Filters








301 Hits in 3.8 sec

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

Tasleem Kausar, Adeeba Kausar, Muhammad Adnan Ashraf, Muhammad Farhan Siddique, Mingjiang Wang, Muhammad Sajid, Muhammad Zeeshan Siddique, Anwar Ul Haq, Imran Riaz
2021 Applied Sciences  
Histopathological image analysis is an examination of tissue under a light microscope for cancerous disease diagnosis.  ...  These stain variations present in histopathology images affect the accuracy of the CAD systems.  ...  Additionally, different generative adversarial networks (GANs)- [27] based stain transfer techniques [28] [29] [30] [31] have been proposed for color normalization of histopathology images.  ... 
doi:10.3390/app12010288 fatcat:zyjmjf7bdfga7d4hlby33c34gu

Histopathological Stain Transfer using Style Transfer Network with Adversarial Loss [article]

Harshal Nishar, Nikhil Chavanke, Nitin Singhal
2020 arXiv   pre-print
In this work, we present a novel approach for the stain normalization problem using fast neural style transfer coupled with adversarial loss.  ...  In recent years, there has been a good amount of research done for image stain normalization to address this issue.  ...  We propose to use neural style transfer with addition of adversarial loss for image stain normalization.  ... 
arXiv:2010.02659v1 fatcat:zgyfbffjk5bjtbuz5gjoyq66cy

Pix2Pix-based Stain-to-Stain Translation: A Solution for Robust Stain Normalization in Histopathology Images Analysis [article]

Pegah Salehi, Abdolah Chalechale
2020 arXiv   pre-print
In our proposed method, a Stain-to-Stain Translation (STST) approach is used to stain normalization for Hematoxylin and Eosin (H&E) stained histopathology images, which learns not only the specific color  ...  This diversity in staining, in addition to Interpretive disparity among pathologists more is one of the main challenges in designing robust and flexible systems for automated analysis.  ...  Babak Ehteshami Bejnordi, for his guidance, time and feedback on this paper.  ... 
arXiv:2002.00647v1 fatcat:lfzhoxc2pffa5lnekhjekgvr3m

Unsupervised Domain Adaptation for Classification of Histopathology Whole-Slide Images

Jian Ren, Ilker Hacihaliloglu, Eric A. Singer, David J. Foran, Xin Qi
2019 Frontiers in Bioengineering and Biotechnology  
Computational image analysis is one means for evaluating digitized histopathology specimens that can increase the reproducibility and reliability with which cancer diagnoses are rendered while simultaneously  ...  that is appropriate for the entire set of whole-slide images.  ...  Adversarial Adaptation for Target Domain The color normalization process makes it possible to perform the stain transfer from source domain to target domain on images directly.  ... 
doi:10.3389/fbioe.2019.00102 pmid:31158269 pmcid:PMC6529804 fatcat:g6qtz2zs6rbx3e4huot4ph76g4

Inter-Semantic Domain Adversarial in Histopathological Images [article]

Nicolas Dumas, Valentin Derangère, Laurent Arnould, Sylvain Ladoire, Louis-Oscar Morel, Nathan Vinçon
2022 arXiv   pre-print
In medical applications, histopathological images are often associated with data shift and they are hardly available.  ...  We then use domain adversarial methods to transfer data shift invariance from one dataset to another dataset with different semantics and show that domain adversarial methods are efficient inter-semantically  ...  In order words, we question the transferability of the domain adversarial process across tasks and image semantics.  ... 
arXiv:2201.09041v1 fatcat:fxyxfrjhcbajhe2t3nixpajk5q

Unpaired Stain Transfer using Pathology-Consistent Constrained Generative Adversarial Networks

Shuting Liu, Baochang Zhang, Yiqing Liua, Anjia Han, Huijuan Shi, Tian Guan, Yonghong He
2021 IEEE Transactions on Medical Imaging  
In our work, we propose a novel adversarial learning method for effective Ki-67-stained image generation from corresponding H&E-stained image.  ...  We believe that our method has significant potential in clinical virtual staining and advance the progress of computer-aided multi-staining histology image analysis.  ...  For multi staining histopathological image analysis, the most important thing is ensuring the consistency of pathology.  ... 
doi:10.1109/tmi.2021.3069874 pmid:33784619 fatcat:6nwsocrxynemhe5t6husnxfvz4

Structure Preserving Stain Normalization of Histopathology Images Using Self-Supervised Semantic Guidance [article]

Dwarikanath Mahapatra, Behzad Bozorgtabar, Jean-Philippe Thiran, Ling Shao
2021 arXiv   pre-print
Although generative adversarial network (GAN) based style transfer is state of the art in histopathology color-stain normalization, they do not explicitly integrate structural information of tissues.  ...  We integrate semantic information at different layers between a pre-trained semantic network and the stain color normalization network.  ...  BenTaieb, A., Hamarneh, G.: Adversarial stain transfer for histopathology image analysis. IEEE Trans. Med. Imaging 37(3), 792-802 (2018) 10.  ... 
arXiv:2008.02101v3 fatcat:ywy3cavyb5fmjgddqgbhhc3tpa

Stain Style Transfer of Histopathology Images Via Structure-Preserved Generative Learning [article]

Hanwen Liang, Konstantinos N. Plataniotis, Xingyu Li
2020 arXiv   pre-print
To address the issue of color variations in histopathology images, this study proposes two stain style transfer models, SSIM-GAN and DSCSI-GAN, based on the generative adversarial networks.  ...  Computational histopathology image diagnosis becomes increasingly popular and important, where images are segmented or classified for disease diagnosis by computers.  ...  In this study, we develop a novel stain-style transfer framework combining a GAN network and a classification network for color normalization on histopathology images.  ... 
arXiv:2007.12578v1 fatcat:bwgrkk3zkrdy7fkkq35e7uat3y

