scholarly journals Realistic Hair Simulator for Skin lesion Images Using Conditional Generative Adversarial Network

2018 ◽  
Author(s):  
Mohamed Attia ◽  
Mohammed Hossny ◽  
Hailing Zhou ◽  
Anosha Yazdabadi ◽  
Hamed Asadi ◽  
...  
Keyword(s):  
Skin Lesion ◽  
Similarity Index ◽  
Ground Truth ◽  
Structural Similarity ◽  
Image Synthesis ◽  
Superior Performance ◽  
Hair Removal ◽  
L1 Norm ◽  
Generative Adversarial Network ◽  
L2 Norm

Automated skin lesion analysis is one of the trending fields that has gained attention among the dermatologists and healthcare practitioners. Skin lesion restoration is an essential preprocessing step for lesion enhancements for accurate automated analysis and diagnosis. Digital hair removal is a non-invasive method for image enhancement by solving the hair-occlusion artefact in previously captured images. Several hair removal methods were proposed for skin delineation and removal. However, manual annotation is one of the main challenges that hinder the validation of these proposed methods on a large number of images or using benchmarking datasets for comparison purposes. In the presented work, we propose a realistic hair simulator based on context-aware image synthesis using image-to-image translation techniques via conditional adversarial generative networks for generation of different hair occlusions in skin images, along with the ground-truth mask for hair location. Besides, we explored using three loss functions including L1-norm, L2-norm and structural similarity index (SSIM) to maximise the synthesis quality. For quantitatively evaluate the realism of image synthesis, the t-SNE feature mapping and Bland-Altman test are employed as objective metrics. Experimental results show the superior performance of our proposed method compared to previous methods for hair synthesis with plausible colours and preserving the integrity of the lesion texture.

Dictionary Learning With Convolutional Structure for Seismic Data Denoising and Interpolation

Geophysics ◽  
2021 ◽  
pp. 1-102
Author(s):  
Murad Almadani ◽  
Umair bin Waheed ◽  
Mudassir Masood ◽  
Yangkang Chen
Keyword(s):  
Dictionary Learning ◽  
Seismic Data ◽  
Matching Pursuit ◽  
Random Noise ◽  
Similarity Index ◽  
Structural Similarity ◽  
Superior Performance ◽  
Full Data ◽  
Noisy Input ◽  
L2 Norm

Seismic data inevitably suffers from random noise and missing traces in field acquisition. This limits the utilization of seismic data for subsequent imaging or inversion applications. Recently, dictionary learning has gained remarkable success in seismic data denoising and interpolation. Variants of the patch-based learning technique, such as the K-SVD algorithm, have been shown to improve denoising and interpolation performance compared to the analytic transform-based methods. However, patch-based learning algorithms work on overlapping patches of data and do not take the full data into account during reconstruction. By contrast, the Convolutional Sparse Coding (CSC) model treats signals globally and, therefore, has shown superior performance over patch-based methods in several image processing applications. In consequence, we test the use of CSC model for seismic data denoising and interpolation. In particular, we use the Local Block Coordinate Descent (LoBCoD) algorithm to reconstruct missing traces and clean seismic data from noisy input. The denoising and interpolation performance of the LoBCoD algorithm has been compared with that of K-SVD and Orthogonal Matching Pursuit (OMP) algorithms using synthetic and field data examples. We use three quality measures to test the denoising accuracy: the peak signal-to-noise ratio (PSNR), the relative L2-norm of the error (RLNE), and the structural similarity index (SSIM). We find that LoBCoD performs better than K-SVD and OMP for all test cases in improving PSNR and SSIM, and in reducing RLNE. These observations suggest enormous potential of the CSC model in seismic data denoising and interpolation applications.

scholarly journals GPR B-Scan Image Denoising via Multi-Scale Convolutional Autoencoder with Data Augmentation

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1269
Author(s):  
Jiabin Luo ◽  
Wentai Lei ◽  
Feifei Hou ◽  
Chenghao Wang ◽  
Qiang Ren ◽  
...  
Keyword(s):  
Image Denoising ◽  
Data Augmentation ◽  
Noise Suppression ◽  
Random Noise ◽  
Similarity Index ◽  
Structural Similarity ◽  
Training Dataset ◽  
Generative Adversarial Network ◽  
Multi Scale ◽  
Convolutional Autoencoder

