Dictionary Based Super-Resolution for Diffusion MRI

Yoldemir, Burak; Bajammal, Mohammad; Abugharbieh, Rafeef

doi:10.1007/978-3-319-11182-7_18

Cited by 3 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the need to acquire multiple images increases the total imaging time and makes the technique susceptible to motions (11). An alternative SR approach is based on sparse representation (18)(19)(20), but is sensitive to noise and is computationally expansive.…”

Section: Introductionmentioning

confidence: 99%

Mouse brain MR super-resolution using a deep learning network trained with optical imaging data

Liang

Zhang

2023

Front. Radiol.

View full text Add to dashboard Cite

IntroductionThe resolution of magnetic resonance imaging is often limited at the millimeter level due to its inherent signal-to-noise disadvantage compared to other imaging modalities. Super-resolution (SR) of MRI data aims to enhance its resolution and diagnostic value. While deep learning-based SR has shown potential, its applications in MRI remain limited, especially for preclinical MRI, where large high-resolution MRI datasets for training are often lacking.MethodsIn this study, we first used high-resolution mouse brain auto-fluorescence (AF) data acquired using serial two-photon tomography (STPT) to examine the performance of deep learning-based SR for mouse brain images.ResultsWe found that the best SR performance was obtained when the resolutions of training and target data were matched. We then applied the network trained using AF data to MRI data of the mouse brain, and found that the performance of the SR network depended on the tissue contrast presented in the MRI data. Using transfer learning and a limited set of high-resolution mouse brain MRI data, we were able to fine-tune the initial network trained using AF to enhance the resolution of MRI data.DiscussionOur results suggest that deep learning SR networks trained using high-resolution data of a different modality can be applied to MRI data after transfer learning.

show abstract

Section: Introductionmentioning

confidence: 99%

Mouse brain MR super-resolution using a deep learning network trained with optical imaging data

Liang

Zhang

2023

Front. Radiol.

View full text Add to dashboard Cite

show abstract

“…Our experiments on phantom and real HARDI brain data show that it is possible to achieve accurate global HARDI reconstructions with a sparse representation of less than one dictionary atom per voxel, exceeding the theoretical limit of the state of the art in sparse coding. Sparse coding has many important applications like de-noising (Ouyang et al, 2013), dictionary learning (Cheng et al, 2015b) and super-resolution (Yoldemir et al, 2014), and, in particular, applying our joint spatial-angular sparse coding framework within the application of (k, q)-CS will be the subject of future work.…”

Section: Introductionmentioning

confidence: 99%

Joint spatial-angular sparse coding for dMRI with separable dictionaries

Schwab

Vidal

Charon

2018

Medical Image Analysis

View full text Add to dashboard Cite

Diffusion MRI (dMRI) provides the ability to reconstruct neuronal fibers in the brain, in vivo, by measuring water diffusion along angular gradient directions in q-space. High angular resolution diffusion imaging (HARDI) can produce better estimates of fiber orientation than the popularly used diffusion tensor imaging, but the high number of samples needed to estimate diffusivity requires longer patient scan times. To accelerate dMRI, compressed sensing (CS) has been utilized by exploiting a sparse dictionary representation of the data, discovered through sparse coding. The sparser the representation, the fewer samples are needed to reconstruct a high resolution signal with limited information loss, and so an important area of research has focused on finding the sparsest possible representation of dMRI. Current reconstruction methods however, rely on an angular representation per voxel with added spatial regularization, and so, for non-zero signals, one is required to have at least one non-zero coefficient per voxel. This means that the global level of sparsity must be greater than the number of voxels. In contrast, we propose a joint spatial-angular representation of dMRI that will allow us to achieve levels of global sparsity that are below the number of voxels. A major challenge, however, is the computational complexity of solving a global sparse coding problem over large-scale dMRI. In this work, we present novel adaptations of popular sparse coding algorithms that become better suited for solving large-scale problems by exploiting spatial-angular separability. Our experiments show that our method achieves significantly sparser representations of HARDI than is possible by the state of the art.

show abstract

“…Alexander et al [22] implemented a random forest for SR in diffusion MRI with cubic patches and features customized for diffusion tensor images (DTIs). Yoldemir et al [23] applied dictionary learning to diffusion-weighted 3-D images for volumetric SR. Recently, Tanno et al [24] integrated an uncertainty modeling with a 3-D convolutional neural network (CNN) on DTIs.…”

Section: Introductionmentioning

confidence: 99%

Learning from a Handful Volumes: MRI Resolution Enhancement with Volumetric Super-Resolution Forests

Sindel¹,

Breininger²,

Käßer

et al. 2018

2018 25th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) enables 3-D imaging of anatomical structures. However, the acquisition of MR volumes with high spatial resolution leads to long scan times. To this end, we propose volumetric super-resolution forests (VSRF) to enhance MRI resolution retrospectively. Our method learns a locally linear mapping between low-resolution and high-resolution volumetric image patches by employing random forest regression. We customize features suitable for volumetric MRI to train the random forest and propose a median tree ensemble for robust regression. VSRF outperforms state-of-the-art example-based super-resolution in term of image quality and efficiency for model training and inference in different MRI datasets. It is also superior to unsupervised methods with just a handful or even a single volume to assemble training data.

show abstract

Dictionary Based Super-Resolution for Diffusion MRI

Cited by 3 publications

References 22 publications

Mouse brain MR super-resolution using a deep learning network trained with optical imaging data

Mouse brain MR super-resolution using a deep learning network trained with optical imaging data

Joint spatial-angular sparse coding for dMRI with separable dictionaries

Learning from a Handful Volumes: MRI Resolution Enhancement with Volumetric Super-Resolution Forests

Contact Info

Product

Resources

About