scholarly journals Normalization of HE-Stained Histological Images using Cycle Consistent Generative Adversarial Networks

2021 ◽  
Author(s):  
Marlen Runz ◽  
Daniel Rusche ◽  
Martin R Weihrauch ◽  
Jürgen Hesser ◽  
Cleo-Aron Weis
Keyword(s):  
Image Acquisition ◽  
Similarity Measures ◽  
Staining Intensity ◽  
Generative Adversarial Networks ◽  
Target Domain ◽  
Inverse Mapping ◽  
Generative Adversarial Network ◽  
Source Domain ◽  
Adversarial Network ◽  
Histological Images

Abstract Background: Histological images show huge variance (e.g. illumination, color, staining quality) due to differences in image acquisition, tissue processing, staining, etc. The variance can impede many image analyzes such as staining intensity evaluation or classification. Methods to reduce these variances are gathered under the term image normalization. Methods: We present the application of CylceGAN - a cycle consistent Generative Adversarial Network for color normalization in hematoxylin-eosin stained histological images using typical clinical data including variability of internal staining. The network consists of a generator network GB that learns to map an image X from a source domain A to a target domain B, i.e. GB : XA → XB. In addition, a discriminator network DB is trained to distinguish whether an image from domain B is an original or generated one. The same process is applied to another generator-discriminator pair (GA, DA), for the inverse mapping GA : XB → XA. Cycle consistency ensures that the generated image is close to the original image when being mapped backwards (GA(GB(XA)) ≈ XA and vice versa). We validate the CycleGAN approach on a breast cancer challenge and a follicular thyroid carcinoma dataset for various stain variations. We evaluate the quality of the generated images compared to the original images using similarity measures. Results: We present qualitative results of the images generated by our network compared to the original color distributions. Our evaluation shows that by mapping images from a source domain to a target domain, the similarity to original images from the target domain improve up to 96%. We also achieve a high cycle consistency for the inverse mapping by obtaining similarity indices bigger than 0.9. Conclusions: CycleGANs have proven to efficiently normalize HE-stained images. The approach enables to compensate for deviations resulting from image acquisition (e.g. different scanning devices) as well as from tissue staining (e.g. different staining protocols), and thus overcomes the staining variations in images from various institutions. The code is publicly available at https://github.com/m4ln/stainTransfer_CycleGAN_pytorch. The dataset supporting the solutions is available at https://heidata.uni-heidelberg. de/privateurl.xhtml?token=12493b50-1538-4bdf-aca5-03352a1399a8.

scholarly journals Normalization of HE-stained histological images using cycle consistent generative adversarial networks

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Marlen Runz ◽  
Daniel Rusche ◽  
Stefan Schmidt ◽  
Martin R. Weihrauch ◽  
Jürgen Hesser ◽  
...  
Keyword(s):  
Image Acquisition ◽  
Similarity Measures ◽  
Staining Intensity ◽  
Generative Adversarial Networks ◽  
Target Domain ◽  
Inverse Mapping ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Link Type ◽  
Histological Images

Abstract Background Histological images show strong variance (e.g. illumination, color, staining quality) due to differences in image acquisition, tissue processing, staining, etc. This can impede downstream image analysis such as staining intensity evaluation or classification. Methods to reduce these variances are called image normalization techniques. Methods In this paper, we investigate the potential of CycleGAN (cycle consistent Generative Adversarial Network) for color normalization in hematoxylin-eosin stained histological images using daily clinical data with consideration of the variability of internal staining protocol variations. The network consists of a generator network GB that learns to map an image X from a source domain A to a target domain B, i.e. GB:XA→XB. In addition, a discriminator network DB is trained to distinguish whether an image from domain B is real or generated. The same process is applied to another generator-discriminator pair (GA,DA), for the inverse mapping GA:XB→XA. Cycle consistency ensures that a generated image is close to its original when being mapped backwards (GA(GB(XA))≈XA and vice versa). We validate the CycleGAN approach on a breast cancer challenge and a follicular thyroid carcinoma data set for various stain variations. We evaluate the quality of the generated images compared to the original images using similarity measures. In addition, we apply stain normalization on pathological lymph node data from our institute and test the gain from normalization on a ResNet classifier pre-trained on the Camelyon16 data set. Results Qualitative results of the images generated by our network are compared to original color distributions. Our evaluation indicates that by mapping images to a target domain, the similarity training images from that domain improves up to 96%. We also achieve a high cycle consistency for the generator networks by obtaining similarity indices greater than 0.9. When applying the CycleGAN normalization to HE-stain images from our institute the kappa-value of the ResNet-model that is only trained on Camelyon16 data is increased more than 50%. Conclusions CycleGANs have proven to efficiently normalize HE-stained images. The approach compensates for deviations resulting from image acquisition (e.g. different scanning devices) as well as from tissue staining (e.g. different staining protocols), and thus overcomes the staining variations in images from various institutions.The code is publicly available at https://github.com/m4ln/stainTransfer_CycleGAN_pytorch. The data set supporting the solutions is available at 10.11588/data/8LKEZF.

