scholarly journals Lung Cancer Segmentation With Transfer Learning: Usefulness of a Pretrained Model Constructed From an Artificial Dataset Generated Using a Generative Adversarial Network

2021 ◽  
Vol 4 ◽  
Author(s):  
Mizuho Nishio ◽  
Koji Fujimoto ◽  
Hidetoshi Matsuo ◽  
Chisako Muramatsu ◽  
Ryo Sakamoto ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Transfer Learning ◽  
Graph Cut ◽  
Dice Similarity Coefficient ◽  
Generative Adversarial Network ◽  
Lung Cancers ◽  
Artificial Dataset ◽  
Adversarial Network ◽  
The Mean ◽  
Public Datasets

Purpose: The purpose of this study was to develop and evaluate lung cancer segmentation with a pretrained model and transfer learning. The pretrained model was constructed from an artificial dataset generated using a generative adversarial network (GAN).Materials and Methods: Three public datasets containing images of lung nodules/lung cancers were used: LUNA16 dataset, Decathlon lung dataset, and NSCLC radiogenomics. The LUNA16 dataset was used to generate an artificial dataset for lung cancer segmentation with the help of the GAN and 3D graph cut. Pretrained models were then constructed from the artificial dataset. Subsequently, the main segmentation model was constructed from the pretrained models and the Decathlon lung dataset. Finally, the NSCLC radiogenomics dataset was used to evaluate the main segmentation model. The Dice similarity coefficient (DSC) was used as a metric to evaluate the segmentation performance.Results: The mean DSC for the NSCLC radiogenomics dataset improved overall when using the pretrained models. At maximum, the mean DSC was 0.09 higher with the pretrained model than that without it.Conclusion: The proposed method comprising an artificial dataset and a pretrained model can improve lung cancer segmentation as confirmed in terms of the DSC metric. Moreover, the construction of the artificial dataset for the segmentation using the GAN and 3D graph cut was found to be feasible.

scholarly journals Classification of Space Objects by Using Deep Learning with Micro-Doppler Signature Images

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4365
Author(s):  
Kwangyong Jung ◽  
Jae-In Lee ◽  
Nammoon Kim ◽  
Sunjin Oh ◽  
Dong-Wook Seo
Keyword(s):  
Transfer Learning ◽  
Data Augmentation ◽  
Doppler Frequency ◽  
Extraction Methods ◽  
Classification Performance ◽  
Reconstruction Method ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Space Objects ◽  
Target Characteristics

Radar target classification is an important task in the missile defense system. State-of-the-art studies using micro-doppler frequency have been conducted to classify the space object targets. However, existing studies rely highly on feature extraction methods. Therefore, the generalization performance of the classifier is limited and there is room for improvement. Recently, to improve the classification performance, the popular approaches are to build a convolutional neural network (CNN) architecture with the help of transfer learning and use the generative adversarial network (GAN) to increase the training datasets. However, these methods still have drawbacks. First, they use only one feature to train the network. Therefore, the existing methods cannot guarantee that the classifier learns more robust target characteristics. Second, it is difficult to obtain large amounts of data that accurately mimic real-world target features by performing data augmentation via GAN instead of simulation. To mitigate the above problem, we propose a transfer learning-based parallel network with the spectrogram and the cadence velocity diagram (CVD) as the inputs. In addition, we obtain an EM simulation-based dataset. The radar-received signal is simulated according to a variety of dynamics using the concept of shooting and bouncing rays with relative aspect angles rather than the scattering center reconstruction method. Our proposed model is evaluated on our generated dataset. The proposed method achieved about 0.01 to 0.39% higher accuracy than the pre-trained networks with a single input feature.

scholarly journals CDL-GAN: Contrastive Distance Learning Generative Adversarial Network for Image Generation

