Search

Purpose: The low‐dose computed tomography (CT) imaging can reduce the damage caused by x‐ray radiation to the human body. However, low‐dose CT images have a different degree of artifacts than conventional CT images, and their resolution is lower than that of conventional CT images, which can affect disease diagnosis by clinicians. Therefore, methods for noise‐level reduction and resolution improvement in low‐dose CT images have inevitably become a research hotspot in the field of low‐dose CT imaging. Methods: In this paper, residual attention modules (RAMs) are incorporated into the residual encoder–decoder convolutional neural network (RED‐CNN) and generative adversarial network with Wasserstein distance (WGAN) to learn features that are beneficial to improving the performances of denoising networks, and developed models are denoted as RED‐CNN‐RAM and WGAN‐RAM, respectively. In detail, RAM is composed of a multi‐scale convolution module and an attention module built on the residual network architecture, where the attention module consists of a channel attention module and a spatial attention module. The residual network architecture solves the problem of network degradation with increased network depth. The function of the attention module is to learn which features are beneficial to reduce the noise level of low‐dose CT images to reduce the loss of detail in the final denoising images, which is also the key point of the proposed algorithms. Results: To develop a robust network for low‐dose CT image denoising, multidose‐level torso phantom images provided by a cooperating equipment vendor are used to train the network, which can improve the network's adaptability to clinical application. In addition, a clinical dataset is used to test the network's migration capabilities and clinical applicability. The experimental results demonstrate that these proposed networks can effectively remove noise and artifacts from multidose CT scans. Subjective and objective analyses of multiple groups of comparison experiments show that the proposed networks achieve good noise suppression performance while preserving the image texture details. Conclusion: In this study, two deep learning network models are developed using multidose‐level CT images acquired from a commercial spiral CT scanner. The two network models can reduce and even remove streaking artifacts, and noise from low‐dose CT images confirms the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have performed well in image denoising. Although some CNNs enlarge convolutional kernels and increase stacked convolutional layers to overcome the locality defect of convolutional operations, they may increase computational costs. In this paper, we propose a parallel and serial denoising network (PSDNet) for image denoising to preserve image texture. Specifically, the proposed PSDNet contains a parallel block (PB), a serial block (SB), and a reconstruction block (RB). A PB uses two heterogeneous sub-networks with a deformable convolution in a parallel way to extract comparative information for better-recovering image texture. A SB utilizes an enhanced residual dense architecture via combinations of a batch normalization, ReLU, and convolutional layer in a serial way to refine obtained features for obtaining more accurate noise information. A RB is responsible for reconstructing images. Experimental results reveal that our PSDNet is very effective in image denoising, according to quantitative analysis and visual analysis. Codes can be obtained at https://github.com/hellloxiaotian/PSDNet. • Heterogeneous architecture with deformable convolution can better filter noise. • An enhanced residual architecture is used to remove redundant features. • Combining a parallel and serial way can improve effects of images denoising. • Proposed network is effective for synthesized and real noisy image denoising. [ABSTRACT FROM AUTHOR]

In this paper, we propose the incorporation of noisy image patches and the impulse response of a low-pass filter (LPF) in a convolutional neural network (CNN) to denoise Poisson--Gaussian noise in low-dose computed tomography (LDCT) images. The approach is referred to as fast and flexible denoising CNN (FFDNet)-impulse response (FFDNet-IR) in this paper. The power spectrum sparsity LPF (SLPF) allows low-frequency components to pass through while suppressing higher frequency components by the sparsity approach of the power spectrum, and it is employed to determine the impulse response of LPF. Three well-known types of LPF, namely, Direct LPF, Gaussian LPF, and Butterworth LPF, are also considered to obtain the impulse response of LPF. In the FFDNet-IR, both the noisy image patches and the IR of the LPF are sequentially inputted into the FFDNet to eliminate the Poisson--Gaussian noise. This approach enhances the denoising performance in LDCT images compared with the conventional FFDNet in the evaluation metrics of the peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM). Moreover, the FFDNet-IR trained with the Poisson--Gaussian noise model demonstrates the generalization ability and effectively eliminates only Poisson or Gaussian noise. The experiments indicate that the FFDNet-IR more effectively suppresses the noise artifacts and preserves image details compared with the baseline FFDNet, as well as traditional methods such as block-matching and 3D filtering (BM3D) and nonlocal mean (NLM) for LDCT image denoising. [ABSTRACT FROM AUTHOR]