Multi-stage domain adversarial style reconstruction for cytopathological image stain normalization [article]

Xihao Chen and Jingya Yu and Li Chen and Shaoqun Zeng and Xiuli Liu and Shenghua Cheng
2019 arXiv   pre-print
The different stain styles of cytopathological images have a negative effect on the generalization ability of automated image analysis algorithms.  ...  This article proposes a new framework that normalizes the stain style for cytopathological images through a stain removal module and a multi-stage domain adversarial style reconstruction module.  ...  ACKNOWLEDGMENT We thank the Optical Bioimaging Core Facility of WNLO HUST for the support in data acquisition.  ... 
arXiv:1909.05184v1 fatcat:vgscqavbarb45hsnmd2rnup6xq

Self Adversarial Attack as an Augmentation Method for Immunohistochemical Stainings

Jelica Vasiljevic, Friedrich Feuerhake, Cedric Wemmert, Thomas Lampert
2021 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)  
It has been shown that unpaired image-to-image translation methods constrained by cycle-consistency hide the information necessary for accurate input reconstruction as imperceptible noise.  ...  We demonstrate that, when applied to histopathology data, this hidden noise appears to be related to stain specific features and show that this is the case with two immunohistochemical stainings during  ...  STAIN TRANSFER SELF ADVERSARIAL ATTACK Given samples of two histopathological stains a ∼ A and b ∼ B, the goal is to learn two mappings (translators) G AB : a ∼ A → b ∼ B and G BA : b ∼ B → a ∼ A.  ... 
doi:10.1109/isbi48211.2021.9433838 fatcat:rsrfqotr3zaznfs2xcftkzttsa

Self adversarial attack as an augmentation method for immunohistochemical stainings [article]

Jelica Vasiljević, Friedrich Feuerhake, Cédric Wemmert, Thomas Lampert
2021 arXiv   pre-print
It has been shown that unpaired image-to-image translation methods constrained by cycle-consistency hide the information necessary for accurate input reconstruction as imperceptible noise.  ...  We demonstrate that, when applied to histopathology data, this hidden noise appears to be related to stain specific features and show that this is the case with two immunohistochemical stainings during  ...  STAIN TRANSFER SELF ADVERSARIAL ATTACK Given samples of two histopathological stains a ∼ A and b ∼ B, the goal is to learn two mappings (translators) G AB : a ∼ A → b ∼ B and G BA : b ∼ B → a ∼ A.  ... 
arXiv:2103.11362v1 fatcat:j5ezybppt5bcvdfs7q4ub62tou

GAN-based Virtual Re-Staining: A Promising Solution for Whole Slide Image Analysis [article]

Zhaoyang Xu, Carlos Fernández Moro, Béla Bozóky, Qianni Zhang
2019 arXiv   pre-print
Histopathological cancer diagnosis is based on visual examination of stained tissue slides. Hematoxylin and eosin (H&E) is a standard stain routinely employed worldwide.  ...  We proposed a conditional CycleGAN (cCGAN) network to transform the H&E stained images into IHC stained images, facilitating virtual IHC staining on the same slide.  ...  Our contribution In this study, we explore the potential of unpaired image-to-image translation as "virtual staining" for histopathology image analysis.  ... 
arXiv:1901.04059v1 fatcat:chk2uqqmi5ewrkjfk2v3g4r5vm

Deep Learning for Virtual Histological Staining of Bright-Field Microscopic Images of Unlabeled Carotid Artery Tissue

Dan Li, Hui Hui, Yingqian Zhang, Wei Tong, Feng Tian, Xin Yang, Jie Liu, Yundai Chen, Jie Tian
2020 Molecular Imaging and Biology  
Histological analysis of artery tissue samples is a widely used method for diagnosis and quantification of cardiovascular diseases.  ...  We trained a convolutional neural network to build maps between the unstained images and histologically stained images using a conditional generative adversarial network model.  ...  The authors would like to acknowledge the instrumental and technical support of multimodal biomedical imaging experimental platform, Institute of Automation, Chinese Academy of Sciences.  ... 
doi:10.1007/s11307-020-01508-6 pmid:32514884 fatcat:ovpe73vutbdjfphyhl672hwdpm

MVIP 2020 Table of Contents

2020 2020 International Conference on Machine Vision and Image Processing (MVIP)  
High-Resolution Document Image Reconstruction from Video 38. Pix2Pix-based Stain-to-Stain Translation: A Solution for Robust Stain Normalization in Histopathology Images Analysis 39.  ...  Gaussian Soft Margin Angular Loss for Face Recognition 8. An Ensemble Model for Human Posture Recognition 9. Image Colorization using Generative Adversarial Networks and Transfer Learning 10.  ... 
doi:10.1109/mvip49855.2020.9116904 fatcat:6v7rolxpkfh6jb2fg2bhd4ssuq

Learning Domain-Invariant Representations of Histological Images

Maxime W. Lafarge, Josien P. W. Pluim, Koen A. J. Eppenhof, Mitko Veta
2019 Frontiers in Medicine  
We carried out a comparative analysis with staining normalization and data augmentation on two different tasks: generalization to images acquired in unseen pathology labs for mitosis detection and generalization  ...  The proposed framework for domain-adversarial training is able to improve generalization performances on top of conventional methods.  ...  In conclusion, we proposed a domain-adversarial framework for training CNN models on histopathology images, and we made a comparative analysis against conventional preprocessing methods.  ... 
doi:10.3389/fmed.2019.00162 pmid:31380377 pmcid:PMC6646468 fatcat:amrgj5rljbeczpuva34qbce6fy
« Previous Showing results 1 — 15 out of 301 results