Restoration of Marker Occluded Hematoxylin and Eosin Stained Whole Slide Histology Images Using Generative Adversarial Networks

Venkatesh, Bairavi; Shaht, Tosha; Chen, Antong; Ghafurian, Soheil

doi:10.1109/isbi45749.2020.9098358

Cited by 12 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since there is a scarcity of universal metrics for understanding a GAN's efficiency, we plan to expand our PGGAN river satellite imagery survey and distribute it to more participants (Venkatesh et al, 2020). To establish a wider variety of images, we could generate the images directly from the PGGAN on the fly, rather than sampling from a constant repository of pre-selected images.…”

Section: Discussionmentioning

confidence: 99%

Realistic River Image Synthesis Using Deep Generative Adversarial Networks

2022

View full text Add to dashboard Cite

In this paper, we demonstrated a practical application of realistic river image generation using deep learning. Specifically, we explored a generative adversarial network (GAN) model capable of generating high-resolution and realistic river images that can be used to support modeling and analysis in surface water estimation, river meandering, wetland loss, and other hydrological research studies. First, we have created an extensive repository of overhead river images to be used in training. Second, we incorporated the Progressive Growing GAN (PGGAN), a network architecture that iteratively trains smaller-resolution GANs to gradually build up to a very high resolution to generate high quality (i.e., 1,024 × 1,024) synthetic river imagery. With simpler GAN architectures, difficulties arose in terms of exponential increase of training time and vanishing/exploding gradient issues, which the PGGAN implementation seemed to significantly reduce. The results presented in this study show great promise in generating high-quality images and capturing the details of river structure and flow to support hydrological modeling and research.

show abstract

Section: Discussionmentioning

confidence: 99%

Realistic River Image Synthesis Using Deep Generative Adversarial Networks

2022

View full text Add to dashboard Cite

show abstract

“…Several works have been proposed to address ink removal from histopathology images using image-to-image translation. Venkatesh et al 19 used a Cycle GAN 20 for ink restoration given a set of ink patches. Cycle GANs, based on GANs 21 also do image-to-image translations by learning the mapping between source and target domain using unpaired dataset.…”

Section: Ink Removalmentioning

confidence: 99%

“…Here original and restored refer to before and after patch restoration using Pix2Pix. Values are shown in the format of mean ± std ±0.33 0.54 ±0 19. 13.51 ±5.77 16.43 ±3.97 0.10 ±0.11 0.13 ±0.11 Inked tissue patches 0.05 ±0.22 0.47 ±0.20 9.13 ±4.10 14.95 ±3.88 0.08 ±0.14 0.14 ±0.13 Clean tissue patches 0.59 ±0.17 0.61 ±0.16 17.88 ±3.83 17.91 ±3.48 0.12 ±0.07 0.13 ±0.07 Filtered tissue patches 0.32 ±0.33 0.53 ±0.20 13.51 ±5.77 16.39 ±3.94 0.10 ±0.11 0.13 ±0.11…”

mentioning

confidence: 99%

Ink removal in whole slide images using hallucinated data

Ramanathan

Han

Bassiouny

et al. 2023

Medical Imaging 2023: Digital and Computational Pathology

View full text Add to dashboard Cite

Pathologists regularly use ink markings on histopathology slides to highlight specific areas of interest or orientation, making it an integral part of the workflow. Unfortunately, digitization of these ink-annotated slides hinders any computer-aided analyses, particularly deep learning algorithms, which require clean data free from artifacts. We propose a methodology that can identify and remove the ink markings for the purpose of computational analyses. We propose a two-stage network with a binary classifier for ink filtering and Pix2Pix for ink removal. We trained our network by artificially generating pseudo ink markings using only clean slides, requiring no manual annotation or curation of data. Furthermore, we demonstrate our algorithm's efficacy over an independent dataset of H&E stained breast carcinoma slides scanned before and after the removal of pen markings. Our quantitative analysis shows promising results, achieving 98.7% accuracy for the binary classifier. For Pix2Pix, we observed a 65.6% increase in structure similarity index, a 21.3% increase in peak signal-to-noise ratio, and a 30% increase in visual information fidelity. As only clean slides are required for training, the pipeline can be adapted to multiple colors of ink markings or new domains, making it easy to deploy over different sets of histopathology slides. Code and trained models are available at: https://github.com/Vishwesh4/Ink-WSI.

show abstract

“…A similar study has approached the ink removal as a style transfer problem using a cycleGAN to remove ink marks from human melanoma tissues, when preserving the tissue structure underneath the marker region. [ 69 ] The melanoma WSIs were first tiled to obtain marker patches which contain full or partial ink marks and clean patches which do not contain any ink marks. The cycleGAN used, here, is composed of two generative and one discriminative CNN.…”

Section: G Enerative a Dversarial N Etwork In H Istopathological mentioning

confidence: 99%

Generative Adversarial Networks in Digital Pathology and Histopathological Image Processing: A Review

Jose

Liu

Russo

et al. 2021

Journal of Pathology Informatics

View full text Add to dashboard Cite

Digital pathology is gaining prominence among the researchers with developments in advanced imaging modalities and new technologies. Generative adversarial networks (GANs) are a recent development in the field of artificial intelligence and since their inception, have boosted considerable interest in digital pathology. GANs and their extensions have opened several ways to tackle many challenging histopathological image processing problems such as color normalization, virtual staining, ink removal, image enhancement, automatic feature extraction, segmentation of nuclei, domain adaptation and data augmentation. This paper reviews recent advances in histopathological image processing using GANs with special emphasis on the future perspectives related to the use of such a technique. The papers included in this review were retrieved by conducting a keyword search on Google Scholar and manually selecting the papers on the subject of H&E stained digital pathology images for histopathological image processing. In the first part, we describe recent literature that use GANs in various image preprocessing tasks such as stain normalization, virtual staining, image enhancement, ink removal, and data augmentation. In the second part, we describe literature that use GANs for image analysis, such as nuclei detection, segmentation, and feature extraction. This review illustrates the role of GANs in digital pathology with the objective to trigger new research on the application of generative models in future research in digital pathology informatics.

show abstract

Restoration of Marker Occluded Hematoxylin and Eosin Stained Whole Slide Histology Images Using Generative Adversarial Networks

Cited by 12 publications

References 10 publications

Realistic River Image Synthesis Using Deep Generative Adversarial Networks

Realistic River Image Synthesis Using Deep Generative Adversarial Networks

Ink removal in whole slide images using hallucinated data

Generative Adversarial Networks in Digital Pathology and Histopathological Image Processing: A Review

Contact Info

Product

Resources

About