Ground-penetrating radar (GPR), as a non-invasive instrument, has been widely used in civil engineering. In GPR B-scan images, there may exist random noise due to the influence of the environment and equipment hardware, which complicates the interpretability of the useful information. Many methods have been proposed to eliminate or suppress the random noise. However, the existing methods have an unsatisfactory denoising effect when the image is severely contaminated by random noise. This paper proposes a multi-scale convolutional autoencoder (MCAE) to denoise GPR data. At the same time, to solve the problem of training dataset insufficiency, we designed the data augmentation strategy, Wasserstein generative adversarial network (WGAN), to increase the training dataset of MCAE. Experimental results conducted on both simulated, generated, and field datasets demonstrated that the proposed scheme has promising performance for image denoising. In terms of three indexes: the peak signal-to-noise ratio (PSNR), the time cost, and the structural similarity index (SSIM), the proposed scheme can achieve better performance of random noise suppression compared with the state-of-the-art competing methods (e.g., CAE, BM3D, WNNM).

scholarly journals Single Image Super-Resolution: Depthwise Separable Convolution Super-Resolution Generative Adversarial Network

2020 ◽  
Vol 10 (1) ◽  
pp. 375 ◽  
Author(s):  
Zetao Jiang ◽  
Yongsong Huang ◽  
Lirui Hu
Keyword(s):  
Similarity Index ◽  
Super Resolution ◽  
Structural Similarity ◽  
Image Features ◽  
Single Image ◽  
Generative Adversarial Network ◽  
Visual Evaluation ◽  
Adversarial Network ◽  
Image Super Resolution ◽  
Single Image Super Resolution

The super-resolution generative adversarial network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied by unpleasant artifacts. To further enhance the visual quality, we propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The method is based on depthwise separable convolution super-resolution generative adversarial network (DSCSRGAN). A new depthwise separable convolution dense block (DSC Dense Block) was designed for the generator network, which improved the ability to represent and extract image features, while greatly reducing the total amount of parameters. For the discriminator network, the batch normalization (BN) layer was discarded, and the problem of artifacts was reduced. A frequency energy similarity loss function was designed to constrain the generator network to generate better super-resolution images. Experiments on several different datasets showed that the peak signal-to-noise ratio (PSNR) was improved by more than 3 dB, structural similarity index (SSIM) was increased by 16%, and the total parameter was reduced to 42.8% compared with the original model. Combining various objective indicators and subjective visual evaluation, the algorithm was shown to generate richer image details, clearer texture, and lower complexity.

A compensating total variation image denoising model combining L1 and L2 norm

2020 ◽  
pp. 002072092092330
Author(s):  
Liqiong Zhang ◽  
Min Li ◽  
Xiaohua Qiu
Keyword(s):  
Image Denoising ◽  
Total Variation ◽  
Structural Information ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Structural Similarity ◽  
Isotropic Diffusion ◽  
Model Combining ◽  
L2 Norm ◽  
Staircase Effect

To overcome the “staircase effect” while preserving the structural information such as image edges and textures quickly and effectively, we propose a compensating total variation image denoising model combining L1 and L2 norm. A new compensating regular term is designed, which can perform anisotropic and isotropic diffusion in image denoising, thus making up for insufficient diffusion in the total variation model. The algorithm first uses local standard deviation to distinguish neighborhood types. Then, the anisotropic diffusion based on L1 norm plays the role of edge protection in the strong edge region. The anisotropic and the isotropic diffusion simultaneously exist in the smooth region, so that the weak textures can be protected while overcoming the “staircase effect” effectively. The simulation experiments show that this method can effectively improve the peak signal-to-noise ratio and obtain the higher structural similarity index and the shorter running time.

scholarly journals High-fidelity fast volumetric brain MRI using a hybrid denoising generative adversarial network (HDnGAN)

