Channel-Attention U-Net: Channel Attention Mechanism for Semantic Segmentation of Esophagus and Esophageal Cancer

Abstract

The effective segmentation of esophagus and esophagus tumors from Computed Tomography (CT) images can meaningfully assist doctors in the diagnosis and treatment of esophageal cancer patients. However, problems such as the small proportion of esophageal region in CT images and the irregular shape of esophagus will make the diagnosis difficult. In practical applications, not all esophagus and esophageal cancer morphology can be included in the training set, so the generalization ability of the model is very important. These are the difficulties in segmenting the esophagus and esophageal cancer. Since some adjacent tissues and organs of the esophagus are visually close to esophagus and esophageal cancer, how to ensure that the network can extract effective distinguishing features has become the focus of research. In this paper, a novel U-Net structure ─ Channel-attention U-Net is proposed to segment esophagus and esophagus cancer from CT slices. This novel network combines a Channel Attention Module (CAM) that can distinguish esophagus and surrounding tissues by emphasizing and inhibiting channel feature and Cross-level Feature Fusion Module (CFFM) which is utilized to strengthen the generalization ability of the network by using high-level features to weight low-level features. Because the high-level features represent specific organizational information, and the low-level features represent the characteristics of detailed information such as edges and contours, the network can learn specific detailed features of a definite organization. In addition, in order to locate the esophageal region better, a 3D semi-automatic method for segmenting esophagus and esophageal cancer is proposed. The proposed network is trained using 46,400 CT pictures as the training set and divides 11,600 CT images from the dataset at a ratio of 0.2 as the validation set. Finally, 7,250 CT images were used as the test set to test the performance of the network. The experimental results show that the IoU value of our network can reach 0.625, the dice value is 0.732 and Hausdorff distance is 3.193. INDEX TERMS Esophageal cancer, channel attention mechanism, deep learning, computed tomography (CT).

Esophagus Segmentation in CT Images via Spatial Attention Network and STAPLE Algorithm

“…Several studies focus on solving the problem of esophagus segmentation [ 4 , 5 , 6 , 7 , 8 ]. A model FCN [ 4 ] is used for segmentation of esophagus.…”

“…The Channel Attention mechanism is employed inside the method [ 6 ] to distinguish the esophagus and surrounding area by emphasizing and inhibiting channel features. This method integrated a Channel Attention Module (CAM) and Cross-level Feature Fusion Module (CFFM) into a deep learning model to strengthen the generalization ability of the network by employing high-level features to low-level features.…”

“…The proposed method aims to support the specialist or the medical doctors in radiotherapy treatment planning. In recent years there has been quite a lot of research focusing on the field of esophagus segmentation [ 4 , 5 , 6 , 7 , 8 ]. However, most of these methods ignore the spatial information from organs.…”

Adaptive Adversarial Latent Space for Novelty Detection

“…propose a general attention framework which integrates spatial attention and spatial attention. Huang et al [37]. combine channel attention and UNet, which apply attention mechanism in skip-connection.…”

Affective EEG-Based Person Identification Using Channel Attention Convolutional Neural Dense Connection Network

“…HEADIT uses the experimental paradigm of audio stimulation to stimulate the emotions of each state. Be able to effectively PI based on emotional EEG signals, this paper proposes a deep learning method based on the channel attention mechanism (CA) [19] convolutional neural dense connection network (DCNN) [20] for emotional EEG of PI.…”