scholarly journals Unified Generative Adversarial Networks for Multidomain Fingerprint Presentation Attack Detection

Entropy ◽  
2021 ◽  
Vol 23 (8) ◽  
pp. 1089
Author(s):  
Soha B. Sandouka ◽  
Yakoub Bazi ◽  
Haikel Alhichri ◽  
Naif Alajlan
Keyword(s):  
Attack Detection ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Source Domain ◽  
The Public ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Biometric Systems ◽  
Security And Reliability ◽  
Presentation Attack Detection

With the rapid growth of fingerprint-based biometric systems, it is essential to ensure the security and reliability of the deployed algorithms. Indeed, the security vulnerability of these systems has been widely recognized. Thus, it is critical to enhance the generalization ability of fingerprint presentation attack detection (PAD) cross-sensor and cross-material settings. In this work, we propose a novel solution for addressing the case of a single source domain (sensor) with large labeled real/fake fingerprint images and multiple target domains (sensors) with only few real images obtained from different sensors. Our aim is to build a model that leverages the limited sample issues in all target domains by transferring knowledge from the source domain. To this end, we train a unified generative adversarial network (UGAN) for multidomain conversion to learn several mappings between all domains. This allows us to generate additional synthetic images for the target domains from the source domain to reduce the distribution shift between fingerprint representations. Then, we train a scale compound network (EfficientNetV2) coupled with multiple head classifiers (one classifier for each domain) using the source domain and the translated images. The outputs of these classifiers are then aggregated using an additional fusion layer with learnable weights. In the experiments, we validate the proposed methodology on the public LivDet2015 dataset. The experimental results show that the proposed method improves the average classification accuracy over twelve classification scenarios from 67.80 to 80.44% after adaptation.

scholarly journals Multi-Source Domain Adaptation for Visual Sentiment Classification

2020 ◽  
Vol 34 (03) ◽  
pp. 2661-2668
Author(s):  
Chuang Lin ◽  
Sicheng Zhao ◽  
Lei Meng ◽  
Tat-Seng Chua
Keyword(s):  
Domain Adaptation ◽  
Sentiment Classification ◽  
Similar Distribution ◽  
Single Source ◽  
Target Domain ◽  
Generative Adversarial Network ◽  
Source Domain ◽  
Adversarial Network ◽  
Latent Space ◽  
Benchmark Datasets

Existing domain adaptation methods on visual sentiment classification typically are investigated under the single-source scenario, where the knowledge learned from a source domain of sufficient labeled data is transferred to the target domain of loosely labeled or unlabeled data. However, in practice, data from a single source domain usually have a limited volume and can hardly cover the characteristics of the target domain. In this paper, we propose a novel multi-source domain adaptation (MDA) method, termed Multi-source Sentiment Generative Adversarial Network (MSGAN), for visual sentiment classification. To handle data from multiple source domains, it learns to find a unified sentiment latent space where data from both the source and target domains share a similar distribution. This is achieved via cycle consistent adversarial learning in an end-to-end manner. Extensive experiments conducted on four benchmark datasets demonstrate that MSGAN significantly outperforms the state-of-the-art MDA approaches for visual sentiment classification.

