Automated Segmentation of Epithelial Tissue Using Cycle-Consistent Generative Adversarial Networks

Eule, Stephan; Haering, Matthias; Grosshans, Joerg; Wolf, Fred

doi:10.1101/311373

Cited by 15 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Duggal et al utilized a form of generative model known as a deep belief network for separating touching or overlapping white blood cell nuclei from leukemia in microscopy images. Recently, Haering et al presented a cycle‐consistent GAN (Cycle‐GAN) for segmenting epithelial cell tissue in drosophila embryos. Their approach circumvents the need for annotated data by employing two generators, where the second generator translates the output of the first generator back to the input space.…”

Section: Deep Learning For Image Cytometrymentioning

confidence: 99%

Deep Learning in Image Cytometry: A Review

et al. 2018

View full text Add to dashboard Cite

Artificial intelligence, deep convolutional neural networks, and deep learning are all niche terms that are increasingly appearing in scientific presentations as well as in the general media. In this review, we focus on deep learning and how it is applied to microscopy image data of cells and tissue samples. Starting with an analogy to neuroscience, we aim to give the reader an overview of the key concepts of neural networks, and an understanding of how deep learning differs from more classical approaches for extracting information from image data. We aim to increase the understanding of these methods, while highlighting considerations regarding input data requirements, computational resources, challenges, and limitations. We do not provide a full manual for applying these methods to your own data, but rather review previously published articles on deep learning in image cytometry, and guide the readers toward further reading on specific networks and methods, including new methods not yet applied to cytometry data. © 2018 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

show abstract

Section: Deep Learning For Image Cytometrymentioning

confidence: 99%

Deep Learning in Image Cytometry: A Review

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Moreover, human annotations may suffer from inter-observer variability depending on the biological structure being segmented and the background noise. To cope with the aforementioned lack of annotations, different data augmentation methods have been proposed (11)(12)(13)(14)(15). The limitations of these methods lie in the assumption that the chosen augmentation family can adequately cover the full range of variation of the tissue to be segmented.…”

Section: Introductionmentioning

confidence: 99%

ImPartial: Partial Annotations for Cell Instance Segmentation

Martínez

Sapiro

Tannenbaum

et al. 2021

Preprint

View full text Add to dashboard Cite

Segmenting noisy multiplex spatial tissue images constitutes a challenging task, since the characteristics of both the noise and the biology being imaged differs significantly across tissues and modalities; this is compounded by the high monetary and time costs associated with manual annotations. It is therefore imperative to build algorithms that can accurately segment the noisy images based on a small number of annotations. Recently techniques to derive such an algorithm from a few scribbled annotations have been proposed, mostly relying on the refinement and estimation of pseudo-labels. Other techniques leverage the success of self-supervised denoising as a parallel task to potentially improve the segmentation objective when few annotations are available. In this paper, we propose a method that augments the segmentation objective via self-supervised multi-channel quantized imputation, meaning that each class of the segmentation objective can be characterized by a mixture of distributions. This approach leverages the observation that perfect pixel-wise reconstruction or denoising of the image is not needed for accurate segmentation, and introduces a self-supervised classification objective that better aligns with the overall segmentation goal. We demonstrate the superior performance of our approach for a variety of cancer datasets acquired with different highly-multiplexed imaging modalities in real clinical settings. Code for our method along with a benchmarking dataset is available at https://github.com/natalialmg/ImPartial.

show abstract

“…In the biomedical field we seek to turn real data into segmented data. Not needing paired images makes this approach very versatile, because one can use publicly available labeled data that share similarities with the images to segment [11,12,13,14,15]. However this still requires previously existing annotations and thus is a limiting factor.…”

Section: Introductionmentioning

confidence: 99%

“…The UDCT is a cycleGAN adaptation with the focus on segmenting images. By focusing on only the segmentation task, we do not require both of the domains to be raw or labelled images any more, as it has been the case in earlier works that used cycleGANs for such tasks [8,11]. Instead, One of our image domains can be replaced with synthetic data.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised data to content transformation with histogram-matching cycle-consistent generative adversarial networks

et al. 2019

View full text Add to dashboard Cite

The segmentation of images is a common task in a broad range of research fields. To tackle increasingly complex images, artificial intelligence (AI) based approaches have emerged to overcome the shortcomings of traditional feature detection methods. Owing to the fact that most AI research is made publicly accessible and programming the required algorithms is now possible in many popular languages, the use of such approaches is becoming widespread. However, these methods often require data labeled by the researcher to provide a training target for the algorithms to converge to the desired result. This labeling is a limiting factor in many cases and can become prohibitively time consuming. Inspired by Cycle-consistent Generative Adversarial Networks' (cycleGAN) ability to perform style transfer, we outline a method whereby a computer generated set of images is used to segment the true images. We benchmark our unsupervised approach against a state-of-the-art supervised cell-counting network on the VGG Cells dataset and show that it is not only competitive but can also precisely locate individual cells. We demonstrate the power of this method by segmenting bright-field images of cell cultures, a live-dead assay of C. elegans and X-ray-computed tomography of metallic nanowire meshes.

show abstract

Automated Segmentation of Epithelial Tissue Using Cycle-Consistent Generative Adversarial Networks

Cited by 15 publications

References 20 publications

Deep Learning in Image Cytometry: A Review

Deep Learning in Image Cytometry: A Review

ImPartial: Partial Annotations for Cell Instance Segmentation

Unsupervised data to content transformation with histogram-matching cycle-consistent generative adversarial networks

Contact Info

Product

Resources

About