Noise as Domain Shift: Denoising Medical Images by Unpaired Image Translation

Manakov, Ilja; Rohm, Markus; Kern, Christoph; Schworm, Benedikt; Kortuem, Karsten; Tresp, Volker

doi:10.1007/978-3-030-33391-1_1

Cited by 31 publications

(18 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The weights for the training parameters of CycleGAN modules can be tuned depending on the image domain or task. CycleGAN can perform denoising by mapping clean and noisy domains from unpaired training data [ 22 ]. Currently, variants of CycleGAN, such as StarGAN [ 23 ] and its variants [ 24 ], have been introduced to achieve high performance in a multiple domain transfer problem.…”

Section: Reviewmentioning

confidence: 99%

Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey

et al. 2022

View full text Add to dashboard Cite

Background Recent advances in deep learning techniques have led to improved diagnostic abilities in ophthalmology. A generative adversarial network (GAN), which consists of two competing types of deep neural networks, including a generator and a discriminator, has demonstrated remarkable performance in image synthesis and image-to-image translation. The adoption of GAN for medical imaging is increasing for image generation and translation, but it is not familiar to researchers in the field of ophthalmology. In this work, we present a literature review on the application of GAN in ophthalmology image domains to discuss important contributions and to identify potential future research directions. Methods We performed a survey on studies using GAN published before June 2021 only, and we introduced various applications of GAN in ophthalmology image domains. The search identified 48 peer-reviewed papers in the final review. The type of GAN used in the analysis, task, imaging domain, and the outcome were collected to verify the usefulness of the GAN. Results In ophthalmology image domains, GAN can perform segmentation, data augmentation, denoising, domain transfer, super-resolution, post-intervention prediction, and feature extraction. GAN techniques have established an extension of datasets and modalities in ophthalmology. GAN has several limitations, such as mode collapse, spatial deformities, unintended changes, and the generation of high-frequency noises and artifacts of checkerboard patterns. Conclusions The use of GAN has benefited the various tasks in ophthalmology image domains. Based on our observations, the adoption of GAN in ophthalmology is still in a very early stage of clinical validation compared with deep learning classification techniques because several problems need to be overcome for practical use. However, the proper selection of the GAN technique and statistical modeling of ocular imaging will greatly improve the performance of each image analysis. Finally, this survey would enable researchers to access the appropriate GAN technique to maximize the potential of ophthalmology datasets for deep learning research.

show abstract

Section: Reviewmentioning

confidence: 99%

Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…All these DL-based applications have high clinical relevance and may prove effective in supporting the design of suitable protocols in ophthalmology. Going deeper into DL-based applications, the image translation problem has also appeared in different ophthalmology image domains, such as image super resolution [ 22 ], denoising of retinal optical coherence tomography (OCT) [ 23 ], and OCT segmentation [ 24 ]. For instance, Mahapatra et al [ 22 ] introduced a generative adversarial network (GAN) to increase the resolution of fundus images in order to enable more precise image analysis.…”

Section: Related Workmentioning

confidence: 99%

“…For instance, Mahapatra et al [ 22 ] introduced a generative adversarial network (GAN) to increase the resolution of fundus images in order to enable more precise image analysis. Aiming at solving the issue of image denoising in high- and low-noise domains for OCT images, Manakov et al [ 23 ] developed a model on the basis of the cycleGAN network to learn a mapping between these domains. Still on image translation, Sanchez et al [ 24 ] combined two CNNs, the Pix2Pix and a modified deep retinal understanding network, to achieve the segmentation of intraretinal and subretinal fluids, and hyper-reflective foci in OCT images.…”

Section: Related Workmentioning

confidence: 99%

A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration

Benvenuto

Colnago²,

Dias

et al. 2022

Bioengineering

View full text Add to dashboard Cite

In ophthalmology, the registration problem consists of finding a geometric transformation that aligns a pair of images, supporting eye-care specialists who need to record and compare images of the same patient. Considering the registration methods for handling eye fundus images, the literature offers only a limited number of proposals based on deep learning (DL), whose implementations use the supervised learning paradigm to train a model. Additionally, ensuring high-quality registrations while still being flexible enough to tackle a broad range of fundus images is another drawback faced by most existing methods in the literature. Therefore, in this paper, we address the above-mentioned issues by introducing a new DL-based framework for eye fundus registration. Our methodology combines a U-shaped fully convolutional neural network with a spatial transformation learning scheme, where a reference-free similarity metric allows the registration without assuming any pre-annotated or artificially created data. Once trained, the model is able to accurately align pairs of images captured under several conditions, which include the presence of anatomical differences and low-quality photographs. Compared to other registration methods, our approach achieves better registration outcomes by just passing as input the desired pair of fundus images.

show abstract

“…Experiments on the CAMELYON17 challenge dataset 7 demonstrate the effectiveness. Manakov et al [122] propose to leverage unsupervised DA to tackle retinal optical coherence tomography (OCT) image denoising problem. They treat image noises as domain shift between high and low noise domains.…”

Section: Unsupervised Deep Damentioning

confidence: 99%

Domain Adaptation for Medical Image Analysis: A Survey

Guan,

Liu

2021

Preprint

View full text Add to dashboard Cite

Machine learning techniques used in computeraided medical image analysis usually suffer from the domain shift problem caused by different distributions between source/reference data and target data. As a promising solution, domain adaptation has attracted considerable attention in recent years. The aim of this paper is to survey the recent advances of domain adaptation methods in medical image analysis. We first present the motivation of introducing domain adaptation techniques to tackle domain heterogeneity issues for medical image analysis. Then we provide a review of recent domain adaptation models in various medical image analysis tasks. We categorize the existing methods into shallow and deep models, and each of them is further divided into supervised, semi-supervised and unsupervised methods. We also provide a brief summary of the benchmark medical image datasets that support current domain adaptation research. This survey will enable researchers to gain a better understanding of the current status, challenges and future directions of this energetic research field.

show abstract

Noise as Domain Shift: Denoising Medical Images by Unpaired Image Translation

Cited by 31 publications

References 15 publications

Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey

Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey

A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration

Domain Adaptation for Medical Image Analysis: A Survey

Contact Info

Product

Resources

About