2021 ◽  
Author(s):  
Ziyu Li ◽  
Qiyuan Tian ◽  
Chanon Ngamsombat ◽  
Samuel Cartmell ◽  
John Conklin ◽  
...  
Keyword(s):  
Parallel Imaging ◽  
Mean Squared Error ◽  
Brain Mri ◽  
Similarity Index ◽  
Image Synthesis ◽  
Image Sharpness ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Significant Difference ◽  
Multiple Sclerosis Patients

Purpose: To improve the signal-to-noise ratio (SNR) of highly accelerated volumetric MRI while preserve realistic textures using a generative adversarial network (GAN). Methods: A hybrid GAN for denoising entitled "HDnGAN" with a 3D generator and a 2D discriminator was proposed to denoise 3D T2-weighted fluid-attenuated inversion recovery (FLAIR) images acquired in 2.75 minutes (R=3×2) using wave-controlled aliasing in parallel imaging (Wave-CAIPI). HDnGAN was trained on data from 25 multiple sclerosis patients by minimizing a combined mean squared error and adversarial loss with adjustable weight λ. Results were evaluated on eight separate patients by comparing to standard T2-SPACE FLAIR images acquired in 7.25 minutes (R=2×2) using mean absolute error (MAE), peak SNR (PSNR), structural similarity index (SSIM), and VGG perceptual loss, and by two neuroradiologists using a five-point score regarding gray-white matter contrast, sharpness, SNR, lesion conspicuity, and overall quality. Results: HDnGAN (λ=0) produced the lowest MAE, highest PSNR and SSIM. HDnGAN (λ=10-3) produced the lowest VGG loss. In the reader study, HDnGAN (λ=10-3) significantly improved the gray-white contrast and SNR of Wave-CAIPI images, and outperformed BM4D and HDnGAN (λ=0) regarding image sharpness. The overall quality score from HDnGAN (λ=10-3) was significantly higher than those from Wave-CAIPI, BM4D, and HDnGAN (λ=0), with no significant difference compared to standard images. Conclusion: HDnGAN concurrently benefits from improved image synthesis performance of 3D convolution and increased training samples for training the 2D discriminator on limited data. HDnGAN generates images with high SNR and realistic textures, similar to those acquired in longer times and preferred by neuroradiologists.

scholarly journals Optical to Planar X-ray Mouse Image Mapping in Preclinical Nuclear Medicine Using Conditional Adversarial Networks

2021 ◽  
Vol 7 (12) ◽  
pp. 262
Author(s):  
Eleftherios Fysikopoulos ◽  
Maritina Rouchota ◽  
Vasilis Eleftheriadis ◽  
Christina-Anna Gatsiou ◽  
Irinaios Pilatis ◽  
...  
Keyword(s):  
Molecular Imaging ◽  
Performance Metrics ◽  
Ex Vivo ◽  
Imaging Techniques ◽  
Similarity Index ◽  
Zero Point ◽  
Ground Truth ◽  
Generative Adversarial Network ◽  
X Ray ◽  
Photographic Images

In the current work, a pix2pix conditional generative adversarial network has been evaluated as a potential solution for generating adequately accurate synthesized morphological X-ray images by translating standard photographic images of mice. Such an approach will benefit 2D functional molecular imaging techniques, such as planar radioisotope and/or fluorescence/bioluminescence imaging, by providing high-resolution information for anatomical mapping, but not for diagnosis, using conventional photographic sensors. Planar functional imaging offers an efficient alternative to biodistribution ex vivo studies and/or 3D high-end molecular imaging systems since it can be effectively used to track new tracers and study the accumulation from zero point in time post-injection. The superimposition of functional information with an artificially produced X-ray image may enhance overall image information in such systems without added complexity and cost. The network has been trained in 700 input (photography)/ground truth (X-ray) paired mouse images and evaluated using a test dataset composed of 80 photographic images and 80 ground truth X-ray images. Performance metrics such as peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM) and Fréchet inception distance (FID) were used to quantitatively evaluate the proposed approach in the acquired dataset.

scholarly journals Franken-CT: Head and Neck MR-Based Pseudo-CT Synthesis Using Diverse Anatomical Overlapping MR-CT Scans

