A residual U-Net network with image prior for 3D image denoising

Abascal, Juan F P J; Bussod, Suzanne; Ducros, Nicolas; Douek, P.; Chappard, Christine; Peyrin, Françoise

doi:10.23919/eusipco47968.2020.9287607

Cited by 15 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…U-Net-fairSIM U-Net is also a popular learning architecture that is extensively used in the domain of image restoration such as image denoising and super-resolution [23,30,31]. In the pipeline proposed for RED-fairSIM, we replaced the RED-Net by U-Net and analyzed the resulting super-resolution images.…”

Section: Sr-redsim: Sr-sim Image Denoising and Reconstruction Using The Super-resolution Redsim Methodsmentioning

confidence: 99%

Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images

et al. 2021

View full text Add to dashboard Cite

Super-resolution structured illumination microscopy (SR-SIM) provides an up to two-fold enhanced spatial resolution of fluorescently labeled samples. The reconstruction of high quality SR-SIM images critically depends on patterned illumination with high modulation contrast. Noisy raw image data, e.g. as a result of low excitation power or low exposure times, result in reconstruction artifacts. Here, we demonstrate deep-learning based SR-SIM image denoising that results in high quality reconstructed images. A residual encoding-decoding convolution neural network (RED-Net) was used to successfully denoise computationally reconstructed noisy SR-SIM images. We also demonstrate the entirely deep-learning based denoising and reconstruction of raw SIM images into high-resolution SR-SIM images. Both image reconstruction methods prove to be very robust against image reconstruction artifacts and generalize very well over various noise levels. The combination of computational reconstruction and subsequent denoising via RED-Net shows very robust performance during inference after training even if the microscope settings change.

show abstract

Section: Sr-redsim: Sr-sim Image Denoising and Reconstruction Using The Super-resolution Redsim Methodsmentioning

confidence: 99%

Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images

et al. 2021

View full text Add to dashboard Cite

show abstract

“…An AWGN noise level map-guided image denoising network based on Unet was proposed in [16], which has the plug-and-play capability that makes the network more portable. Similar U-net inspired approaches with different residual and dense connections were proposed in [17], [18], [19], [20], [21], [22], and [23]. Another U-net based architecture in [20] used a cascading U-net with multi-scale input feature supervision and residual dense blocks.…”

Section: Introductionmentioning

confidence: 99%

EFID: Edge-Focused Image Denoising Using a Convolutional Neural Network

Park

Lee

2023

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose an edge-focused image denoising convolutional neural network for the restoration of noisy images corrupted with additive white Gaussian noise (AWGN). First, the edge information for an input image is obtained for each RGB channel using the simple Laplacian edge operator on a smoothened image using the smoothen mask. Second, residual convolutional blocks, where each block comprises two parallel depth layers (one for an image channel and the other for respective edge channels), perform image and edge processing. Finally, the processed image and edge features are mixed and mapped using a single convolutional layer into the restored image. Our proposed parallel image and edge processing blocks can recover edges and fine structures while smoothing out the noise. In addition, our proposed network is efficiently designed such that the total number of weight parameters can be considerably reduced compared with conventional methods. Experimental results show that the proposed model is more effective in preserving textures and edges while removing noise and achieves up to 0.8 dB higher PSNR and 0.05 higher SSIM on a real image dataset than conventional methods.INDEX TERMS Convolutional neural networks, deep learning, denoising, edge guidance, Gaussian noise.

show abstract

“…The PET scan is a nuclear medicine imaging technique that monitors the normal and abnormal physiologic actions of living organisms and detects disease inside the body. This technology has revolutionized medical diagnostics, enabling early disease detection and personalized treatment planning 1,2 . Over the past several decades, the efficiency and effectiveness of PET imaging have grown exponentially with the integration of advanced technologies, such as upgrading equipment hardware and software.…”

Section: Introductionmentioning

confidence: 99%

“…These innovative approaches leverage the full potential of DL to enhance the quality of imaging data. Other proposed methods include a residual network (RNET) method for denoising PET images, harnessing the capacity of deep neural network (DNN) to learn complex patterns in noisy data 2,16,17 . A DNN‐based approach has been instrumental in improving whole‐body PET scan images and lowering image noise, improving the accuracy of disease staging and treatment planning 18,19 .…”

Section: Introductionmentioning

confidence: 99%

“…This technology has revolutionized medical diagnostics, enabling early disease detection and personalized treatment planning. 1,2 Over the past several decades, the efficiency and effectiveness of PET imaging have grown exponentially with the integration of advanced technologies, such as upgrading equipment hardware and software. These innovations have not only improved image quality but also reduced radiation exposure to patients, making PET scans safer and more accessible.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Utilizing deep learning techniques to improve image quality and noise reduction in preclinical low‐dose PET images in the sinogram domain

Manoj Doss,

Chen

2023

Medical Physics

View full text Add to dashboard Cite

BackgroundLow‐dose positron emission tomography (LD‐PET) imaging is commonly employed in preclinical research to minimize radiation exposure to animal subjects. However, LD‐PET images often exhibit poor quality and high noise levels due to the low signal‐to‐noise ratio. Deep learning (DL) techniques such as generative adversarial networks (GANs) and convolutional neural network (CNN) have the capability to enhance the quality of images derived from noisy or low‐quality PET data, which encodes critical information about radioactivity distribution in the body.PurposeOur objective was to optimize the image quality and reduce noise in preclinical PET images by utilizing the sinogram domain as input for DL models, resulting in improved image quality as compared to LD‐PET images.MethodsA GAN and CNN model were utilized to predict high‐dose (HD) preclinical PET sinograms from the corresponding LD preclinical PET sinograms. In order to generate the datasets, experiments were conducted on micro‐phantoms, animal subjects (rats), and virtual simulations. The quality of DL‐generated images was weighted by performing the following quantitative measures: structural similarity index measure (SSIM), root mean squared error (RMSE), peak signal‐to‐noise ratio (PSNR), signal‐to‐noise ratio (SNR), and contrast‐to‐noise ratio (CNR). Additionally, DL input and output were both subjected to a spatial resolution calculation of full width half maximum (FWHM) and full width tenth maximum (FWTM). DL outcomes were then compared with the conventional denoising algorithms such as non‐local means (NLM), block‐matching, and 3D filtering (BM3D).ResultsThe DL models effectively learned image features and produced high‐quality images, as reflected in the quantitative metrics. Notably, the FWHM and FWTM values of DL PET images exhibited significantly improved accuracy compared to LD, NLM, and BM3D PET images, and just as precise as HD PET images. The MSE loss underscored the excellent performance of the models, indicating that the models performed well. To further improve the training, the generator loss (G loss) was increased to a value higher than the discriminator loss (D loss), thereby achieving convergence in the GAN model.ConclusionsThe sinograms generated by the GAN network closely resembled real HD preclinical PET sinograms and were more realistic than LD. There was a noticeable improvement in image quality and noise factor in the predicted HD images. Importantly, DL networks did not fully compromise the spatial resolution of the images.

show abstract

A residual U-Net network with image prior for 3D image denoising

Cited by 15 publications

References 19 publications

Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images

Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images

EFID: Edge-Focused Image Denoising Using a Convolutional Neural Network

Utilizing deep learning techniques to improve image quality and noise reduction in preclinical low‐dose PET images in the sinogram domain

Contact Info

Product

Resources

About