Blind image denoising and edge-preserving are two primary challenges to recover an image from low-level vision to high-level vision. Blind denoising requires a single denoiser can denoise images with any intensity of noise, and it has practical utility since accurate noise levels cannot be acquired from realistic images. On the other hand, edge preservation can provide more image features for subsequent processing which is also important for the denoising. In this paper, we propose a novel blind universal image denoiser to remove synthesis and realistic noise while preserving the image texture. The denoiser consists of noise network and prior network parallelly, and then a fusion block is used to give the weight between these two networks to balance computation cost and denoising performance. We also use the Non-subsampled Shearlet Transform (NSST) to enlarge the size of receptive field to obtain more detailed information. Extensive denoising experiments on synthetic images and realistic images show the effectiveness of our denoiser. [ABSTRACT FROM AUTHOR]

Wetland experimental images are often affected by factors such as waves, weather conditions, and lighting, resulting in severe noise in the images. In order to improve the quality and accuracy of wetland experimental images, this paper proposes a wetland experimental image denoising method based on the fast finite shearlet transform (FFST) and a deep convolutional neural network model. The FFST is used to decompose the wetland experimental images, which can capture the features of different frequencies and directions in the images. The network model has a deep network structure and powerful feature extraction capabilities. By training the model, it can learn the relevant features in the wetland experimental images, thereby achieving denoising effects. The experimental results show that, compared to traditional denoising methods, the proposed method in this paper can effectively remove noise from wetland experimental images while preserving the details and textures of the images. This is of great significance for improving the quality and accuracy of wetland experimental images. [ABSTRACT FROM AUTHOR]

Recent years, thanks to the prosperous development of deep convolutional neural network, image denoising task has achieved unprecedented achievements. However, previous researches have difficulties in keeping the balance between noise removing and textual details preserving, even bringing the negative effect, such as local blurring. To overcome these weaknesses, in this paper, we propose an innovative multi-attention complementary fusion network (MACFNet) to restore delicate texture details while eliminating noise to the greatest extent. To be specific, our proposed MACFNet mainly composes of several multi-attention complementary fusion modules (MACFMs). Firstly, we use feature extraction block (FEB) to extract basic features.Then, we use spatial attention (SA), channel attention (CA) and patch attention (PA) three different kinds of attention mechanisms to extract spatial-dimensional, channel-dimensional and patch-dimensional attention aware features, respectively. In addition, we attempt to integrate three attention mechanisms in an effective way. Instead of directly concatenate, we design a subtle complementary fusion block (CFB), which is skilled in incorporating three sub-branches characteristics adaptively. Extensive experiments are carried out on gray-scale image denoising, color image denoising and real noisy image denoising. The quantitative results (PSNR) and visual effects all prove that our proposed network achieves great performance over some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep Image Prior (DIP) is currently among the most efficient unsupervised deep learning based methods for ill-posed inverse problems in imaging. This novel framework relies on the implicit regularization provided by representing images as the output of generative Convolutional Neural Network (CNN) architectures. So far, DIP has been shown to be an effective approach when combined with classical and novel regularizers. Unfortunately, to obtain appropriate solutions, all the models proposed up to now require an accurate estimate of the regularization parameter. To overcome this difficulty, we consider a locally adapted regularized unconstrained model whose local regularization parameters are automatically estimated for additively separable regularizers. Moreover, we propose a novel constrained formulation in analogy to Morozov's discrepancy principle which enables the application of a broader range of regularizers. Both the unconstrained and the constrained models are solved via the proximal gradient descent-ascent method. Numerical results demonstrate the robustness with respect to image content, noise levels and hyperparameters of the proposed models on both denoising and deblurring of simulated as well as real natural and medical images. [ABSTRACT FROM AUTHOR]