scholarly journals Category-Sensitive Domain Adaptation for Land Cover Mapping in Aerial Scenes

2019 ◽  
Vol 11 (22) ◽  
pp. 2631 ◽  
Author(s):  
Bo Fang ◽  
Rong Kou ◽  
Li Pan ◽  
Pengfei Chen
Keyword(s):  
Land Cover ◽  
Domain Adaptation ◽  
Feature Space ◽  
Aerial Images ◽  
Land Cover Mapping ◽  
Target Domain ◽  
Generative Adversarial Network ◽  
Source Domain ◽  
Adversarial Network ◽  
Semantic Labeling

Since manually labeling aerial images for pixel-level classification is expensive and time-consuming, developing strategies for land cover mapping without reference labels is essential and meaningful. As an efficient solution for this issue, domain adaptation has been widely utilized in numerous semantic labeling-based applications. However, current approaches generally pursue the marginal distribution alignment between the source and target features and ignore the category-level alignment. Therefore, directly applying them to land cover mapping leads to unsatisfactory performance in the target domain. In our research, to address this problem, we embed a geometry-consistent generative adversarial network (GcGAN) into a co-training adversarial learning network (CtALN), and then develop a category-sensitive domain adaptation (CsDA) method for land cover mapping using very-high-resolution (VHR) optical aerial images. The GcGAN aims to eliminate the domain discrepancies between labeled and unlabeled images while retaining their intrinsic land cover information by translating the features of the labeled images from the source domain to the target domain. Meanwhile, the CtALN aims to learn a semantic labeling model in the target domain with the translated features and corresponding reference labels. By training this hybrid framework, our method learns to distill knowledge from the source domain and transfers it to the target domain, while preserving not only global domain consistency, but also category-level consistency between labeled and unlabeled images in the feature space. The experimental results between two airborne benchmark datasets and the comparison with other state-of-the-art methods verify the robustness and superiority of our proposed CsDA.

scholarly journals A Smart Surveillance System for Uncooperative Gait Recognition Using Cycle Consistent Generative Adversarial Networks (CCGANs)

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Wafaa Adnan Alsaggaf ◽  
Irfan Mehmood ◽  
Enas Fawai Khairullah ◽  
Samar Alhuraiji ◽  
Maha Farouk S. Sabir ◽  
...  
Keyword(s):  
Gait Recognition ◽  
Recognition System ◽  
Research Area ◽  
Generative Adversarial Networks ◽  
Normal Walking ◽  
Target Domain ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Adversarial Network ◽  
Smart Surveillance

Surveillance remains an important research area, and it has many applications. Smart surveillance requires a high level of accuracy even when persons are uncooperative. Gait Recognition is the study of recognizing people by the way they walk even when they are unwilling to cooperate. It is another form of a behavioral biometric system in which unique attributes of an individual’s gait are analyzed to determine their identity. On the other hand, one of the big limitations of the gait recognition system is uncooperative environments in which both gallery and probe sets are made under different and unknown walking conditions. In order to tackle this problem, we propose a deep learning-based method that is trained on individuals with the normal walking condition, and to deal with an uncooperative environment and recognize the individual with any dynamic walking conditions, a cycle consistent generative adversarial network is used. This method translates a GEI disturbed from different covariate factors to a normal GEI. It works like unsupervised learning, and during its training, a GEI disrupts from different covariate factors of each individual and acts as a source domain while the normal walking conditions of individuals are our target domain to which translation is required. The cycle consistent GANs automatically find an individual pair with the help of the Cycle Loss function and generate the required GEI, which is tested by the CNN model to predict the person ID. The proposed system is evaluated over a publicly available data set named CASIA-B, and it achieved excellent results. Moreover, this system can be implemented in sensitive areas, like banks, seminar halls (events), airports, embassies, shopping malls, police stations, military areas, and other public service areas for security purposes.

scholarly journals SA-GAN: Stain Acclimation Generative Adversarial Network for Histopathology Image Analysis

