensor encoding provides unique contrast in grey matter. Motivated by this and recent work showing that the diffusion signature of soma in grey matter may be captured with spherical compartments, we use B-tensor encoding measurements and a biophysical model to disentangle spherical and cylindrical cellular structures. We map apparent markers of these geometries in healthy human subjects and evaluate the extent to which they may be interpreted as correlates of soma and projections. To ensure fast and robust model fitting, we use supervised machine learning (ML) to estimate parameters. We explore limitations in ML fitting in several microstructure models, including the model developed here, and demonstrate that the choice of training data significantly impacts estimation performance. We highlight that high precision obtained using ML may mask strong biases and that visual assessment of the parameter maps is not sufficient for evaluating the quality of the estimates. We believe that the methods developed in this work provide new insight into the reliability and potential utility of advanced dMRI and ML in microstructure imaging.
... Multiple review papers illustrate pitfalls to be avoided when performing quantitative dMRI analysis and studying the brains connectivity using tractography ( Daducci et al., 2016;Jones, 2010;O'Donnell and Pasternak, 2015;Rheault et al., 2020c ). Research is underway to improve biological specificity to the type of tissue change, by improving the information that is obtained at the acquisition level ( Barakovic et al., 2021a;Henriques et al., 2020;Hutter et al., 2018;Ning et al., 2019;Shemesh et al., 2016;Westin et al., 2016 ), and by proposing advanced mathematical modeling and machine learning techniques ( Nath et al., 2021;Ning et al., 2021;Pizzolato et al., 2020;Wu and Miller, 2017 ). ...
Article
Full-text available
Diffusion magnetic resonance imaging (dMRI) tractography is an advanced imaging technique that enables in vivo reconstruction of the brain’s white matter connections at macro scale. It provides an important tool for quantitative mapping of the brain’s structural connectivity using measures of connectivity or tissue microstructure. Over the last two decades, the study of brain connectivity using dMRI tractography has played a prominent role in the neuroimaging research landscape. In this paper, we provide a high-level overview of how tractography is used to enable quantitative analysis of the brain’s structural connectivity in health and disease. We focus on two types of quantitative analyses of tractography, including: 1) tract-specific analysis that refers to research that is typically hypothesis-driven and studies particular anatomical fiber tracts, and 2) connectome-based analysis that refers to research that is more data-driven and generally studies the structural connectivity of the entire brain. We first provide a review of methodology involved in three main processing steps that are common across most approaches for quantitative analysis of tractography, including methods for tractography correction, segmentation and quantification. For each step, we aim to describe methodological choices, their popularity, and potential pros and cons. We then review studies that have used quantitative tractography approaches to study the brain’s white matter, focusing on applications in neurodevelopment, aging, neurological disorders, mental disorders, and neurosurgery. We conclude that, while there have been considerable advancements in methodological technologies and breadth of applications, there nevertheless remains no consensus about the “best” methodology in quantitative analysis of tractography, and researchers should remain cautious when interpreting results in research and clinical applications.
Preprint
Full-text available
White matter alterations are increasingly implicated in neurological diseases and their progression. International-scale studies use diffusion-weighted magnetic resonance imaging (DW-MRI) to qualitatively identify changes in white matter microstructure and connectivity. Yet, quantitative analysis of DW-MRI data is hindered by inconsistencies stemming from varying acquisition protocols. There is a pressing need to harmonize the preprocessing of DW-MRI datasets to ensure the derivation of robust quantitative diffusion metrics across acquisitions. In the MICCAI-CDMRI 2023 QuantConn challenge, participants were provided raw data from the same individuals collected on the same scanner but with two different acquisitions and tasked with preprocessing the DW-MRI to minimize acquisition differences while retaining biological variation. Submissions are evaluated on the reproducibility and comparability of cross-acquisition bundle-wise microstructure measures, bundle shape features, and connectomics. The key innovations of the QuantConn challenge are that (1) we assess bundles and tractography in the context of harmonization for the first time, (2) we assess connectomics in the context of harmonization for the first time, and (3) we have 10x additional subjects over prior harmonization challenge, MUSHAC and 100x over SuperMUDI. We find that bundle surface area, fractional anisotropy, connectome assortativity, betweenness centrality, edge count, modularity, nodal strength, and participation coefficient measures are most biased by acquisition and that machine learning voxel-wise correction, RISH mapping, and NeSH methods effectively reduce these biases. In addition, microstructure measures AD, MD, RD, bundle length, connectome density, efficiency, and path length are least biased by these acquisition differences.