Considering the potential risk of X-ray to patients, denoising of low-dose X-ray medical images is imperative. Inspired by deep learning, a convolutional autoencoder method for X-ray breast image denoising is proposed in this paper. First, image symmetry and flip are used to increase the number of images in the public dataset; second, the number of samples is increased further by image cropping segmentation, adding simulated noise, and producing the dataset. Finally, a convolutional autoencoder neural network model is constructed, and clean and noisy images are fed into it to complete the training. The results show that this method effectively removes noise while retaining image details in X-ray breast images, yielding higher peak signal-to-noise ratio and structural similarity index values than classical and novel denoising methods. [ABSTRACT FROM AUTHOR]

In the literature, numerous techniques have been employed to decrease noise in medical image modalities, including X-Ray (XR), Ultrasonic (Us), Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET). These techniques are organized into two main classes: the Multiple Image (MI) and the Single Image (SI) techniques. In the MI techniques, images usually obtained for the same area scanned from different points of view are used. A single image is used in the entire procedure in the SI techniques. SI denoising techniques can be carried out both in a transform or spatial domain. This paper is concerned with single-image noise reduction techniques because we deal with single medical images. The most well-known spatial domain noise reduction techniques, including Gaussian filter, Kuan filter, Frost filter, Lee filter, Gabor filter, Median filter, Homomorphic filter, Speckle reducing anisotropic diffusion (SRAD), Nonlocal-Means (NL-Means), and Total Variation (TV), are studied. Also, the transform domain noise reduction techniques, including wavelet-based and Curvelet-based techniques, and some hybridization techniques are investigated. Finally, a deep (Convolutional Neural Network) CNN-based denoising model is proposed to eliminate Gaussian and Speckle noises in different medical image modalities. This model utilizes the Batch Normalization (BN) and the ReLU as a basic structure. As a result, it attained a considerable improvement over the traditional techniques. The previously mentioned techniques are evaluated and compared by calculating qualitative visual inspection and quantitative parameters like Peak Signal-to-Noise Ratio (PSNR), Correlation Coefficient (Cr), and system complexity to determine the optimum denoising algorithm to be applied universally. Based on the quality metrics, it is demonstrated that the proposed deep CNN-based denoising model is efficient and has superior denoising performance over the traditional denoising techniques. [ABSTRACT FROM AUTHOR]

In recent years, image denoising has benefited a lot from deep neural networks. However, these models need large amounts of noisy-clean image pairs for supervision. Although there have been attempts in training denoising networks with only noisy images, existing self-supervised algorithms suffer from inefficient network training, heavy computational burden, or dependence on noise modeling. In this paper, we proposed a self-supervised framework named Neighbor2Neighbor for deep image denoising. We develop a theoretical motivation and prove that by designing specific samplers for training image pairs generation from only noisy images, we can train a self-supervised denoising network similar to the network trained with clean images supervision. Besides, we propose a regularizer in the perspective of optimization to narrow the optimization gap between the self-supervised denoiser and the supervised denoiser. We present a very simple yet effective self-supervised training scheme based on the theoretical understandings: training image pairs are generated by random neighbor sub-samplers, and denoising networks are trained with a regularized loss. Moreover, we propose a training strategy named BayerEnsemble to adapt the Neighbor2Neighbor framework in raw image denoising. The proposed Neighbor2Neighbor framework can enjoy the progress of state-of-the-art supervised denoising networks in network architecture design. It also avoids heavy dependence on the assumption of the noise distribution. We evaluate the Neighbor2Neighbor framework through extensive experiments, including synthetic experiments with different noise distributions and real-world experiments under various scenarios. The code is available online: https://github.com/TaoHuang2018/Neighbor2Neighbor. [ABSTRACT FROM AUTHOR]

