DeepAI AI Chat
Log In Sign Up

Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation

by   Hang Zhang, et al.

Recently, 3D medical image reconstruction (MIR) and segmentation (MIS) based on deep neural networks have been developed with promising results, and attention mechanism has been further designed to capture global contextual information for performance enhancement. However, the large size of 3D volume images poses a great computational challenge to traditional attention methods. In this paper, we propose a folded attention (FA) approach to improve the computational efficiency of traditional attention methods on 3D medical images. The main idea is that we apply tensor folding and unfolding operations with four permutations to build four small sub-affinity matrices to approximate the original affinity matrix. Through four consecutive sub-attention modules of FA, each element in the feature tensor can aggregate spatial-channel information from all other elements. Compared to traditional attention methods, with moderate improvement of accuracy, FA can substantially reduce the computational complexity and GPU memory consumption. We demonstrate the superiority of our method on two challenging tasks for 3D MIR and MIS, which are quantitative susceptibility mapping and multiple sclerosis lesion segmentation.


page 5

page 6

page 7


Dynamic Linear Transformer for 3D Biomedical Image Segmentation

Transformer-based neural networks have surpassed promising performance o...

Sparse Spatial Attention Network for Semantic Segmentation

The spatial attention mechanism captures long-range dependencies by aggr...

Interlaced Sparse Self-Attention for Semantic Segmentation

In this paper, we present a so-called interlaced sparse self-attention a...

Patch Network for medical image Segmentation

Accurate and fast segmentation of medical images is clinically essential...

Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation

Multi-organ segmentation is one of most successful applications of deep ...

Spatially Covariant Lesion Segmentation

Compared to natural images, medical images usually show stronger visual ...

MS-DC-UNeXt: An MLP-based Multi-Scale Feature Learning Framework For X-ray Images

The advancement of deep learning theory and infrastructure is crucial in...

Code Repositories


Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation (AAAI'2021)

view repo