mlsanityData to 7 Oct 2026

Tissue-Mixture Entropy-Weighted Reconstruction for Partial-Volume-Aware Brain MRI Super-Resolution

arXiv 2608.26647 ↗First posted 27 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Background and Objectives: Full-image objectives in brain magnetic resonance imaging (MRI) super-resolution (SR) can underweight tissue-transition regions affected by the partial-volume effect (PVE), as these regions occupy a small fraction of the image. Binary boundaries further provide only a discrete approximation of continuous tissue mixtures within a voxel. Methods: We propose Anatomy-Guided Gaussian-Parameter Warping with PVE-Balanced Reconstruction (AGW-PBR), combining a low-resolution (LR)-only reconstruction backbone with a PVE-aware training objective. The backbone uses LR-derived anatomical guidance, soft latent assignment, and bounded residual warping. Quality-controlled tissue fractions are converted into tissue-mixture entropy to spatially weight reconstruction within validated PVE support. PVE sidecars are used only during training, while inference requires only the LR image. Downstream utility is further evaluated through zero-shot transfer to whole-tumor segmentation on BraTS2023. Results: AGW-PBR improves reconstruction across 2x and 4x SR on IXI and achieves the lowest normalized gradient-vector reconstruction error at both CSF--GM and GM--WM interfaces at 4x. Ablation studies verify the contributions of PVE-aware weighting and soft latent assignment. The PVE-free AGW backbone also maintains strong performance on fastMRI. On BraTS2023, AGW-PBR achieves competitive whole-tumor Dice and the lowest HD95 under direct zero-shot transfer. Conclusions:AGW-PBR improves brain MRI SR while preserving tissue-transition information relevant to downstream analysis. The results support tissue-mixture entropy as an effective supervision signal for partial-volume-aware MRI reconstruction.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 38 references that are in the map. First posted on arXiv 27 Aug 2026.

Builds on

18 of 38 references.

References · 18

  1. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  3. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  4. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  5. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  6. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  7. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 360
  8. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 216
  9. 2021Local Texture Estimator for Implicit Representation Functioncited by 126
  10. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 69
  11. 2021An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural Representationcited by 47
  12. 2019Multi-Contrast Super-Resolution MRI Through a Progressive Networkcited by 45
6 more
  1. 2021Multi-Contrast MRI Super-Resolution via a Multi-Stage Integration Networkcited by 42
  2. 2024GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolutioncited by 32
  3. 2022Cross-Modality High-Frequency Transformer for MR Image Super-Resolutioncited by 20
  4. 2025MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shiftingcited by 10
  5. 2024SuperFormer: Volumetric Transformer Architectures for MRI Super-Resolutioncited by 8
  6. 2022Spatial Attention-based Implicit Neural Representation for Arbitrary Reduction of MRI Slice Spacingcited by 6

Built on by

Not cited yet.