Purpose: Deep learning (DL) is rapidly finding applications in low‐dose CT image denoising. While having the potential to improve the image quality (IQ) over the filtered back projection method (FBP) and produce images quickly, performance generalizability of the data‐driven DL methods is not fully understood yet. The main purpose of this work is to investigate the performance generalizability of a low‐dose CT image denoising neural network in data acquired under different scan conditions, particularly relating to these three parameters: reconstruction kernel, slice thickness, and dose (noise) level. A secondary goal is to identify any underlying data property associated with the CT scan settings that might help predict the generalizability of the denoising network. Methods: We select the residual encoder–decoder convolutional neural network (REDCNN) as an example of a low‐dose CT image denoising technique in this work. To study how the network generalizes on the three imaging parameters, we grouped the CT volumes in the Low‐Dose Grand Challenge (LDGC) data into three pairs of training datasets according to their imaging parameters, changing only one parameter in each pair. We trained REDCNN with them to obtain six denoising models. We test each denoising model on datasets of matching and mismatching parameters with respect to its training sets regarding dose, reconstruction kernel, and slice thickness, respectively, to evaluate the denoising performance changes. Denoising performances are evaluated on patient scans, simulated phantom scans, and physical phantom scans using IQ metrics including mean‐squared error (MSE), contrast‐dependent modulation transfer function (MTF), pixel‐level noise power spectrum (pNPS), and low‐contrast lesion detectability (LCD). Results: REDCNN had larger MSE when the testing data were different from the training data in reconstruction kernel, but no significant MSE difference when varying slice thickness in the testing data. REDCNN trained with quarter‐dose data had slightly worse MSE in denoising higher‐dose images than that trained with mixed‐dose data (17%–80%). The MTF tests showed that REDCNN trained with the two reconstruction kernels and slice thicknesses yielded images of similar image resolution. However, REDCNN trained with mixed‐dose data preserved the low‐contrast resolution better compared to REDCNN trained with quarter‐dose data. In the pNPS test, it was found that REDCNN trained with smooth‐kernel data could not remove high‐frequency noise in the test data of sharp kernel, possibly because the lack of high‐frequency noise in the smooth‐kernel data limited the ability of the trained model in removing high‐frequency noise. Finally, in the LCD test, REDCNN improved the lesion detectability over the original FBP images regardless of whether the training and testing data had matching reconstruction kernels. Conclusions: REDCNN is observed to be poorly generalizable between reconstruction kernels, more robust in denoising data of arbitrary dose levels when trained with mixed‐dose data, and not highly sensitive to slice thickness. It is known that reconstruction kernel affects the in‐plane pNPS shape of a CT image, whereas slice thickness and dose level do not, so it is possible that the generalizability performance of this CT image denoising network highly correlates to the pNPS similarity between the testing and training data. [ABSTRACT FROM AUTHOR]

BACKGROUND: The noise in magnetic resonance (MR) images causes severe issues for medical diagnosis purposes. OBJECTIVE: In this paper, we propose a discriminative learning based convolutional neural network denoiser to denoise the MR image data contaminated with noise. METHODS: The proposed method incorporates the use of depthwise separable convolution along with local response normalization with modified hyperparameters and internal skip connections to denoise the contaminated MR images. Moreover, the addition of parametric RELU instead of normal conventional RELU in our proposed architecture gives more stable and fine results. The denoised images were further segmented to test the appropriateness of the results. The network is trained on one dataset and tested on other dataset produces remarkably good results. RESULTS: Our proposed network was used to denoise the images of different noise levels, and it yields better performance as compared with various networks. The SSIM and PSNR showed an average improvement of (7.2 ± 0.002) % and (8.5 ± 0.25) % respectively when tested on different datasets without retaining the network. An improvement of 5% and 6% was achieved in the values of mean intersection over union (mIoU) and BF score when the denoised images were segmented for testing the relevancy in biomedical imaging applications. The statistical test suggests that the obtained results are statistically significant as p < 0.05. CONCLUSION: The denoised images obtained are more clinically suitable for medical image diagnosis purposes, as depicted by the evaluation parameters. Further, external clinical validation was performed by an experienced radiologist for testing the validation of the resulting images. [ABSTRACT FROM AUTHOR]

