Large-Kernel Attention for 3D Medical Image Segmentation

07/19/2022
by   Hao Li, et al.
12

Automatic segmentation of multiple organs and tumors from 3D medical images such as magnetic resonance imaging (MRI) and computed tomography (CT) scans using deep learning methods can aid in diagnosing and treating cancer. However, organs often overlap and are complexly connected, characterized by extensive anatomical variation and low contrast. In addition, the diversity of tumor shape, location, and appearance, coupled with the dominance of background voxels, makes accurate 3D medical image segmentation difficult. In this paper, a novel large-kernel (LK) attention module is proposed to address these problems to achieve accurate multi-organ segmentation and tumor segmentation. The advantages of convolution and self-attention are combined in the proposed LK attention module, including local contextual information, long-range dependence, and channel adaptation. The module also decomposes the LK convolution to optimize the computational cost and can be easily incorporated into FCNs such as U-Net. Comprehensive ablation experiments demonstrated the feasibility of convolutional decomposition and explored the most efficient and effective network design. Among them, the best Mid-type LK attention-based U-Net network was evaluated on CT-ORG and BraTS 2020 datasets, achieving state-of-the-art segmentation performance. The performance improvement due to the proposed LK attention module was also statistically validated.

READ FULL TEXT

page 15

page 16

research
03/10/2021

U-Net Transformer: Self and Cross Attention for Medical Image Segmentation

Medical image segmentation remains particularly challenging for complex ...
research
12/16/2020

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

Multi-organ segmentation is one of most successful applications of deep ...
research
08/15/2018

Holographic Visualisation of Radiology Data and Automated Machine Learning-based Medical Image Segmentation

Within this thesis we propose a platform for combining Augmented Reality...
research
05/25/2022

Structure Unbiased Adversarial Model for Medical Image Segmentation

Generative models have been widely proposed in image recognition to gene...
research
06/11/2019

PAN: Projective Adversarial Network for Medical Image Segmentation

Adversarial learning has been proven to be effective for capturing long-...
research
04/08/2022

Multimodal Multi-Head Convolutional Attention with Various Kernel Sizes for Medical Image Super-Resolution

Super-resolving medical images can help physicians in providing more acc...
research
11/04/2020

Covariance Self-Attention Dual Path UNet for Rectal Tumor Segmentation

Deep learning algorithms are preferable for rectal tumor segmentation. H...

Please sign up or login with your details

Forgot password? Click here to reset