Region Attention Transformer for Medical Image Restoration

TL;DR

This paper introduces a Region Attention Transformer (RAT) that uses semantic region partitioning via SAM to improve medical image restoration by focusing attention within meaningful regions, reducing interference from irrelevant areas.

Contribution

The novel R-MSA mechanism with dynamic semantic region partitioning and the focal region loss enhance the effectiveness of Transformers in medical image restoration tasks.

Findings

RAT outperforms existing methods in PET image synthesis.

RAT improves denoising in CT images.

RAT achieves superior super-resolution in pathological images.

Abstract

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 (\text{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 \href{https://github.com/Yaziwel/Region-Attention-Transformer-for-Medical-Image-Restoration.git}{https://github.com/RAT}.