scholarly journals Automated Segmentation Method for Low Field 3D Stomach MRI Using Transferred Learning Image Enhancement Network

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Luguang Huang ◽  
Mengbin Li ◽  
Shuiping Gou ◽  
Xiaopeng Zhang ◽  
Kun Jiang
Keyword(s):  
Neural Network ◽  
Image Enhancement ◽  
Field Intensity ◽  
High Field ◽  
Training Data ◽  
Segmentation Method ◽  
Generative Adversarial Network ◽  
Low Field ◽  
Low Field Mri ◽  
High Field Intensity

Accurate segmentation of abdominal organs has always been a difficult problem, especially for organs with cavities. And MRI-guided radiotherapy is particularly attractive for abdominal targets compared with low CT contrast. But in the limit of radiotherapy environment, only low field MRI segmentation can be used for stomach location, tracking, and treatment planning. In clinical applications, the existing 3D segmentation network model is trained by the low field MRI, and the segmentation result cannot be used in radiotherapy plan since the bad segmentation performance. Another way is that historical high field intensity MR images are directly used for data expansion to network learning; there will be a domain shift problem. How to use different domain images to improve the segmentation accuracy of deep neural network? A 3D low field MRI stomach segmentation method based on transfer learning image enhancement is proposed in this paper. In this method, Cycle Generative Adversarial Network (CycleGAN) is used to construct and learn the mapping relationship between high and low field intensity MRI and to overcome domain shift. Then, the image generated by the high field intensity MRI through the CycleGAN network is with transferred information as the extended data. The low field MRI combines these extended datasets to form the training data for training the 3D Res-Unet segmentation network. Furthermore, the convolution layer, batch normalization layer, and Relu layer together were replaced with a residual module to relieve the gradient disappearance of the neural network. The experimental results show that the Dice coefficient is 2.5 percent better than the baseline method. The over segmentation and under segmentation are reduced by 0.7 and 5.5 percent, respectively. And the sensitivity is improved by 6.4 percent.

Deep Learning–based Method for Denoising and Image Enhancement in Low-Field MRI

2021 ◽  
Author(s):  
Dang Bich Thuy Le ◽  
Meredith Sadinski ◽  
Aleksandar Nacev ◽  
Ram Narayanan ◽  
Dinesh Kumar
Keyword(s):  
Deep Learning ◽  
Image Enhancement ◽  
Low Field ◽  
Low Field Mri

scholarly journals Generative Adversarial Network Performance in Low-Dimensional Settings

2021 ◽  
Vol 126 ◽  
Author(s):  
Felix Jimenez ◽  
Amanda Koepke ◽  
Mary Gregg ◽  
Michael Frey
Keyword(s):  
Neural Network ◽  
Network Performance ◽  
Training Data ◽  
High Dimensional ◽  
Generative Adversarial Network ◽  
Low Dimensions ◽  
Target Distribution ◽  
Adversarial Network ◽  
Low Dimensional ◽  
And Training

A generative adversarial network (GAN) is an artificial neural network with a distinctive training architecture, designed to createexamples that faithfully reproduce a target distribution. GANs have recently had particular success in applications involvinghigh-dimensional distributions in areas such as image processing. Little work has been reported for low dimensions, where properties of GANs may be better identified and understood. We studied GAN performance in simulated low-dimensional settings, allowing us totransparently assess effects of target distribution complexity and training data sample size on GAN performance in a simpleexperiment. This experiment revealed two important forms of GAN error, tail underfilling and bridge bias, where the latter is analogousto the tunneling observed in high-dimensional GANs.

scholarly journals Sentiment Analysis Method based on Piecewise Convolutional Neural Network and Generative Adversarial Network

2019 ◽  
Vol 14 (1) ◽  
pp. 7-20 ◽  
Author(s):  
Changshun Du ◽  
Lei Huang
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Convolution Neural Network ◽  
Training Data ◽  
Sentence Structure ◽  
Analysis Model ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Text Sentiment Analysis

Text sentiment analysis is one of the most important tasks in the field of public opinion monitoring, service evaluation and satisfaction analysis under network environments. Compared with the traditional Natural Language Processing analysis tools, convolution neural networks can automatically learn useful features from sentences and improve the performance of the affective analysis model. However, the original convolution neural network model ignores sentence structure information which is very important for text sentiment analysis. In this paper, we add piece-wise pooling to the convolution neural network, which allows the model to obtain the sentence structure. And the main features of different sentences are extracted to analyze the emotional tendencies of the text. At the same time, the user’s feedback involves many different fields, and there is less labeled data. In order to alleviate the sparsity of the data, this paper also uses the generative adversarial network to make common feature extractions, so that the model can obtain the common features associated with emotions in different fields, and improves the model’s Generalization ability with less training data. Experiments on different datasets demonstrate the effectiveness of this method.

scholarly journals SEEK: A Framework of Superpixel Learning with CNN Features for Unsupervised Segmentation

