Arbitrary Reduction of MRI Inter-slice Spacing Using Hierarchical Feature Conditional Diffusion

• URL: http://arxiv.org/abs/2304.07756v3
• Date: Fri, 15 Sep 2023 11:46:48 GMT
• Title: Arbitrary Reduction of MRI Inter-slice Spacing Using Hierarchical Feature Conditional Diffusion
• Authors: Xin Wang, Zhenrong Shen, Zhiyun Song, Sheng Wang, Mengjun Liu, Lichi Zhang, Kai Xuan, Qian Wang
• Abstract summary: Super-resolution techniques can reduce the inter-slice spacing of 2D scanned MR images, facilitating the downstream visual experience and computer-aided diagnosis. Most existing super-resolution methods are trained at a fixed scaling ratio, which is inconvenient in clinical settings where MR scanning may have varying inter-slice spacings. We propose Hierarchical Feature Conditional Diffusion (HiFi-Diff) for arbitrary reduction of MR inter-slice spacing.
• Score: 13.979654208364948
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Magnetic resonance (MR) images collected in 2D scanning protocols typically have large inter-slice spacing, resulting in high in-plane resolution but reduced through-plane resolution. Super-resolution techniques can reduce the inter-slice spacing of 2D scanned MR images, facilitating the downstream visual experience and computer-aided diagnosis. However, most existing super-resolution methods are trained at a fixed scaling ratio, which is inconvenient in clinical settings where MR scanning may have varying inter-slice spacings. To solve this issue, we propose Hierarchical Feature Conditional Diffusion (HiFi-Diff)} for arbitrary reduction of MR inter-slice spacing. Given two adjacent MR slices and the relative positional offset, HiFi-Diff can iteratively convert a Gaussian noise map into any desired in-between MR slice. Furthermore, to enable fine-grained conditioning, the Hierarchical Feature Extraction (HiFE) module is proposed to hierarchically extract conditional features and conduct element-wise modulation. Our experimental results on the publicly available HCP-1200 dataset demonstrate the high-fidelity super-resolution capability of HiFi-Diff and its efficacy in enhancing downstream segmentation performance.

Related papers

• Learning Two-factor Representation for Magnetic Resonance Image Super-resolution [1.294284364022674]
  We propose a novel method for MR image super-resolution based on two-factor representation. Specifically, we factorize intensity signals into a linear combination of learnable basis and coefficient factors. Our method achieves state-of-the-art performance, providing superior visual fidelity and robustness.
  arXiv  Detail & Related papers  (2024-09-15T13:32:24Z)
• QMambaBSR: Burst Image Super-Resolution with Query State Space Model [55.56075874424194]
  Burst super-resolution aims to reconstruct high-resolution images with higher quality and richer details by fusing the sub-pixel information from multiple burst low-resolution frames. In BusrtSR, the key challenge lies in extracting the base frame's content complementary sub-pixel details while simultaneously suppressing high-frequency noise disturbance. We introduce a novel Query Mamba Burst Super-Resolution (QMambaBSR) network, which incorporates a Query State Space Model (QSSM) and Adaptive Up-sampling module (AdaUp)
  arXiv  Detail & Related papers  (2024-08-16T11:15:29Z)
• Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning [49.197385954021456]
  In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for visualization and subsequent analysis tasks. To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated. Most current solutions require a substantial number of paired high-resolution and low-resolution images for supervised training, which are typically unavailable in real-world scenarios.
  arXiv  Detail & Related papers  (2024-06-10T02:20:26Z)
• WIA-LD2ND: Wavelet-based Image Alignment for Self-supervised Low-Dose CT Denoising [74.14134385961775]
  We introduce a novel self-supervised CT image denoising method called WIA-LD2ND, only using NDCT data. WIA-LD2ND comprises two modules: Wavelet-based Image Alignment (WIA) and Frequency-Aware Multi-scale Loss (FAM)
  arXiv  Detail & Related papers  (2024-03-18T11:20:11Z)
• SuperMask: Generating High-resolution object masks from multi-view, unaligned low-resolution MRIs [0.8074019565026543]
  High-resolution isotropic MRIs are rare and typical MRIs are anisotropic, with the out-of-plane dimension having a much lower resolution. We propose a weakly-supervised deep learning-based solution to generate high-resolution masks from multiple low-resolution images.
  arXiv  Detail & Related papers  (2023-03-13T23:09:51Z)
• Flexible Alignment Super-Resolution Network for Multi-Contrast MRI [7.727046305845654]
  Super-Resolution plays a crucial role in preprocessing the low-resolution images for more precise medical analysis. We propose the Flexible Alignment Super-Resolution Network (FASR-Net) for multi-contrast magnetic resonance images Super-Resolution.
  arXiv  Detail & Related papers  (2022-10-07T11:07:20Z)
• Deep filter bank regression for super-resolution of anisotropic MR brain images [18.41979609846356]
  In 2D multi-slice magnetic resonance (MR) acquisition, the through-plane signals are typically of lower resolution than the in-plane signals. Super-resolution (SR) methods aim to recover the underlying high-resolution volume, but the estimated high-frequency information is implicit via end-to-end data-driven training. We propose a two-stage approach to approximate the completion of a perfect reconstruction filter bank corresponding to the anisotropic acquisition of a particular scan.
  arXiv  Detail & Related papers  (2022-09-06T16:05:19Z)
• Spatial Attention-based Implicit Neural Representation for Arbitrary Reduction of MRI Slice Spacing [17.16588480746507]
  We propose a Spatial Attention-based Implicit Neural Representation (SA-INR) network for arbitrary reduction of MR inter-slice spacing. The SA-INR can reconstruct the MR image with arbitrary inter-slice spacing by continuously sampling the coordinates in 3D space. We evaluate our method on the public HCP-1200 dataset and the clinical knee MR dataset to demonstrate its superiority over other existing methods.
  arXiv  Detail & Related papers  (2022-05-23T14:36:59Z)
• Cross-Modality High-Frequency Transformer for MR Image Super-Resolution [100.50972513285598]
  We build an early effort to build a Transformer-based MR image super-resolution framework. We consider two-fold domain priors including the high-frequency structure prior and the inter-modality context prior. We establish a novel Transformer architecture, called Cross-modality high-frequency Transformer (Cohf-T), to introduce such priors into super-resolving the low-resolution images.
  arXiv  Detail & Related papers  (2022-03-29T07:56:55Z)
• Hyperspectral-Multispectral Image Fusion with Weighted LASSO [68.04032419397677]
  We propose an approach for fusing hyperspectral and multispectral images to provide high-quality hyperspectral output. We demonstrate that the proposed sparse fusion and reconstruction provides quantitatively superior results when compared to existing methods on publicly available images.
  arXiv  Detail & Related papers  (2020-03-15T23:07:56Z)
• Multifold Acceleration of Diffusion MRI via Slice-Interleaved Diffusion Encoding (SIDE) [50.65891535040752]
  We propose a diffusion encoding scheme, called Slice-Interleaved Diffusion. SIDE, that interleaves each diffusion-weighted (DW) image volume with slices encoded with different diffusion gradients. We also present a method based on deep learning for effective reconstruction of DW images from the highly slice-undersampled data.
  arXiv  Detail & Related papers  (2020-02-25T14:48:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.