AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising

• URL: http://arxiv.org/abs/2008.05753v1
• Date: Thu, 13 Aug 2020 08:30:23 GMT
• Title: AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising
• Authors: Jawook Gu, Jong Chul Ye
• Abstract summary: We propose a novel cycleGAN architecture using a single switchable generator. The proposed method outperforms the previous cycleGAN approaches while using only about half the parameters.
• Score: 46.0231398013639
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Recently, deep learning approaches have been extensively studied for low-dose CT denoising thanks to its superior performance despite the fast computational time. In particular, cycleGAN has been demonstrated as a powerful unsupervised learning scheme to improve the low-dose CT image quality without requiring matched high-dose reference data. Unfortunately, one of the main limitations of the cycleGAN approach is that it requires two deep neural network generators at the training phase, although only one of them is used at the inference phase. The secondary auxiliary generator is needed to enforce the cycle-consistency, but the additional memory requirement and increases of the learnable parameters are the main huddles for cycleGAN training. To address this issue, here we propose a novel cycleGAN architecture using a single switchable generator. In particular, a single generator is implemented using adaptive instance normalization (AdaIN) layers so that the baseline generator converting a low-dose CT image to a routine-dose CT image can be switched to a generator converting high-dose to low-dose by simply changing the AdaIN code. Thanks to the shared baseline network, the additional memory requirement and weight increases are minimized, and the training can be done more stably even with small training data. Experimental results show that the proposed method outperforms the previous cycleGAN approaches while using only about half the parameters.

Related papers

• Low-Dose CT Image Reconstruction by Fine-Tuning a UNet Pretrained for Gaussian Denoising for the Downstream Task of Image Enhancement [3.7960472831772765]
  Computed Tomography (CT) is a widely used medical imaging modality, and reconstruction from low-dose CT data is a challenging task. In this paper, we propose a less complex two-stage method for reconstruction of LDCT images. The proposed method achieves a shared top ranking in the LoDoPaB-CT challenge and a first position with respect to the SSIM metric.
  arXiv  Detail & Related papers  (2024-03-06T08:51:09Z)
• DestripeCycleGAN: Stripe Simulation CycleGAN for Unsupervised Infrared Image Destriping [15.797480466799222]
  CycleGAN has been proven to be an advanced approach for unsupervised image restoration. We present a novel framework for single-frame infrared image destriping, named DestripeCycleGAN.
  arXiv  Detail & Related papers  (2024-02-14T11:22:20Z)
• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction [83.73429628413773]
  Supervised deep learning methods have shown the ability to remove noise in images but require accurate ground truth. We propose a novel self-supervised framework for LDCT, in which ground truth is not required for training the convolutional neural network (CNN) Numerical and experimental results show that the reconstruction accuracy of N2I with sparse views is degrading while the proposed rotational augmented Noise2Inverse (RAN2I) method keeps better image quality over a different range of sampling angles.
  arXiv  Detail & Related papers  (2023-12-19T22:40:51Z)
• Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data [125.7135706352493]
  Generative adversarial networks (GANs) typically require ample data for training in order to synthesize high-fidelity images. Recent studies have shown that training GANs with limited data remains formidable due to discriminator overfitting. This paper introduces a novel strategy called Adaptive Pseudo Augmentation (APA) to encourage healthy competition between the generator and the discriminator.
  arXiv  Detail & Related papers  (2021-11-12T18:13:45Z)
• Two-Stage Self-Supervised Cycle-Consistency Network for Reconstruction of Thin-Slice MR Images [62.4428833931443]
  The thick-slice magnetic resonance (MR) images are often structurally blurred in coronal and sagittal views. Deep learning has shown great potential to re-construct the high-resolution (HR) thin-slice MR images from those low-resolution (LR) cases. We propose a novel Two-stage Self-supervised Cycle-consistency Network (TSCNet) for MR slice reconstruction.
  arXiv  Detail & Related papers  (2021-06-29T13:29:18Z)
• TED-net: Convolution-free T2T Vision Transformer-based Encoder-decoder Dilation network for Low-dose CT Denoising [5.2227817530931535]
  We propose a convolution-free vision transformer-based-decoder Dilation net-work (TED-net) to enrich the family of LDCT denoising algorithms. Our model is evaluated on the AAPM-Mayo clinic LDCT Grand Challenge dataset, and results show outperformance over the state-of-the-art denoising methods.
  arXiv  Detail & Related papers  (2021-06-08T19:26:55Z)
• Cycle-free CycleGAN using Invertible Generator for Unsupervised Low-Dose CT Denoising [33.79188588182528]
  CycleGAN provides high-performance, ultra-fast denoising for low-dose X-ray computed tomography (CT) images. CycleGAN requires two generators and two discriminators to enforce cycle consistency. We present a novel cycle-free Cycle-GAN architecture, which consists of a single generator and a discriminator but still guarantees cycle consistency.
  arXiv  Detail & Related papers  (2021-04-17T13:23:36Z)
• Guiding GANs: How to control non-conditional pre-trained GANs for conditional image generation [69.10717733870575]
  We present a novel method for guiding generic non-conditional GANs to behave as conditional GANs. Our approach adds into the mix an encoder network to generate the high-dimensional random input that are fed to the generator network of a non-conditional GAN.
  arXiv  Detail & Related papers  (2021-01-04T14:03:32Z)
• Learning Efficient GANs for Image Translation via Differentiable Masks and co-Attention Distillation [130.30465659190773]
  Generative Adversarial Networks (GANs) have been widely-used in image translation, but their high computation and storage costs impede the deployment on mobile devices. We introduce a novel GAN compression method, termed DMAD, by proposing a Differentiable Mask and a co-Attention Distillation. Experiments show DMAD can reduce the Multiply Accumulate Operations (MACs) of CycleGAN by 13x and that of Pix2Pix by 4x while retaining a comparable performance against the full model.
  arXiv  Detail & Related papers  (2020-11-17T02:39:19Z)
• Iterative Reconstruction for Low-Dose CT using Deep Gradient Priors of Generative Model [24.024765099719886]
  Iterative reconstruction is one of the most promising ways to compensate for the increased noise due to reduction of photon flux. In this work we integrate the data-consistency as a conditional term into the iterative generative model for low-dose CT. The distance between the reconstructed image and the manifold is minimized along with data fidelity during reconstruction.
  arXiv  Detail & Related papers  (2020-09-27T06:36:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.