2021 ◽  
Vol 11 (4) ◽  
pp. 1380
Author(s):  
Yingbo Zhou ◽  
Pengcheng Zhao ◽  
Weiqin Tong ◽  
Yongxin Zhu
Keyword(s):  
Distance Learning ◽  
Feature Learning ◽  
Image Synthesis ◽  
Image Feature ◽  
Generative Adversarial Networks ◽  
Image Generation ◽  
Generative Adversarial Network ◽  
Feature Representations ◽  
Adversarial Network ◽  
Public Datasets

While Generative Adversarial Networks (GANs) have shown promising performance in image generation, they suffer from numerous issues such as mode collapse and training instability. To stabilize GAN training and improve image synthesis quality with diversity, we propose a simple yet effective approach as Contrastive Distance Learning GAN (CDL-GAN) in this paper. Specifically, we add Consistent Contrastive Distance (CoCD) and Characteristic Contrastive Distance (ChCD) into a principled framework to improve GAN performance. The CoCD explicitly maximizes the ratio of the distance between generated images and the increment between noise vectors to strengthen image feature learning for the generator. The ChCD measures the sampling distance of the encoded images in Euler space to boost feature representations for the discriminator. We model the framework by employing Siamese Network as a module into GANs without any modification on the backbone. Both qualitative and quantitative experiments conducted on three public datasets demonstrate the effectiveness of our method.

scholarly journals Improvement of Multiparametric MR Image Segmentation by Augmenting the Data With Generative Adversarial Networks for Glioma Patients

2021 ◽  
Vol 14 ◽  
Author(s):  
Eric Nathan Carver ◽  
Zhenzhen Dai ◽  
Evan Liang ◽  
James Snyder ◽  
Ning Wen
Keyword(s):  
Medical Image ◽  
Medical Image Analysis ◽  
Model Performance ◽  
Image Data ◽  
Generative Adversarial Networks ◽  
Dice Similarity Coefficient ◽  
Generative Adversarial Network ◽  
Post Contrast ◽  
Adversarial Network ◽  
Fluid Attenuated Inversion Recovery

Every year thousands of patients are diagnosed with a glioma, a type of malignant brain tumor. MRI plays an essential role in the diagnosis and treatment assessment of these patients. Neural networks show great potential to aid physicians in the medical image analysis. This study investigated the creation of synthetic brain T1-weighted (T1), post-contrast T1-weighted (T1CE), T2-weighted (T2), and T2 Fluid Attenuated Inversion Recovery (Flair) MR images. These synthetic MR (synMR) images were assessed quantitatively with four metrics. The synMR images were also assessed qualitatively by an authoring physician with notions that synMR possessed realism in its portrayal of structural boundaries but struggled to accurately depict tumor heterogeneity. Additionally, this study investigated the synMR images created by generative adversarial network (GAN) to overcome the lack of annotated medical image data in training U-Nets to segment enhancing tumor, whole tumor, and tumor core regions on gliomas. Multiple two-dimensional (2D) U-Nets were trained with original BraTS data and differing subsets of the synMR images. Dice similarity coefficient (DSC) was used as the loss function during training as well a quantitative metric. Additionally, Hausdorff Distance 95% CI (HD) was used to judge the quality of the contours created by these U-Nets. The model performance was improved in both DSC and HD when incorporating synMR in the training set. In summary, this study showed the ability to generate high quality Flair, T2, T1, and T1CE synMR images using GAN. Using synMR images showed encouraging results to improve the U-Net segmentation performance and shows potential to address the scarcity of annotated medical images.