Electronics ◽  
2020 ◽  
Vol 9 (3) ◽  
pp. 383 ◽  
Author(s):  
Talha Ilyas ◽  
Abbas Khan ◽  
Muhammad Umraiz ◽  
Hyongsuk Kim
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Enhancement ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Segmentation Method ◽  
Unsupervised Segmentation ◽  
Segmentation Algorithms ◽  
Salient Features ◽  
The Given

Supervised semantic segmentation algorithms have been a hot area of exploration recently, but now the attention is being drawn towards completely unsupervised semantic segmentation. In an unsupervised framework, neither the targets nor the ground truth labels are provided to the network. That being said, the network is unaware about any class instance or object present in the given data sample. So, we propose a convolutional neural network (CNN) based architecture for unsupervised segmentation. We used the squeeze and excitation network, due to its peculiar ability to capture the features’ interdependencies, which increases the network’s sensitivity to more salient features. We iteratively enable our CNN architecture to learn the target generated by a graph-based segmentation method, while simultaneously preventing our network from falling into the pit of over-segmentation. Along with this CNN architecture, image enhancement and refinement techniques are exploited to improve the segmentation results. Our proposed algorithm produces improved segmented regions that meet the human level segmentation results. In addition, we evaluate our approach using different metrics to show the quantitative outperformance.

CT Image Segmentation of Liver Tumor with Deep Convolutional Neural Network

2021 ◽  
Vol 11 (2) ◽  
pp. 337-344
Author(s):  
Yao Zeng ◽  
Huanhuan Dai
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Automatic Segmentation ◽  
Abdominal Cavity ◽  
Mutual Exclusion ◽  
Image Data ◽  
Deep Convolutional Neural Network ◽  
Training Data ◽  
Segmentation Method ◽  
Segmentation Boundary

The liver is the largest substantial organ in the abdominal cavity of the human body. Its structure is complex, the incidence of vascular abundance is high, and it has been seriously ribbed, human health and life. In this study, an automatic segmentation method based on deep convolutional neural network is proposed. Image data blocks of different sizes are extracted as training data and different network structures are designed, and features are automatically learned to obtain a segmentation structure of the tumor. Secondly, in order to further refine the segmentation boundary, we establish a multi-region segmentation model with region mutual exclusion constraints. The model combines the image grayscale, gradient and prior probability information, and overcomes the problem that the boundary point attribution area caused by boundary blur and regional adhesion is difficult to determine. Finally, the model is solved quickly using the time-invisible multi-phase level set. Compared with the traditional multi-organ segmentation method, this method does not require registration or model initialization. The experimental results show that the model can segment the liver, kidney and spleen quickly and effectively, and the segmentation accuracy reaches the advanced level of current methods.

Evaluation of Magnetic Resonance Imaging Responsiveness in Active Psoriatic Arthritis at Multiple Timepoints during the First 12 Weeks of Antitumor Necrosis Factor Therapy

2015 ◽  
Vol 43 (1) ◽  
pp. 75-80 ◽  
Author(s):  
Marie Feletar ◽  
Stephen Hall ◽  
Paul Bird
Keyword(s):  
Magnetic Resonance Imaging ◽  
Psoriatic Arthritis ◽  
Magnetic Resonance ◽  
High Field ◽  
Early Response ◽  
Resonance Imaging ◽  
Low Field ◽  
Low Field Mri ◽  
Magnetic Resonance Imaging Mri ◽  
Necrosis Factor

Objective.To assess the responsiveness of high- and low-field extremity magnetic resonance imaging (MRI) variables at multiple timepoints in the first 12 weeks post-antitumor necrosis factor (anti-TNF) therapy initiation in patients with psoriatic arthritis (PsA) and active dactylitis.Methods.Twelve patients with active PsA and clinical evidence of dactylitis involving at least 1 digit were recruited. Patients underwent sequential high-field conventional (1.5 Tesla) and extremity low-field MRI (0.2 Tesla) of the affected hand or foot, pre- and postgadolinium at baseline (pre-TNF), 2 weeks (post-TNF), 6 weeks, and 12 weeks. A blinded observer scored all images on 2 occasions using the PsA MRI scoring system.Results.Eleven patients completed the study, but only 6 patients completed all high-field and low-field MRI assessments. MRI scores demonstrated rapid response to TNF inhibition with score reduction in tenosynovitis, synovitis, and osteitis at 2 weeks. Intraobserver reliability was good to excellent for all variables. High-field MRI demonstrated greater sensitivity to tenosynovitis, synovitis, and osteitis and greater responsiveness to change posttreatment. Treatment responses were maintained to 12 weeks.Conclusion.This study demonstrates the use of MRI in detecting early response to biologic therapy. MRI variables of tenosynovitis, synovitis, and osteitis demonstrated responsiveness posttherapy with high-field scores more responsive to change than low-field scores.

Sign in / Sign up

Export Citation Format

Share Document