2021 ◽  
Vol 11 (8) ◽  
pp. 3508
Author(s):  
Pedro Miguel Martinez-Girones ◽  
Javier Vera-Olmos ◽  
Mario Gil-Correa ◽  
Ana Ramos ◽  
Lina Garcia-Cañamaque ◽  
...  
Keyword(s):  
Deep Learning ◽  
Confidence Interval ◽  
Head And Neck ◽  
Similarity Index ◽  
Ground Truth ◽  
Structural Similarity ◽  
Absolute Error ◽  
Ct Scans ◽  
Learning Methods ◽  
Index Measure

Typically, pseudo-Computerized Tomography (CT) synthesis schemes proposed in the literature rely on complete atlases acquired with the same field of view (FOV) as the input volume. However, clinical CTs are usually acquired in a reduced FOV to decrease patient ionization. In this work, we present the Franken-CT approach, showing how the use of a non-parametric atlas composed of diverse anatomical overlapping Magnetic Resonance (MR)-CT scans and deep learning methods based on the U-net architecture enable synthesizing extended head and neck pseudo-CTs. Visual inspection of the results shows the high quality of the pseudo-CT and the robustness of the method, which is able to capture the details of the bone contours despite synthesizing the resulting image from knowledge obtained from images acquired with a completely different FOV. The experimental Zero-Normalized Cross-Correlation (ZNCC) reports 0.9367 ± 0.0138 (mean ± SD) and 95% confidence interval (0.9221, 0.9512); the experimental Mean Absolute Error (MAE) reports 73.9149 ± 9.2101 HU and 95% confidence interval (66.3383, 81.4915); the Structural Similarity Index Measure (SSIM) reports 0.9943 ± 0.0009 and 95% confidence interval (0.9935, 0.9951); and the experimental Dice coefficient for bone tissue reports 0.7051 ± 0.1126 and 95% confidence interval (0.6125, 0.7977). The voxel-by-voxel correlation plot shows an excellent correlation between pseudo-CT and ground-truth CT Hounsfield Units (m = 0.87; adjusted R2 = 0.91; p < 0.001). The Bland–Altman plot shows that the average of the differences is low (−38.6471 ± 199.6100; 95% CI (−429.8827, 352.5884)). This work serves as a proof of concept to demonstrate the great potential of deep learning methods for pseudo-CT synthesis and their great potential using real clinical datasets.

scholarly journals Image Denoising Using a Novel Deep Generative Network with Multiple Target Images and Adaptive Termination Condition

2021 ◽  
Vol 11 (11) ◽  
pp. 4803
Author(s):  
Shiming Chen ◽  
Shaoping Xu ◽  
Xiaoguo Chen ◽  
Fen Li
Keyword(s):  
Image Denoising ◽  
Similarity Index ◽  
Structural Similarity ◽  
Superior Performance ◽  
Natural Image ◽  
Noisy Image ◽  
Multiple Target ◽  
Convolutional Networks ◽  
Training Images ◽  
Image Priors

Image denoising, a classic ill-posed problem, aims to recover a latent image from a noisy measurement. Over the past few decades, a considerable number of denoising methods have been studied extensively. Among these methods, supervised deep convolutional networks have garnered increasing attention, and their superior performance is attributed to their capability to learn realistic image priors from a large amount of paired noisy and clean images. However, if the image to be denoised is significantly different from the training images, it could lead to inferior results, and the networks may even produce hallucinations by using inappropriate image priors to handle an unseen noisy image. Recently, deep image prior (DIP) was proposed, and it overcame this drawback to some extent. The structure of the DIP generator network is capable of capturing the low-level statistics of a natural image using an unsupervised method with no training images other than the image itself. Compared with a supervised denoising model, the unsupervised DIP is more flexible when processing image content that must be denoised. Nevertheless, the denoising performance of DIP is usually inferior to the current supervised learning-based methods using deep convolutional networks, and it is susceptible to the over-fitting problem. To solve these problems, we propose a novel deep generative network with multiple target images and an adaptive termination condition. Specifically, we utilized mainstream denoising methods to generate two clear target images to be used with the original noisy image, enabling better guidance during the convergence process and improving the convergence speed. Moreover, we adopted the noise level estimation (NLE) technique to set a more reasonable adaptive termination condition, which can effectively solve the problem of over-fitting. Extensive experiments demonstrated that, according to the denoising results, the proposed approach significantly outperforms the original DIP method in tests on different databases. Specifically, the average peak signal-to-noise ratio (PSNR) performance of our proposed method on four databases at different noise levels is increased by 1.90 to 4.86 dB compared to the original DIP method. Moreover, our method achieves superior performance against state-of-the-art methods in terms of popular metrics, which include the structural similarity index (SSIM) and feature similarity index measurement (FSIM). Thus, the proposed method lays a good foundation for subsequent image processing tasks, such as target detection and super-resolution.

