mlsanityData to 7 Oct 2026

Region Attention Transformer for Medical Image Restoration

arXiv 2407.09268 ↗First posted 12 Jul 2024eess.IV cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Transformer-based methods have demonstrated impressive results in medical image restoration, attributed to the multi-head self-attention (MSA) mechanism in the spatial dimension. However, the majority of existing Transformers conduct attention within fixed and coarsely partitioned regions (e.g. the entire image or fixed patches), resulting in interference from irrelevant regions and fragmentation of continuous image content. To overcome these challenges, we introduce a novel Region Attention Transformer (RAT) that utilizes a region-based multi-head self-attention mechanism (R-MSA). The R-MSA dynamically partitions the input image into non-overlapping semantic regions using the robust Segment Anything Model (SAM) and then performs self-attention within these regions. This region partitioning is more flexible and interpretable, ensuring that only pixels from similar semantic regions complement each other, thereby eliminating interference from irrelevant regions. Moreover, we introduce a focal region loss to guide our model to adaptively focus on recovering high-difficulty regions. Extensive experiments demonstrate the effectiveness of RAT in various medical image restoration tasks, including PET image synthesis, CT image denoising, and pathological image super-resolution. Code is available at hrefhttps://github.com/Yaziwel/Region-Attention-Transformer-for-Medical-Image-Restoration.githttps://github.com/RAT.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 12 Jul 2024.

Builds on

20 of 32 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2023Segment Anythingcited by 8,158
  4. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  6. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  7. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  8. 2022Simple Baselines for Image Restorationcited by 701
  9. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  10. 2022Vision Transformer with Deformable Attentioncited by 293
  11. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  12. 2017Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Losscited by 161
8 more
  1. 2019Explicit Sparse Transformer: Concentrated Attention Through Explicit Selectioncited by 61
  2. 2018Brain MRI Super Resolution Using 3D Deep Densely Connected Neural Networkscited by 46
  3. 2022CTformer: Convolution-free Token2Token Dilated Vision Transformer for Low-dose CT Denoisingcited by 46
  4. 2020EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoisingcited by 26
  5. 2022Spach Transformer: Spatial and Channel-wise Transformer Based on Local and Global Self-attentions for PET Image Denoisingcited by 19
  6. 2016Low-dose CT denoising with convolutional neural networkcited by 18
  7. 20223D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesiscited by 13
  8. 2023DRMC: A Generalist Model with Dynamic Routing for Multi-Center PET Image Synthesiscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025TAT: Task-Adaptive Transformer for All-in-One Medical Image Restorationcited by 3
  2. 2025Leveraging Multiphase CT for Quality Enhancement of Portal Venous CT: Utility for Pancreas Segmentationcited by 0
  3. 2025Pathology Image Restoration via Mixture of Promptscited by 0
  4. 2026MARR: Decoupling Policy, Execution, and Calibration for All-in-One Medical Image Restorationcited by 0
  5. 2026UniH3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restorationcited by 0