RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans

Abstract

Automatic extraction of liver and tumor from CT volumes is a challenging task due to their heterogeneous and diffusive shapes. Recently, 2D and 3D deep convolutional neural networks have become popular in medical image segmentation tasks because of the utilization of large labeled datasets to learn hierarchical features. However, 3D networks have some drawbacks due to their high cost on computational resources. In this paper, we propose a 3D hybrid residual attention-aware segmentation method, named RA-UNet, to precisely extract the liver volume of interests (VOI) and segment tumors from the liver VOI. The proposed network has a basic architecture as a 3D U-Net which extracts contextual information combining low-level feature maps with high-level ones. Attention modules are stacked so that the attention-aware features change adaptively as the network goes "very deep" and this is made possible by residual learning. This is the first work that an attention residual mechanism is used to process medical volumetric images. We evaluated our framework on the public MICCAI 2017 Liver Tumor Segmentation dataset and the 3DIRCADb dataset. The results show that our architecture outperforms other state-of-the-art methods. We also extend our RA-UNet to brain tumor segmentation on the BraTS2018 and BraTS2017 datasets, and the results indicate that RA-UNet achieves good performance on a brain tumor segmentation task as well.

References in corpus (20)

• Adam: A Method for Stochastic Optimization
• A Survey on Deep Learning in Medical Image Analysis
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Attention U-Net: Learning Where to Look for the Pancreas
• Fully Convolutional Networks for Semantic Segmentation
• DUNet: A deformable network for retinal vessel segmentation
• 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
• RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans
• Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images
• Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation
• 3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study
• 3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes
• H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes
• Attention-Gated Networks for Improving Ultrasound Scan Plane Detection
• Automatic Liver Lesion Detection using Cascaded Deep Residual Networks
• Hierarchical Convolutional-Deconvolutional Neural Networks for Automatic Liver and Tumor Segmentation
• 2D-Densely Connected Convolution Neural Networks for automatic Liver and Tumor Segmentation
• 3D Densely Convolutional Networks for Volumetric Segmentation
• Detection-aided liver lesion segmentation using deep learning
• Segmentation of Liver Lesions with Reduced Complexity Deep Models

Cited by in corpus (17)

• RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans
• DA-TransUNet: Integrating Spatial and Channel Dual Attention with Transformer U-Net for Medical Image Segmentation
• UNETR: Transformers for 3D Medical Image Segmentation
• SUNet: Swin Transformer UNet for Image Denoising
• Efficient Medical Image Segmentation Based on Knowledge Distillation
• LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation
• Cell segmentation from telecentric bright-field transmitted light microscopy images using a Residual Attention U-Net: a case study on HeLa line
• Hybrid Cascaded Neural Network for Liver Lesion Segmentation
• EAR-U-Net: EfficientNet and attention-based residual U-Net for automatic liver segmentation in CT
• Multiclass Segmentation using Teeth Attention Modules for Dental X-ray Images
• U-Net Based Architecture for an Improved Multiresolution Segmentation in Medical Images
• Ground-based image deconvolution with Swin Transformer UNet
• SAR-U-Net: squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver segmentation in Computed Tomography
• DAWN: Domain-Adaptive Weakly Supervised Nuclei Segmentation via Cross-Task Interactions
• T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging
• Brain Tumor Segmentation on MRI with Missing Modalities
• Cell image segmentation by Feature Random Enhancement Module