Cast suppression in radiographs by generative adversarial networks

2021 ◽  
Author(s):  
Franko Hržić ◽  
Ivana Žužić ◽  
Sebastian Tschauner ◽  
Ivan Štajduhar
Keyword(s):  
Software Tool ◽  
Generative Adversarial Networks ◽  
X Rays ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
The Mean ◽  
Radiology Image

Abstract Injured extremities commonly need to be immobilized by casts to allow proper healing. We propose a method to suppress cast superimpositions in pediatric wrist radiographs based on the cycle generative adversarial network (CycleGAN) model. We retrospectively reviewed unpaired pediatric wrist radiographs (n = 9672) and sampled them into 2 equal groups, with and without cast. The test subset consisted of 718 radiographs with cast. We evaluated different quadratic input sizes (256, 512, and 1024 pixels) for U-Net and ResNet-based CycleGAN architectures in cast suppression, quantitatively and qualitatively. The mean age was 11 ± 3 years in images containing cast (n = 4836), and 11 ± 4 years in castless samples (n = 4836). A total of 5956 X-rays had been done in males and 3716 in females. A U-Net 512 CycleGAN performed best (P ≤ .001). CycleGAN models successfully suppressed casts in pediatric wrist radiographs, allowing the development of a related software tool for radiology image viewers.

scholarly journals Presentation Attack Face Image Generation Based on a Deep Generative Adversarial Network

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 1810
Author(s):  
Dat Tien Nguyen ◽  
Tuyen Danh Pham ◽  
Ganbayar Batchuluun ◽  
Kyoung Jun Noh ◽  
Kang Ryoung Park
Keyword(s):  
Recognition Task ◽  
Recognition System ◽  
Attack Detection ◽  
Image Generation ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Face Images ◽  
Problem Presentation ◽  
Recognition Systems ◽  
Public Datasets

Although face-based biometric recognition systems have been widely used in many applications, this type of recognition method is still vulnerable to presentation attacks, which use fake samples to deceive the recognition system. To overcome this problem, presentation attack detection (PAD) methods for face recognition systems (face-PAD), which aim to classify real and presentation attack face images before performing a recognition task, have been developed. However, the performance of PAD systems is limited and biased due to the lack of presentation attack images for training PAD systems. In this paper, we propose a method for artificially generating presentation attack face images by learning the characteristics of real and presentation attack images using a few captured images. As a result, our proposed method helps save time in collecting presentation attack samples for training PAD systems and possibly enhance the performance of PAD systems. Our study is the first attempt to generate PA face images for PAD system based on CycleGAN network, a deep-learning-based framework for image generation. In addition, we propose a new measurement method to evaluate the quality of generated PA images based on a face-PAD system. Through experiments with two public datasets (CASIA and Replay-mobile), we show that the generated face images can capture the characteristics of presentation attack images, making them usable as captured presentation attack samples for PAD system training.

Deep semi-supervised generative adversarial fault diagnostics of rolling element bearings

2019 ◽  
Vol 19 (2) ◽  
pp. 390-411 ◽  
Author(s):  
David Benjamin Verstraete ◽  
Enrique López Droguett ◽  
Viviana Meruane ◽  
Mohammad Modarres ◽  
Andrés Ferrada
Keyword(s):  
Multidimensional Data ◽  
Data Streaming ◽  
Rolling Element Bearings ◽  
Fault Diagnostics ◽  
Generative Adversarial Network ◽  
Vibration Data ◽  
Adversarial Network ◽  
Multidimensional Datasets ◽  
Rolling Element ◽  
Public Datasets

With the availability of cheaper multisensor suites, one has access to massive and multidimensional datasets that can and should be used for fault diagnosis. However, from a time, resource, engineering, and computational perspective, it is often cost prohibitive to label all the data streaming into a database in the context of big machinery data, that is, massive multidimensional data. Therefore, this article proposes both a fully unsupervised and a semi-supervised deep learning enabled generative adversarial network-based methodology for fault diagnostics. Two public datasets of vibration data from rolling element bearings are used to evaluate the performance of the proposed methodology for fault diagnostics. The results indicate that the proposed methodology is a promising approach for both unsupervised and semi-supervised fault diagnostics.

scholarly journals Deep Att-ResGAN: A Retinal Vessel Segmentation Network for Color Fundus Images