2021 ◽  
Vol 12 (1) ◽  
pp. 288
Author(s):  
Tasleem Kausar ◽  
Adeeba Kausar ◽  
Muhammad Adnan Ashraf ◽  
Muhammad Farhan Siddique ◽  
Mingjiang Wang ◽  
...  
Keyword(s):  
Image Analysis ◽  
Reference Image ◽  
Target Image ◽  
Target Domain ◽  
Generative Adversarial Network ◽  
Cad Systems ◽  
Source Domain ◽  
Adversarial Network ◽  
Single Target ◽  
Histopathology Images

Histopathological image analysis is an examination of tissue under a light microscope for cancerous disease diagnosis. Computer-assisted diagnosis (CAD) systems work well by diagnosing cancer from histopathology images. However, stain variability in histopathology images is inevitable due to the use of different staining processes, operator ability, and scanner specifications. These stain variations present in histopathology images affect the accuracy of the CAD systems. Various stain normalization techniques have been developed to cope with inter-variability issues, allowing standardizing the appearance of images. However, in stain normalization, these methods rely on the single reference image rather than incorporate color distributions of the entire dataset. In this paper, we design a novel machine learning-based model that takes advantage of whole dataset distributions as well as color statistics of a single target image instead of relying only on a single target image. The proposed deep model, called stain acclimation generative adversarial network (SA-GAN), consists of one generator and two discriminators. The generator maps the input images from the source domain to the target domain. Among discriminators, the first discriminator forces the generated images to maintain the color patterns as of target domain. While second discriminator forces the generated images to preserve the structure contents as of source domain. The proposed model is trained using a color attribute metric, extracted from a selected template image. Therefore, the designed model not only learns dataset-specific staining properties but also image-specific textural contents. Evaluated results on four different histopathology datasets show the efficacy of SA-GAN to acclimate stain contents and enhance the quality of normalization by obtaining the highest values of performance metrics. Additionally, the proposed method is also evaluated for multiclass cancer type classification task, showing a 6.9% improvement in accuracy on ICIAR 2018 hidden test data.

ORGANIC (1).pdf

2017 ◽  
Author(s):  
Benjamin Sanchez-Lengeling ◽  
Carlos Outeiral ◽  
Gabriel L. Guimaraes ◽  
Alan Aspuru-Guzik
Keyword(s):  
Machine Learning ◽  
Learning Community ◽  
Chemical Species ◽  
Material Design ◽  
Organic Photovoltaic ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Photovoltaic Material

Molecular discovery seeks to generate chemical species tailored to very specific needs. In this paper, we present ORGANIC, a framework based on Objective-Reinforced Generative Adversarial Networks (ORGAN), capable of producing a distribution over molecular space that matches with a certain set of desirable metrics. This methodology combines two successful techniques from the machine learning community: a Generative Adversarial Network (GAN), to create non-repetitive sensible molecular species, and Reinforcement Learning (RL), to bias this generative distribution towards certain attributes. We explore several applications, from optimization of random physicochemical properties to candidates for drug discovery and organic photovoltaic material design.

scholarly journals Restoring Raindrops Using Attentive Generative Adversarial Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 7034
Author(s):  
Hee-Deok Yang
Keyword(s):  
Weather Conditions ◽  
Recurrent Network ◽  
Generative Adversarial Networks ◽  
Navigation Systems ◽  
Vision Systems ◽  
Generative Adversarial Network ◽  
Network Layers ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Outdoor Vision

Artificial intelligence technologies and vision systems are used in various devices, such as automotive navigation systems, object-tracking systems, and intelligent closed-circuit televisions. In particular, outdoor vision systems have been applied across numerous fields of analysis. Despite their widespread use, current systems work well under good weather conditions. They cannot account for inclement conditions, such as rain, fog, mist, and snow. Images captured under inclement conditions degrade the performance of vision systems. Vision systems need to detect, recognize, and remove noise because of rain, snow, and mist to boost the performance of the algorithms employed in image processing. Several studies have targeted the removal of noise resulting from inclement conditions. We focused on eliminating the effects of raindrops on images captured with outdoor vision systems in which the camera was exposed to rain. An attentive generative adversarial network (ATTGAN) was used to remove raindrops from the images. This network was composed of two parts: an attentive-recurrent network and a contextual autoencoder. The ATTGAN generated an attention map to detect rain droplets. A de-rained image was generated by increasing the number of attentive-recurrent network layers. We increased the number of visual attentive-recurrent network layers in order to prevent gradient sparsity so that the entire generation was more stable against the network without preventing the network from converging. The experimental results confirmed that the extended ATTGAN could effectively remove various types of raindrops from images.

