scholarly journals Multi-Scale and Multi-Branch Convolutional Neural Network for Retinal Image Segmentation

Symmetry ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 365
Author(s):  
Yun Jiang ◽  
Wenhuan Liu ◽  
Chao Wu ◽  
Huixiao Yao
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Convolutional Neural Network ◽  
Retinal Image ◽  
Spatial Information ◽  
Multi Scale ◽  
Segmentation Methods ◽  
Feature Information ◽  
The Impact ◽  
Retinal Image Segmentation

The accurate segmentation of retinal images is a basic step in screening for retinopathy and glaucoma. Most existing retinal image segmentation methods have insufficient feature information extraction. They are susceptible to the impact of the lesion area and poor image quality, resulting in the poor recovery of contextual information. This also causes the segmentation results of the model to be noisy and low in accuracy. Therefore, this paper proposes a multi-scale and multi-branch convolutional neural network model (multi-scale and multi-branch network (MSMB-Net)) for retinal image segmentation. The model uses atrous convolution with different expansion rates and skip connections to reduce the loss of feature information. Receiving domains of different sizes captures global context information. The model fully integrates shallow and deep semantic information and retains rich spatial information. The network embeds an improved attention mechanism to obtain more detailed information, which can improve the accuracy of segmentation. Finally, the method of this paper was validated on the fundus vascular datasets, DRIVE, STARE and CHASE datasets, with accuracies/F1 of 0.9708/0.8320, 0.9753/0.8469 and 0.9767/0.8190, respectively. The effectiveness of the method in this paper was further validated on the optic disc visual cup DRISHTI-GS1 dataset with an accuracy/F1 of 0.9985/0.9770. Experimental results show that, compared with existing retinal image segmentation methods, our proposed method has good segmentation performance in all four benchmark tests.

scholarly journals SEMANTIC SEGMENTATION OF AERIAL IMAGERY VIA MULTI-SCALE SHUFFLING CONVOLUTIONAL NEURAL NETWORKS WITH DEEP SUPERVISION

2018 ◽  
Vol IV-1 ◽  
pp. 29-36 ◽  
Author(s):  
K. Chen ◽  
M. Weinmann ◽  
X. Sun ◽  
M. Yan ◽  
S. Hinz ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Semantic Segmentation ◽  
Aerial Imagery ◽  
Geometric Features ◽  
Feature Maps ◽  
Multi Scale ◽  
Intermediate Layers ◽  
Segmentation Task ◽  
The Impact

<p><strong>Abstract.</strong> In this paper, we address the semantic segmentation of aerial imagery based on the use of multi-modal data given in the form of true orthophotos and the corresponding Digital Surface Models (DSMs). We present the Deeply-supervised Shuffling Convolutional Neural Network (DSCNN) representing a multi-scale extension of the Shuffling Convolutional Neural Network (SCNN) with deep supervision. Thereby, we take the advantage of the SCNN involving the shuffling operator to effectively upsample feature maps and then fuse multiscale features derived from the intermediate layers of the SCNN, which results in the Multi-scale Shuffling Convolutional Neural Network (MSCNN). Based on the MSCNN, we derive the DSCNN by introducing additional losses into the intermediate layers of the MSCNN. In addition, we investigate the impact of using different sets of hand-crafted radiometric and geometric features derived from the true orthophotos and the DSMs on the semantic segmentation task. For performance evaluation, we use a commonly used benchmark dataset. The achieved results reveal that both multi-scale fusion and deep supervision contribute to an improvement in performance. Furthermore, the use of a diversity of hand-crafted radiometric and geometric features as input for the DSCNN does not provide the best numerical results, but smoother and improved detections for several objects.</p>

A deep fully residual convolutional neural network for segmentation in EM images

2020 ◽  
Vol 18 (03) ◽  
pp. 2050007
Author(s):  
Juanjuan He ◽  
Song Xiang ◽  
Ziqi Zhu
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Convolutional Neural Network ◽  
Medical Image ◽  
Spatial Information ◽  
State Of The Art ◽  
Ct Images ◽  
Medical Image Segmentation ◽  
Post Process ◽  
Proposed Model

