Staingan: Stain Style Transfer for Digital Histological Images

Shaban, Muhammad; Baur, Christoph; Navab, Nassir; Albarqouni, Shadi

doi:10.1109/isbi.2019.8759152

Cited by 218 publications

(195 citation statements)

References 12 publications

Supporting

Mentioning

194

Contrasting

Unclassified

Order By: Relevance

“…To have fair and comprehensive comparisons with other methods, we evaluated our model as follows: i) Analysis of the image quality at different levels of downsampling; ii) Analysis of the effect of the proposed generator on the results and comparisons of results using different generators; iii) Quantitative and qualitative comparisons between our method and state-of-the-art approaches [22]. We will introduce the experimental dataset, the training details, the evaluational metrics and experimental results in the following sections.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Since the medical images are unpaired in different centers, we used the cycle-consistent loss [24] to map the patches from domain A to domain H, and compared the generated patches with the real patches of scanner H (ground truth). The stateof-the-art method is StainGAN [22], the difference between TAN and StainGAN is that we have designed a novel generator we refer to as Trans-Net. The author of StainGAN adopted the architecture for their generative networks from Johnson et al [11] who have shown impressive results for neural style transfer and super-resolution.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…However, this stain style transfer model depends on a specific model for a specific task on top. Shaban [22] proposed a method which is known as StainGAN. StainGAN is based on an Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (Cy-cleGAN).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Stain Style Transfer Using Transitive Adversarial Networks

Cai¹,

Xue²,

Gao³

et al. 2019

Machine Learning for Medical Image Reconstruction

View full text Add to dashboard Cite

Digitized pathological diagnosis has been in increasing demand recently. It is well known that color information is critical to the automatic and visual analysis of pathological slides. However, the color variations due to various factors not only have negative impact on pathologist's diagnosis, but also will reduce the robustness of the algorithms. The factors that cause the color differences are not only in the process of making the slices, but also in the process of digitization. Different strategies have been proposed to alleviate the color variations. Most of such techniques rely on collecting color statistics to perform color matching across images and highly dependent on a reference template slide. Since the pathological slides between hospitals are usually unpaired, these methods do not yield good matching results. In this work, we propose a novel network that we refer to as Transitive Adversarial Networks (TAN) to transfer the color information among slides from different hospitals or centers. It is not necessary for an expert to pick a representative reference slide in the proposed TAN method. We compare the proposed method with the state-of-the-art methods quantitatively and qualitatively. Compared with the state-of-the-art methods, our method yields an improvement of 0.87dB in terms of PSNR, demonstrating the effectiveness of the proposed TAN method in stain style transfer.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Stain Style Transfer Using Transitive Adversarial Networks

Cai¹,

Xue²,

Gao³

et al. 2019

Machine Learning for Medical Image Reconstruction

View full text Add to dashboard Cite

show abstract

“…Quite a few [25,72,73,94] have utilized deep learning to perform a multimodal registration. Deep learning is also used for the separation of staining colors [3,3,20,39,93] or for registration [10,27,28].…”

Section: Deep Learningmentioning

confidence: 99%

The tempest in a cubic millimeter: Image-based refinements necessitate the reconstruction of 3D microvasculature from a large series of damaged alternately-stained histological sections

Lobachev

2019

Preprint

View full text Add to dashboard Cite

This work presents two methods that facilitate a 3D reconstruction of microscopic blood vessels in the volume slightly larger than 1 mm 3 . The source of the data are histological serial sections, i. e., microscopic images of probes, stained with immunohistochemistry. Odd and even sections have different stainings in our primary data set. Thus, firstly, an approach to register an alternately-stained series is presented. With image filtering and a feature-detection-based registration we obtain a registered stack of 148 serial sections. The series has missing sections, locally damaged sections, artifacts from acquisition. All these hinder correct connectivity of blood vessels. With our second approach we interpolate the missing information while maintaining the connectivity. We achieve this with deformations based on dense optical flow. The presented methodology is applicable to further histological series. A combination of both approaches allows us to reconstruct more than 76 % larger volumes. An important detail was the composition mode of images. Summarizing, we use methods from image processing and computer vision to create large-scale 3D models from immunostained histological serial sections.

show abstract

“…The training of these supervised methods is based on spatially registered image pairs of the input and output modalities. As generating paired slide images with different stainings is a complex task involving the use of consecutive tissue sections or a stain-washstain technique, unsupervised deep learning methods have been used in virtual staining [8] and stain normalization applications [14]. In [8], CycleGAN [16] has been used in order to virtually generate duplex Immunohistochemistry (IHC) stained images from real stained images.…”

Section: Introductionmentioning

confidence: 99%

Perceptual Embedding Consistency for Seamless Reconstruction of Tilewise Style Transfer

Lahiani

Navab

Albarqouni

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Style transfer is a field with growing interest and use cases in deep learning. Recent work has shown Generative Adversarial Networks (GANs) can be used to create realistic images of virtually stained slide images in digital pathology with clinically validated interpretability. Digital pathology images are typically of extremely high resolution, making tilewise analysis necessary for deep learning applications. It has been shown that image generators with instance normalization can cause a tiling artifact when a large image is reconstructed from the tilewise analysis. We introduce a novel perceptual embedding consistency loss significantly reducing the tiling artifact created in the reconstructed whole slide image (WSI). We validate our results by comparing virtually stained slide images with consecutive real stained tissue slide images. We also demonstrate that our model is more robust to contrast, color and brightness perturbations by running comparative sensitivity analysis tests.

show abstract

Staingan: Stain Style Transfer for Digital Histological Images

Cited by 218 publications

References 12 publications

Stain Style Transfer Using Transitive Adversarial Networks

Stain Style Transfer Using Transitive Adversarial Networks

The tempest in a cubic millimeter: Image-based refinements necessitate the reconstruction of 3D microvasculature from a large series of damaged alternately-stained histological sections

Perceptual Embedding Consistency for Seamless Reconstruction of Tilewise Style Transfer

Contact Info

Product

Resources

About