CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation

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/HiLabgit/CA-Net

Trilateral Attention Network for Real-Time Cardiac Region Segmentation

“…Other recent methods for echocardiography segmentation include Res-U [21] and CA-Net [29]. In this section, we compare the proposed network to recent segmentation models [21], [29] for echocardiography segmentation. Table 3 provides a performance comparison of TaNet and SOTA segmentation models using our IVC and PLAX datasets.…”

Cross-Modality Coherent Registration of Whole Mouse Brains

“…Our method is further improved by deep learning. Previously, DNN approaches have achieved great success in biomedical image segmentation 50,51 , segmentation-induced registration 52 and intra-modality registration 53,54 . However, cross-modality bioimaging registration remains challenging for DNNs due to the large scale of the problem, the difficulties in generating sufficient training data for supervised networks 55,56 and in designing effective similarity loss function for unsupervised networks 57,58 .…”

PCXRNet: Condense attention block and Multiconvolution spatial attention block for Pneumonia Chest X-Ray detection

“…In recent years, the attention mechanism has been widely applied in computer vision tasks and achieved remarkable achievements [33] [34] [35]. Given different channels of feature maps in traditional CNNs contains much redundant information, the attention module assigns lower weights to useless information and higher weights to helpful information, enhancing representation capacity and improving classification performance without increasing the depth of the deep learning network.…”