scholarly journals Modified distance regularized level set evolution for brain ventricles segmentation

2020 ◽  
Vol 3 (1) ◽  
Author(s):  
Thirumagal Jayaraman ◽  
Sravan Reddy M. ◽  
Manjunatha Mahadevappa ◽  
Anup Sadhu ◽  
Pranab Kumar Dutta
Keyword(s):  
Level Set ◽  
Morphological Changes ◽  
Similarity Index ◽  
Neuronal Loss ◽  
Optimization Procedure ◽  
Ground Truth ◽  
Structural Similarity ◽  
Computed Tomography Images ◽  
Level Set Evolution ◽  
The Brain

AbstractNeurodegenerative disorders are commonly characterized by atrophy of the brain which is caused by neuronal loss. Ventricles are one of the prominent structures in the brain; their shape changes, due to their content, the cerebrospinal fluid. Analyzing the morphological changes of ventricles, aids in the diagnosis of atrophy, for which the region of interest needs to be separated from the background. This study presents a modified distance regularized level set evolution segmentation method, incorporating regional intensity information. The proposed method is implemented for segmenting ventricles from brain images for normal and atrophy subjects of magnetic resonance imaging and computed tomography images. Results of the proposed method were compared with ground truth images and produced sensitivity in the range of 65%–90%, specificity in the range of 98%–99%, and accuracy in the range of 95%–98%. Peak signal to noise ratio and structural similarity index were also used as performance measures for determining segmentation accuracy: 95% and 0.95, respectively. The parameters of level set formulation vary for different datasets. An optimization procedure was followed to fine tune parameters. The proposed method was found to be efficient and robust against noisy images. The proposed method is adaptive and multimodal.

scholarly journals Deep Learning Based Super Resolution and Classification Applications for Neonatal Thermal Images

2021 ◽  
Vol 38 (5) ◽  
pp. 1361-1368
Author(s):  
Fatih M. Senalp ◽  
Murat Ceylan
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Thermal Imaging ◽  
Similarity Index ◽  
Super Resolution ◽  
Ground Truth ◽  
Structural Similarity ◽  
Generative Adversarial Networks ◽  
Thermal Camera ◽  
Thermal Images

The thermal camera systems can be used in all kinds of applications that require the detection of heat change, but thermal imaging systems are highly costly systems. In recent years, developments in the field of deep learning have increased the success by obtaining quality results compared to traditional methods. In this paper, thermal images of neonates (healthy - unhealthy) obtained from a high-resolution thermal camera were used and these images were evaluated as high resolution (ground truth) images. Later, these thermal images were downscaled at 1/2, 1/4, 1/8 ratios, and three different datasets consisting of low-resolution images in different sizes were obtained. In this way, super-resolution applications have been carried out on the deep network model developed based on generative adversarial networks (GAN) by using three different datasets. The successful performance of the results was evaluated with PSNR (peak signal to noise ratio) and SSIM (structural similarity index measure). In addition, healthy - unhealthy classification application was carried out by means of a classifier network developed based on convolutional neural networks (CNN) to evaluate the super-resolution images obtained using different datasets. The obtained results show the importance of combining medical thermal imaging with super-resolution methods.

Sign in / Sign up

Export Citation Format

Share Document