As a preprocessing module, denoising can affect the overall image processing; thus, image denoising algorithms are of high significance for image processing and have been studied for several decades. Theoretically, the performances of existing algorithms can be significantly improved, but these improvements are indeed slowing down. To significantly improve the denoising performance, we propose a denoising network method called the fast denoising fusion network (FDFNet). It combines the advantages of a neural network based on block matching and 3D filtering (BM3D-Net) and a fast and flexible denoising convolutional neural network (FFDNet), which simultaneously utilizes internal and external priors to remove noise in a given image; thus, it is a fast and efficient denoising method that delivers superior performance. BM3D-Net and FFDNet can generate two images as basic estimates for fusion. We adopt a combination model to receive the two estimates, which can fuse them effectively to obtain a latent image. Through testing on standard datasets, our experimental results reveal that FDFNet outperformed state-of-the-art denoising methods in terms of both subjective and objective quality. By implementing the entire method on a CNN, the proposed method could exploit the GPU to achieve a higher efficiency. Because the proposed method combines internal and external priors effectively, it could utilize complementary prior knowledge to derive more information. [ABSTRACT FROM AUTHOR]

Nowadays, skin cancer is one of the most dangerous forms of cancer found in humans. There are various types of skin cancer, like basal, melanoma, carcinoma, and the squamous cell from which the melanoma is unpredictable. Thus, skin cancer detection in the early stage is very useful to treat it successfully. Hence, this study introduces a new algorithm called social bat optimisation algorithm for skin cancer detection. Initially, the pre-processing is done for the input image to eliminate the noise and artefacts present in the image. Then, the pre-processed image is fed to the feature extraction step where the features are extracted based on convolutional neural network features, and the local pixel pattern-based texture feature (local PPBTF). Here, the PPBTF is the combination of texture features and pixel pattern-based features in which the equation of PPBTF is modified based on the local binary pattern. Subsequently, the classification is done based on the extracted features using a deep stacked auto-encoder, which is trained by the proposed social bat optimisation. The performance of skin cancer detection based on the proposed model is evaluated based on accuracy, sensitivity, and specificity. The proposed model achieves the maximal accuracy of 93.38%, maximal sensitivity of 95%, and the maximal specificity of 96% for K-fold. [ABSTRACT FROM AUTHOR]

Deep learning has been successfully introduced for 2D-image denoising, but it is still unsatisfactory for hyperspectral image (HSI) denoising due to the unacceptable computational complexity of the end-to-end training process and the difficulty of building a universal 3D-image training dataset. In this paper, instead of developing an end-to-end deep learning denoising network, we propose an HSI denoising framework for the removal of mixed Gaussian impulse noise, in which the denoising problem is modeled as a convolutional neural network (CNN) constrained non-negative matrix factorization problem. Using the proximal alternating linearized minimization, the optimization can be divided into three steps: the update of the spectral matrix, the update of the abundance matrix, and the estimation of the sparse noise. Then, we design the CNN architecture and proposed two training schemes, which can allow the CNN to be trained with a 2D-image dataset. Compared with the state-of-the-art denoising methods, the proposed method has a relatively good performance on the removal of the Gaussian and mixed Gaussian impulse noises. More importantly, the proposed model can be only trained once by a 2D-image dataset but can be used to denoise HSIs with different numbers of channel bands. [ABSTRACT FROM AUTHOR]