2021 ◽  
Vol 38 (5) ◽  
pp. 1309-1317
Author(s):  
Jie Zhao ◽  
Qianjin Feng
Keyword(s):  
Retinal Vessel ◽  
Vessel Segmentation ◽  
Original Image ◽  
Generative Adversarial Network ◽  
Low Contrast ◽  
Adversarial Network ◽  
Vessel Structure ◽  
Retinal Vessel Segmentation ◽  
Vessel Extraction ◽  
Public Datasets

Retinal vessel segmentation plays a significant role in the diagnosis and treatment of ophthalmological diseases. Recent studies have proved that deep learning can effectively segment the retinal vessel structure. However, the existing methods have difficulty in segmenting thin vessels, especially when the original image contains lesions. Based on generative adversarial network (GAN), this paper proposes a deep network with residual module and attention module (Deep Att-ResGAN). The network consists of four identical subnetworks. The output of each subnetwork is imported to the next subnetwork as contextual features that guide the segmentation. Firstly, the problems of the original image, namely, low contrast, uneven illumination, and data insufficiency, were solved through image enhancement and preprocessing. Next, an improved U-Net was adopted to serve as the generator, which stacks the residual and attention modules. These modules optimize the weight of the generator, and enhance the generalizability of the network. Further, the segmentation was refined iteratively by the discriminator, which contributes to the performance of vessel segmentation. Finally, comparative experiments were carried out on two public datasets: Digital Retinal Images for Vessel Extraction (DRIVE) and Structured Analysis of the Retina (STARE). The experimental results show that Deep Att-ResGAN outperformed the equivalent models like U-Net and GAN in most metrics. Our network achieved accuracy of 0.9565 and F1 of 0.829 on DRIVE, and accuracy of 0.9690 and F1 of 0.841 on STARE.

scholarly journals A Transfer Deep Generative Adversarial Network Model to Synthetic Brain CT Generation from MR Images

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Yi Gu ◽  
Qiankun Zheng
Keyword(s):  
Transfer Learning ◽  
Network Model ◽  
Medical Images ◽  
Image Method ◽  
Data Sets ◽  
Generation Process ◽  
Image Generation ◽  
Generative Adversarial Network ◽  
Model Based ◽  
Adversarial Network

Background. The generation of medical images is to convert the existing medical images into one or more required medical images to reduce the time required for sample diagnosis and the radiation to the human body from multiple medical images taken. Therefore, the research on the generation of medical images has important clinical significance. At present, there are many methods in this field. For example, in the image generation process based on the fuzzy C-means (FCM) clustering method, due to the unique clustering idea of FCM, the images generated by this method are uncertain of the attribution of certain organizations. This will cause the details of the image to be unclear, and the resulting image quality is not high. With the development of the generative adversarial network (GAN) model, many improved methods based on the deep GAN model were born. Pix2Pix is a GAN model based on UNet. The core idea of this method is to use paired two types of medical images for deep neural network fitting, thereby generating high-quality images. The disadvantage is that the requirements for data are very strict, and the two types of medical images must be paired one by one. DualGAN model is a network model based on transfer learning. The model cuts the 3D image into multiple 2D slices, simulates each slice, and merges the generated results. The disadvantage is that every time an image is generated, bar-shaped “shadows” will be generated in the three-dimensional image. Method/Material. To solve the above problems and ensure the quality of image generation, this paper proposes a Dual3D&PatchGAN model based on transfer learning. Since Dual3D&PatchGAN is set based on transfer learning, there is no need for one-to-one paired data sets, only two types of medical image data sets are needed, which has important practical significance for applications. This model can eliminate the bar-shaped “shadows” produced by DualGAN’s generated images and can also perform two-way conversion of the two types of images. Results. From the multiple evaluation indicators of the experimental results, it can be analyzed that Dual3D&PatchGAN is more suitable for the generation of medical images than other models, and its generation effect is better.

Sign in / Sign up

Export Citation Format

Share Document