scholarly journals Prediction and analysis of multiple protein lysine modified sites based on conditional wasserstein generative adversarial networks

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Yingxi Yang ◽  
Hui Wang ◽  
Wen Li ◽  
Xiaobo Wang ◽  
Shizhao Wei ◽  
...  
Keyword(s):  
Correlation Coefficient ◽  
Sequence Data ◽  
Rapid Development ◽  
Pearson Correlation ◽  
Structural Features ◽  
Generative Adversarial Networks ◽  
Post Translational Modification ◽  
Generative Adversarial Network ◽  
Data Imbalance ◽  
Adversarial Network

Abstract Background Protein post-translational modification (PTM) is a key issue to investigate the mechanism of protein’s function. With the rapid development of proteomics technology, a large amount of protein sequence data has been generated, which highlights the importance of the in-depth study and analysis of PTMs in proteins. Method We proposed a new multi-classification machine learning pipeline MultiLyGAN to identity seven types of lysine modified sites. Using eight different sequential and five structural construction methods, 1497 valid features were remained after the filtering by Pearson correlation coefficient. To solve the data imbalance problem, Conditional Generative Adversarial Network (CGAN) and Conditional Wasserstein Generative Adversarial Network (CWGAN), two influential deep generative methods were leveraged and compared to generate new samples for the types with fewer samples. Finally, random forest algorithm was utilized to predict seven categories. Results In the tenfold cross-validation, accuracy (Acc) and Matthews correlation coefficient (MCC) were 0.8589 and 0.8376, respectively. In the independent test, Acc and MCC were 0.8549 and 0.8330, respectively. The results indicated that CWGAN better solved the existing data imbalance and stabilized the training error. Alternatively, an accumulated feature importance analysis reported that CKSAAP, PWM and structural features were the three most important feature-encoding schemes. MultiLyGAN can be found at https://github.com/Lab-Xu/MultiLyGAN. Conclusions The CWGAN greatly improved the predictive performance in all experiments. Features derived from CKSAAP, PWM and structure schemes are the most informative and had the greatest contribution to the prediction of PTM.

scholarly journals Stochastic Restoration of Heavily Compressed Musical Audio Using Generative Adversarial Networks

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1349
Author(s):  
Stefan Lattner ◽  
Javier Nistal
Keyword(s):  
Data Storage ◽  
Audio Signal ◽  
Human Perception ◽  
Generative Adversarial Networks ◽  
Audio Signals ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Extensive Evaluation ◽  
Listening Tests ◽  
Musical Audio

Lossy audio codecs compress (and decompress) digital audio streams by removing information that tends to be inaudible in human perception. Under high compression rates, such codecs may introduce a variety of impairments in the audio signal. Many works have tackled the problem of audio enhancement and compression artifact removal using deep-learning techniques. However, only a few works tackle the restoration of heavily compressed audio signals in the musical domain. In such a scenario, there is no unique solution for the restoration of the original signal. Therefore, in this study, we test a stochastic generator of a Generative Adversarial Network (GAN) architecture for this task. Such a stochastic generator, conditioned on highly compressed musical audio signals, could one day generate outputs indistinguishable from high-quality releases. Therefore, the present study may yield insights into more efficient musical data storage and transmission. We train stochastic and deterministic generators on MP3-compressed audio signals with 16, 32, and 64 kbit/s. We perform an extensive evaluation of the different experiments utilizing objective metrics and listening tests. We find that the models can improve the quality of the audio signals over the MP3 versions for 16 and 32 kbit/s and that the stochastic generators are capable of generating outputs that are closer to the original signals than those of the deterministic generators.

Sign in / Sign up

Export Citation Format

Share Document