CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation (2020-09-22T00:00:00.000000Z)

TL;DR

This work makes extensive use of multiple attentions in a CNN architecture and proposes a comprehensive attention-based CNN (CA-Net) for more accurate and explainable medical image segmentation that is aware of the most important spatial positions, channels and scales at the same time.

Abstract

Accurate medical image segmentation is essential for diagnosis and treatment planning of diseases. Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they are still challenged by complicated conditions where the segmentation target has large variations of position, shape and scale, and existing CNNs have a poor explainability that limits their application to clinical decisions. In this work, we make extensive use of multiple attentions in a CNN architecture and propose a comprehensive attention-based CNN (CA-Net) for more accurate and explainable medical image segmentation that is aware of the most important spatial positions, channels and scales at the same time. In particular, we first propose a joint spatial attention module to make the network focus more on the foreground region. Then, a novel channel attention module is proposed to adaptively recalibrate channel-wise feature responses and highlight the most relevant feature channels. Also, we propose a scale attention module implicitly emphasizing the most salient feature maps among multiple scales so that the CNN is adaptive to the size of an object. Extensive experiments on skin lesion segmentation from ISIC 2018 and multi-class segmentation of fetal MRI found that our proposed CA-Net significantly improved the average segmentation Dice score from 87.77% to 92.08% for skin lesion, 84.79% to 87.08% for the placenta and 93.20% to 95.88% for the fetal brain respectively compared with U-Net. It reduced the model size to around 15 times smaller with close or even better accuracy compared with state-of-the-art DeepLabv3+. In addition, it has a much higher explainability than existing networks by visualizing the attention weight maps. Our code is available at https://github.com/HiLab-git/CA-Net.

References41 items

Dynamic Convolution: Attention Over Convolution Kernels

Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)

Segmentation and classification in MRI and US fetal imaging: Recent trends and future prospects☆

Explaining Neural Networks Semantically and Quantitatively

Deep Attentional Features for Prostate Segmentation in Ultrasound

Dual Attention Network for Scene Segmentation

Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images

CBAM: Convolutional Block Attention Module

DenseASPP for Semantic Segmentation in Street Scenes

SLSDeep: Skin Lesion Segmentation Based on Dilated Residual and Pyramid Pooling Networks

Autofocus Layer for Semantic Segmentation

Attention U-Net: Learning Where to Look for the Pancreas

Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks

Tell Me Where to Look: Guided Attention Inference Network

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Non-local Neural Networks

Real-time automatic fetal brain extraction in fetal MRI by deep learning

Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning

Squeeze-and-Excitation Networks

Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models

DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation

On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task

Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks

Dilated Residual Networks

Residual Attention Network for Image Classification

A survey on deep learning in medical image analysis

Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning

RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation

Xception: Deep Learning with Depthwise Separable Convolutions

Densely Connected Convolutional Networks

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation

Learning Deep Features for Discriminative Localization

Deep Residual Learning for Image Recognition

Attention to Scale: Scale-Aware Semantic Image Segmentation

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

Striving for Simplicity: The All Convolutional Net

Fully convolutional networks for semantic segmentation