In standard U-net, researchers only use long skip connections to skip features from the encoding path to the decoding path in order to recover spatial information loss during downsampling. However, it would result in gradient vanishing and limit the depth of the network. To address this issue, we propose a novel deep fully residual convolutional neural network that combines the U-net with the ResNet for medical image segmentation. By applying short skip connections, this new extension of U-net decreases the amount of parameters compared to the standard U-net, although the depth of the layer is increased. We evaluate the performance of the proposed model and other state-of-the-art models on the Electron Microscopy (EM) images dataset and the Computed Tomography (CT) images dataset. The result shows that our model achieves competitive accuracy on the EM benchmark without any further post-process. Moreover, the performance of image segmentation on CT images of the lungs is improved in contrast to the standard U-net.

scholarly journals Deep Convolutional Neural Network With a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor

2021 ◽  
Vol 15 ◽  
Author(s):  
Xueqin He ◽  
Wenjie Xu ◽  
Jane Yang ◽  
Jianyao Mao ◽  
Sifang Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Brain Tumor ◽  
Brain Tumors ◽  
Convolutional Neural Network ◽  
Feature Fusion ◽  
Deep Convolutional Neural Networks ◽  
Multi Scale ◽  
Mri Brain ◽  
Feature Information

As a non-invasive, low-cost medical imaging technology, magnetic resonance imaging (MRI) has become an important tool for brain tumor diagnosis. Many scholars have carried out some related researches on MRI brain tumor segmentation based on deep convolutional neural networks, and have achieved good performance. However, due to the large spatial and structural variability of brain tumors and low image contrast, the segmentation of MRI brain tumors is challenging. Deep convolutional neural networks often lead to the loss of low-level details as the network structure deepens, and they cannot effectively utilize the multi-scale feature information. Therefore, a deep convolutional neural network with a multi-scale attention feature fusion module (MAFF-ResUNet) is proposed to address them. The MAFF-ResUNet consists of a U-Net with residual connections and a MAFF module. The combination of residual connections and skip connections fully retain low-level detailed information and improve the global feature extraction capability of the encoding block. Besides, the MAFF module selectively extracts useful information from the multi-scale hybrid feature map based on the attention mechanism to optimize the features of each layer and makes full use of the complementary feature information of different scales. The experimental results on the BraTs 2019 MRI dataset show that the MAFF-ResUNet can learn the edge structure of brain tumors better and achieve high accuracy.

scholarly journals Combined with the residual and multi-scale method for Chinese thermal power system record text recognition

2019 ◽  
Vol 23 (5 Part A) ◽  
pp. 2631-2640
Author(s):  
Jun Liu ◽  
Wei Li ◽  
Zhuang Du
Keyword(s):  
Neural Network ◽  
Power System ◽  
Convolutional Neural Network ◽  
Thermal Power ◽  
Image Data ◽  
Text Recognition ◽  
Data Set ◽  
Multi Scale ◽  
Thermal Power System ◽  
Feature Information

Aiming at the problem that the recognition accuracy based on convolutional neural network of thermal power system record text is not high, a method of thermal power system record text recognition based on residual and multi-scale feature combination was proposed and implemented. Combined with the residual, a new network is designed to replace the traditional convolutional neural network and improve the feature extraction ability of the network. The 1 ? 1 convolution core was used to increase the network depth and reduce the parameters instead of the 3 ? 3 convolution core. The network order of each layer in residual block was adjusted so that the network representation ability can be improved. Combining feature information of different scales and retaining more vertical feature information, the classification accuracy of the network is improved. Experiments on the self-built image data set of thermal power system records show that the proposed network model improves the accuracy by 11% compared with convolutional recurrent neural network, and has better robustness to image distortion and blurring.

Sign in / Sign up

Export Citation Format

Share Document