Article
White matter alterations are increasingly implicated in neurological diseases and their progression. International-scale studies use diffusion-weighted magnetic resonance imaging (DW-MRI) to qualitatively identify changes in white matter microstructure and connectivity. Yet, quantitative analysis of DW-MRI data is hindered by inconsistencies stemming from varying acquisition protocols. Specifically, there is a pressing need to harmonize the preprocessing of DW-MRI datasets to ensure the derivation of robust quantitative diffusion metrics across acquisitions. In the MICCAI-CDMRI 2023 QuantConn challenge, participants were provided raw data from the same individuals collected on the same scanner but with two different acquisitions and tasked with preprocessing the DW-MRI to minimize acquisition differences while retaining biological variation. Harmonized submissions are evaluated on the reproducibility and comparability of cross-acquisition bundlewise microstructure measures, bundle shape features, and connectomics. The key innovations of the QuantConn challenge are that (1) we assess bundles and tractography in the context of harmonization for the first time, (2) we assess connectomics in the context of harmonization for the first time, and (3) we have 10x additional subjects over prior harmonization challenge, MUSHAC and 100x over SuperMUDI. We find that bundle surface area, fractional anisotropy, connectome assortativity, betweenness centrality, edge count, modularity, nodal strength, and participation coefficient measures are most biased by acquisition and that machine learning voxel-wise correction, RISH mapping, and NeSH methods effectively reduce these biases. In addition, microstructure measures AD, MD, RD, bundle length, connectome density, efficiency, and path length are least biased by these acquisition differences. A machine learning approach that learned voxelwise cross-acquisition relationships was the most effective at harmonizing connectomic, microstructure, and macrostructure features, but requires the same subject be scanned at each site co-registered. NeSH, a spatial and angular resampling method, was also effective and has generalizable framework not reliant co-registration. Our code is available at https://github.com/nancynewlin-masi/QuantConn/</a
Article
Full-text available
We propose a patch-based singular value shrinkage method for diffusion magnetic resonance image estimation targeted at low signal to noise ratio and accelerated acquisitions. It operates on the complex data resulting from a sensitivity encoding reconstruction, where asymptotically optimal signal recovery guarantees can be attained by modeling the noise propagation in the reconstruction and subsequently simulating or calculating the limit singular value spectrum. Simple strategies are presented to deal with phase inconsistencies and optimize patch construction. The pertinence of our contributions is quantitatively validated on synthetic data, an in vivo adult example, and challenging neonatal and fetal cohorts. Our methodology is compared with related approaches, which generally operate on magnitude-only data and use data-based noise level estimation and singular value truncation. Visual examples are provided to illustrate effectiveness in generating denoised and debiased diffusion estimates with well preserved spatial and diffusion detail.
Article
Full-text available
Cubic convolution interpolation is a new technique for resampling discrete data. It has a number of desirable features which make it useful for image processing. The technique can be performed efficiently on a digital computer. The cubic convolution interpolation function converges uniformly to the function being interpolated as the sampling increment approaches zero. With the appropriate boundary conditions and constraints on the interpolation kernel, it can be shown that the order of accuracy of the cubic convolution method is between that of linear interpolation and that of cubic splines. A one-dimensional interpolation function is derived in this paper. A separable extension of this algorithm to two dimensions is applied to image data.
Article
Diffusion tensor imaging is often performed by acquiring a series of diffusion-weighted spin-echo echo-planar images with different direction diffusion gradients. A problem of echo-planar images is the geometrical distortions that obtain near junctions between tissues of differing magnetic susceptibility. This results in distorted diffusion-tensor maps. To resolve this we suggest acquiring two images for each diffusion gradient; one with bottom-up and one with top-down traversal of k-space in the phase-encode direction. This achieves the simultaneous goals of providing information on the underlying displacement field and intensity maps with adequate spatial sampling density even in distorted areas. The resulting DT maps exhibit considerably higher geometric fidelity, as assessed by comparison to an image volume acquired using a conventional 3D MR technique.
Article
The techniques available for the interrogation and analysis of neuroimaging data have a large influence in determining the flexibility, sensitivity, and scope of neuroimaging experiments. The development of such methodologies has allowed investigators to address scientific questions that could not previously be answered and, as such, has become an important research area in its own right. In this paper, we present a review of the research carried out by the Analysis Group at the Oxford Centre for Functional MRI of the Brain (FMRIB). This research has focussed on the development of new methodologies for the analysis of both structural and functional magnetic resonance imaging data. The majority of the research laid out in this paper has been implemented as freely available software tools within FMRIB's Software Library (FSL).
Computational Diffusion MRI pp 195-208| Acquiring and Predicting Multidimensional Diffusion (MUDI) Data: An Open Challenge
  • M Pizzolato
(Pizzolato et al 2020) Pizzolato, M et al 2020. "Computational Diffusion MRI pp 195-208| Acquiring and Predicting Multidimensional Diffusion (MUDI) Data: An Open Challenge", LNCS CDMRI 2020