Pix2Pix generative adversarial network for low dose myocardial perfusion SPECT denoising

Sun, Jingzhang; Du, Yu; Li, ChienYing; Wu, Tsu‐Juey; Yang, Baofeng; Mok, Greta S. P.

doi:10.21037/qims-21-1042

Cited by 30 publications

(20 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One noise level was evaluated in this cGAN study, whereas more noise levels can be further evaluated for low-dose dual gating MP-SPECT. 11,37,38 Only spatial denoising was evaluated in this study, whereas temporal filtering could be useful for 4D and 5D datasets. 31 Another limitation is that we only considered the CG/NG as the training reference.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Dual gating myocardial perfusion SPECT denoising using a conditional generative adversarial network

Sun

Zhang

et al. 2022

Medical Physics

Self Cite

View full text Add to dashboard Cite

Purpose Dual respiratory–cardiac gating reduces respiratory and cardiac motion blur in myocardial perfusion single‐photon emission computed tomography (MP‐SPECT). However, image noise is increased as detected counts are reduced in each dual gate (DG). We aim to develop a denoising method for dual gating MP‐SPECT images using a 3D conditional generative adversarial network (cGAN). Methods Twenty extended cardiac‐torso phantoms with various 99mTc‐sestamibi distributions, defect characteristics, and body and organ sizes were used in the simulation, modeling six respiratory and eight cardiac gates (CGs), that is, 48 DGs for ordered subset expectation maximization reconstruction. Twenty clinical 99mTc‐sestamibi SPECT/CT datasets were re‐binned into 7 respiratory gates and 8 CGs, that is, 56 DGs for maximum likelihood expectation maximization reconstruction. We evaluated the use of (i) phantoms’ own datasets (patient‐specific denoising [PD]) or other phantoms’ datasets (cross‐patient denoising) for training; (ii) the CG or the static (non‐gated [NG]) data as the training references for cGAN; and (iii) cGAN as compared to conventional 3D post‐reconstruction filtering, cardiac gating methods, and convolutional neural network. Normalized mean squared error, noise as assessed by normalized standard deviation, spatial blurring measured as the full‐width‐at‐half‐maximum of left ventricular wall, ejection fraction, joint correlation histogram, and defect size were analyzed as metrics of image quality. Results Training using patients’ own dataset is superior to conventional training based on other patients’ data. Using CG image as training reference provides a better trade‐off in terms of noise and image blur as compared to the use of NG. cGAN‐CG‐PD provides superior performance as compared to other denoising methods for all physical and diagnostic indices evaluated in both simulation and clinical studies. Conclusions cGAN denoising is promising for dual gating MP‐SPECT based on the metrics mentioned earlier.

show abstract

Section: Discussionmentioning

confidence: 99%

“…There are certain limitations of this study. One noise level was evaluated in this cGAN study, whereas more noise levels can be further evaluated for low‐dose dual gating MP‐SPECT 11,37,38 . Only spatial denoising was evaluated in this study, whereas temporal filtering could be useful for 4D and 5D datasets 31 .…”

Section: Discussionmentioning

confidence: 99%

Dual gating myocardial perfusion SPECT denoising using a conditional generative adversarial network

Sun

Zhang

et al. 2022

Medical Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Somewhat similar yet different is the task of video denoising [179,9,10,275,276,290,259,180,322,161], in which we may seek online filtering of the incoming frames. When handling specific imaging types (e.g., microscopy [223,25,13,103,340,186,158,188], CT [164,48,318,316,70,314] and PET/SPECT imaging [51,82,105,227,343,266], and more), the algorithm design may require adequate adaptations to the data format (e.g. treating 3D volumes [294,336,324,64,178]) or to the way it is captured.…”

Section: Extensions Of Imagementioning

confidence: 99%

Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --

Elad¹,

Kawar²,

Vaksman³

2023

Preprint

View full text Add to dashboard Cite

Image denoising -removal of additive white Gaussian noise from an image -is one of the oldest and most studied problems in image processing. An extensive work over several decades has led to thousands of papers on this subject, and to many well-performing algorithms for this task. Indeed, ten years ago, these achievements have led some researchers to suspect that "Denoising is Dead", in the sense that all that can be achieved in this domain has already been obtained. However, this turned out to be far from the truth, with the penetration of deep learning (DL) into the realm of image processing. The era of DL brought a revolution to image denoising, both by taking the lead in today's ability for noise suppression in images, and by broadening the scope of denoising problems being treated. Our paper starts by describing this evolution, highlighting in particular the tension and synergy that exist between classical approaches and modern Artificial Intelligence (AI) alternatives in design of image denoisers.The recent transitions in the field of image denoising go far beyond the ability to design better denoisers. In the second part of this paper we focus on recently discovered abilities and prospects of image denoisers. We expose the possibility of using image denoisers for service of other problems, such as regularizing general inverse problems and serving as the prime engine in diffusion-based image synthesis. We also unveil the (strange?) idea that denoising and other inverse problems might not have a unique solution, as common algorithms would have us believe. Instead, we describe constructive ways to produce randomized and diverse high perceptual quality results for inverse problems, all fueled by the progress that DL brought to image denoising. This is a survey paper, and its prime goal is to provide a broad view of the history of the field of image denoising and closely related topics in image processing. Our aim is to give a better context to recent discoveries, and to the influence of the AI revolution in our domain.

show abstract

“…We propose a deep learning method inspired by a conditional GAN architecture adapted to image-to-image translation. Several studies have been done using this specific model architecture [33][34][35] for different applications. In this work, the network learns to estimate the propagation of an electromagnetic field according to a distribution of sensors.…”

Section: The Proposed Emgan Modelmentioning

confidence: 99%

Towards Outdoor Electromagnetic Field Exposure Mapping Generation Using Conditional GANs

Mallik¹,

Tesfay²,

Allaert³

et al. 2022

Preprint

View full text Add to dashboard Cite

With the ongoing fifth-generation cellular network (5G) deployment, electromagnetic field exposure has become a critical concern. However, measurements are scarce, and accurate electromagnetic field reconstruction in a geographic region remains challenging. This work proposes a conditional Generative Adversarial Network to address this issue. The main objective is to reconstruct the electromagnetic field exposure map accurately according to the environment’s topology from a few sensors located in an outdoor urban environment. The model is trained to learn and estimate the propagation characteristics of the electromagnetic field according to the topology of a given environment. In addition, the conditional Generative Adversarial Network based electromagnetic field mapping is compared with simple kriging. Results show that the proposed method produces accurate estimates and is a promising solution for exposure map reconstruction.

show abstract

Pix2Pix generative adversarial network for low dose myocardial perfusion SPECT denoising

Cited by 30 publications

References 45 publications

Dual gating myocardial perfusion SPECT denoising using a conditional generative adversarial network

Dual gating myocardial perfusion SPECT denoising using a conditional generative adversarial network

Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --

Towards Outdoor Electromagnetic Field Exposure Mapping Generation Using Conditional GANs

Contact Info

Product

Resources

About