CT super-resolution using multiple dense residual block based GAN

Zhang, Xiong; Feng, Congli; Wang, Anhong; Yang, Linlin; Hao, Yawen

doi:10.1007/s11760-020-01790-5

“…PixelCNNs have been used to perform super resolution on 2d images [32], but to the best of our knowledge it has never been used on 3d images and it's the first time it has been used to generate high fidelity images. Deep learning based super resolution has been an active area of research and includes many models such as SRGAN [33], MFTV [34], FSRCNN [35], SRResNet-V54 [36], LapSRN [37], and multiple dense residual block based GANs [38]. These types of models are designed for 3d images by doing grid based upsampling using transposed convolutions.…”

Section: Discussionmentioning

confidence: 99%

Towards texture accurate slice interpolation of medical images using PixelMiner

Rogers

¹

,

Keek

²

,

Beuque

³

et al. 2023

Computers in Biology and Medicine

0

View full text Add to dashboard Cite

“…PixelCNNs have been used to perform super resolution on 2d images [32], but to the best of our knowledge it has never been used on 3d images and it's the first time it has been used to generate high fidelity images. Deep learning based super resolution has been an active area of research and includes many models such as SRGAN [33], MFTV [34], FSRCNN [35], SRResNet-V54 [36], LapSRN [37], and multiple dense residual block based GANs [38]. These types of models are designed for 3d images by doing grid based upsampling using transposed convolutions.…”

Section: Discussionmentioning

confidence: 99%

Towards Texture Accurate Slice Interpolation of Medical Images Using PixelMiner

Roger¹,

Lambin²,

Keek³

et al. 2021

Preprint

View full text Add to dashboard Cite

Quantitative analysis models are used for various medical imaging tasks such as registration, classification, object detection, and segmentation which all benefit from high-quality imaging. We propose PixelMiner, a convolution-based deep-learning model which interpolates computed tomography (CT) imaging slices while better preserving quantitative imaging features than standard interpolation methods. PixelMiner was designed to produce texture-accurate slice interpolations by trading off pixel accuracy for texture accuracy using a novel architecture. PixelMiner was trained on a large dataset consisting of 7092 lung CT scans and validated using external lung CT datasets. We demonstrated the model's effectiveness by using edge preservation ratio (EPR), compared texture features commonly used in radiomics, and performed a qualitative assessment by human trial. PixelMiner had the highest EPR 82% (p<.01) of the time compared to the closest competing method. It had the lowest texture error, using a normalized root mean squared error (NRMSE) of 0.11 (p<.01), with the highest reproducibility of concordance correlation coefficient (CCC) ≥ 0.85 (p<.01). PixelMiner was chosen 72% of the time by human evaluation (p<.01). PixelMiner was not only demonstrated quantitatively to have improved structural and textural constructions but also shown to be preferable qualitatively.

show abstract

“…Many researchers studied different image denoising models by employing various loss functions. The mean squared error (MSE) or L2 loss function is the most widely used for many GAN-based models [ 14 , 15 , 24 ]. However, it includes the regression-to-mean problem, which causes oversmoothing and texture information loss.…”

Section: Methodsmentioning

confidence: 99%

“…Deep learning methods have already applied to medical imaging denoising, such as convolutional neural network denoising autoencoder (CNN DAE) [ 13 ]. At present, generative adversarial network (GAN) achieves great progress for image denoising with a min-max two-player game between the generative network and the discriminator network [ 14 , 15 ]. Nevertheless, as an unconditional generative model, the samples generated by GAN in the training process cannot be controlled and lack diversity [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

A Novel Medical Image Denoising Method Based on Conditional Generative Adversarial Network

Li

¹

,

Zhang

²

,

Shi

³

et al. 2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Medical image quality is highly relative to clinical diagnosis and treatment, leading to a popular research topic of medical image denoising. Image denoising based on deep learning methods has attracted considerable attention owing to its excellent ability of automatic feature extraction. Most existing methods for medical image denoising adapted to certain types of noise have difficulties in handling spatially varying noise; meanwhile, image detail losses and structure changes occurred in the denoised image. Considering image context perception and structure preserving, this paper firstly introduces a medical image denoising method based on conditional generative adversarial network (CGAN) for various unknown noises. In the proposed architecture, noise image with the corresponding gradient image is merged as network conditional information, which enhances the contrast between the original signal and noise according to the structural specificity. A novel generator with residual dense blocks makes full use of the relationship among convolutional layers to explore image context. Furthermore, the reconstruction loss and WGAN loss are combined as the objective loss function to ensure the consistency of denoised image and real image. A series of experiments for medical image denoising are conducted with the denoising results of PSNR = 33.2642 and SSIM = 0.9206 on JSRT datasets and PSNR = 35.1086 and SSIM = 0.9328 on LIDC datasets. Compared with the state-of-the-art methods, the superior performance of the proposed method is outstanding.

show abstract

CT super-resolution using multiple dense residual block based GAN

Cited by 23 publications

References 21 publications

Towards texture accurate slice interpolation of medical images using PixelMiner

Towards texture accurate slice interpolation of medical images using PixelMiner

Towards Texture Accurate Slice Interpolation of Medical Images Using PixelMiner

A Novel Medical Image Denoising Method Based on Conditional Generative Adversarial Network

Contact Info

Product

Resources

About