IREM: High-Resolution Magnetic Resonance Image Reconstruction via Implicit Neural Representation

Wu, Qing; Li, Yuwei; Xu, Lan; Feng, Ruiming; Wei, Hongjiang; Yang, Qing; Yu, Boliang; Liu, Xiaozhao; Yu, Jingyi; Zhang, Yuyao

doi:10.1007/978-3-030-87231-1_7

Cited by 31 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the field of medical imaging, attempts have been made to reconstruct super-resolved volumes from 2D slices using INR. IREM [17] was proposed for super-resolution reconstruction of adult brain MRI from stacks of thick slices, where only the motion between stacks is considered. Inspired by NeRF−−, Yeung et al developed ImplicitVol [18] for 3D ultrasound reconstruction.…”

Section: B Related Workmentioning

confidence: 99%

NeSVoR: Implicit Neural Representation for Slice-to-Volume Reconstruction in MRI

Moyer

Gagoski³

et al. 2023

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Reconstructing 3D MR volumes from multiple motion-corrupted stacks of 2D slices has shown promise in imaging of moving subjects, e.g., fetal MRI. However, existing slice-to-volume reconstruction methods are time-consuming, especially when a high-resolution volume is desired. Moreover, they are still vulnerable to severe subject motion and when image artifacts are present in acquired slices. In this work, we present NeSVoR, a resolution-agnostic slice-to-volume reconstruction method, which models the underlying volume as a continuous function of spatial coordinates with implicit neural representation. To improve robustness to subject motion and other image artifacts, we adopt a continuous and comprehensive slice acquisition model that takes into account rigid inter-slice motion, point spread function, and bias fields. NeSVoR also estimates pixel-wise and slicewise variances of image noise and enables removal of outliers during reconstruction and visualization of uncertainty. Extensive experiments are performed on both simulated and in vivo data to evaluate the proposed method. Results show that NeSVoR achieves state-of-the-art reconstruction quality while providing two to ten-fold acceleration in reconstruction times over the state-of-the-art algorithms.

show abstract

Section: B Related Workmentioning

confidence: 99%

NeSVoR: Implicit Neural Representation for Slice-to-Volume Reconstruction in MRI

Moyer

Gagoski³

et al. 2023

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…While frequency encoder eases the difficulty of training networks, it is considered quite cumbersome. In medical imaging practise [26,28], the size of encoder output is set to 256 or greater. The following network must be wider and deeper to cope with the inflated inputs.…”

Section: Neural Attenuation Fieldsmentioning

confidence: 99%

NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction

Zha

Zhang

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction (Cone Beam Computed Tomography) that requires no external training data. Specifically, the desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. We synthesize projections discretely and train the network by minimizing the error between real and synthesized projections. A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details. This encoder outperforms the commonly used frequency-domain encoder in terms of having higher performance and efficiency, because it exploits the smoothness and sparsity of human organs. Experiments have been conducted on both human organ and phantom datasets. The proposed method achieves state-of-the-art accuracy and spends reasonably short computation time. Code available at https://github.com/Ruyi-Zha/naf_cbct.

show abstract

“…[29] predicted the density value at a 3D spatial coordinate, and was supervised by mapping its value back to the sensor domain. [35] viewed the 2D slice as the samples from 3D continuous function and tried to reconstruct 3D images from the observed tissue anatomy.…”

Section: Medical Imagementioning

confidence: 99%

MIRNF: Medical Image Registration via Neural Fields

Sun¹,

Han²,

Tang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Image registration is widely used in medical image analysis to provide spatial correspondences between two images. Recently learning-based methods utilizing convolutional neural networks (CNNs) have been proposed for solving image registration problems. The learning-based methods tend to be much faster than traditional optimization based methods, but the accuracy improvements gained from the complex CNN-based methods are modest. Here we introduce a new deep-neural net based image registration framework, named MIRNF, which represents the correspondence mapping with a continuous function implemented via Neural Fields. MIRNF outputs either a deformation vector or velocity vector given a 3D coordinate as input. To ensure the mapping is diffeomorphic, the velocity vector output from MIRNF is integrated using the Neural ODE solver to derive the correspondences between two images. Furthermore, we propose a hybrid coordinate sampler along with a cascaded architecture to achieve the highsimilarity mapping performance and low-distortion deformation fields. We conduct experiments on two 3D MR brain scan datasets, showing that our proposed framework provides state-of-art registration performance while maintaining comparable optimization time.

show abstract

IREM: High-Resolution Magnetic Resonance Image Reconstruction via Implicit Neural Representation

Cited by 31 publications

References 19 publications

NeSVoR: Implicit Neural Representation for Slice-to-Volume Reconstruction in MRI

NeSVoR: Implicit Neural Representation for Slice-to-Volume Reconstruction in MRI

NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction

MIRNF: Medical Image Registration via Neural Fields

Contact Info

Product

Resources

About