RESUMO
BACKGROUND: Recently, X-rays have been widely used to detect complex structural workpieces. Due to the uneven thickness of the workpiece and the high dynamic range of the X-ray image itself, the detailed internal structure of the workpiece cannot be clearly displayed. OBJECTIVE: To solve this problem, we propose an image enhancement algorithm based on a multi-scale local edge-preserving filter. METHODS: Firstly, the global brightness of the image is enhanced through logarithmic transformation. Then, to enhance the local contrast, we propose utilizing the gradient decay function based on fuzzy entropy to process the gradient and then incorporate the gradient into the energy function of the local edge-preserving filter (LEP) as a constraint term. Finally, multiple base layers and detail layers are obtained through filtering multi-scale decomposition. All detail layers are enhanced and fused using S-curve mapping to improve contrast further. RESULTS: This method is competitive in both quantitative indices and visual perception quality. CONCLUSIONS: The experimental results demonstrate that the proposed method significantly enhances various complex workpieces and is highly efficient.
Assuntos
Algoritmos , Entropia , Lógica Fuzzy , Processamento de Imagem Assistida por Computador/métodos , Intensificação de Imagem Radiográfica/métodos , HumanosRESUMO
OBJECTIVES: In the past, guided image filtering (GIF)-based methods often utilized total variation (TV)-based methods to reconstruct guidance images. And they failed to reconstruct the intricate details of complex clinical images accurately. To address these problems, we propose a new sparse-view CT reconstruction method based on group-based sparse representation using weighted guided image filtering. METHODS: In each iteration of the proposed algorithm, the result constrained by the group-based sparse representation (GSR) is used as the guidance image. Then, the weighted guided image filtering (WGIF) was used to transfer the important features from the guidance image to the reconstruction of the SART method. RESULTS: Three representative slices were tested under 64 projection views, and the proposed method yielded the best visual effect. For the shoulder case, the PSNR can achieve 48.82, which is far superior to other methods. CONCLUSIONS: The experimental results demonstrate that our method is more effective in preserving structures, suppressing noise, and reducing artifacts compared to other methods.
RESUMO
Low-dose computed tomography (LDCT) has been widely concerned in the field of medical imaging because of its low radiation hazard to humans. However, under low-dose radiation scenarios, a large amount of noise/artifacts are present in the reconstructed image, which reduces the clarity of the image and is not conducive to diagnosis. To improve the LDCT image quality, we proposed a combined frequency separation network and Transformer (FSformer) for LDCT denoising. Firstly, FSformer decomposes the LDCT images into low-frequency images and multi-layer high-frequency images by frequency separation blocks. Then, the low-frequency components are fused with the high-frequency components of different layers to remove the noise in the high-frequency components with the help of the potential texture of low-frequency parts. Next, the estimated noise images can be obtained by using Transformer stage in the frequency aggregation denoising block. Finally, they are fed into the reconstruction prediction block to obtain improved quality images. In addition, a compound loss function with frequency loss and Charbonnier loss is used to guide the training of the network. The performance of FSformer has been validated and evaluated on AAPM Mayo dataset, real Piglet dataset and clinical dataset. Compared with previous representative models in different architectures, FSformer achieves the optimal metrics with PSNR of 33.7714 dB and SSIM of 0.9254 on Mayo dataset, the testing time is 1.825 s. The experimental results show that FSformer is a state-of-the-art (SOTA) model with noise/artifact suppression and texture/organization preservation. Moreover, the model has certain robustness and can effectively improve LDCT image quality.
Assuntos
Processamento de Imagem Assistida por Computador , Tomografia Computadorizada por Raios X , Animais , Humanos , Suínos , Razão Sinal-Ruído , Tomografia Computadorizada por Raios X/métodos , Processamento de Imagem Assistida por Computador/métodos , AlgoritmosRESUMO
In the medical field, computed tomography (CT) is a commonly used examination method, but the radiation generated increases the risk of illness in patients. Therefore, low-dose scanning schemes have attracted attention, in which noise reduction is essential. We propose a purposeful and interpretable decomposition iterative network (DISN) for low-dose CT denoising. This method aims to make the network design interpretable and improve the fidelity of details, rather than blindly designing or using deep CNN architecture. The experiment is trained and tested on multiple data sets. The results show that the DISN method can restore the low-dose CT image structure and improve the diagnostic performance when the image details are limited. Compared with other algorithms, DISN has better quantitative and visual performance, and has potential clinical application prospects.
Assuntos
Algoritmos , Processamento de Imagem Assistida por Computador , Doses de Radiação , Tomografia Computadorizada por Raios X , Tomografia Computadorizada por Raios X/métodos , Humanos , Processamento de Imagem Assistida por Computador/métodos , Razão Sinal-Ruído , Imagens de FantasmasRESUMO
Objective.Real-time brain monitoring is of importance for intraoperative surgeries and intensive care unit, in order to take timely clinical interventions. Electroencephalogram (EEG) is a conventional technique for recording neural excitations (e.g. brain waves) in the cerebral cortex, and near infrared diffuse correlation spectroscopy (DCS) is an emerging technique that can directly measure the cerebral blood flow (CBF) in microvasculature system. Currently, the relationship between the neural activities and cerebral hemodynamics that reflects the vasoconstriction features of cerebral vessels, especially under both active and passive situation, has not been elucidated thus far, which triggers the motivation of this study.Approach.We used the verbal fluency test as an active cognitive stimulus to the brain, and we manipulated blood pressure changes as a passive challenge to the brain. Under both protocols, the CBF and EEG responses were longitudinally monitored throughout the cerebral stimulus. Power spectrum approaches were applied the EEG signals and compared with CBF responses.Main results.The results show that the EEG response was significantly faster and larger in amplitude during the active cognitive task, when compared to the CBF, but with larger individual variability. By contrast, CBF is more sensitive when response to the passive task, and with better signal stability. We also found that there was a correlation (p< 0.01,r= 0.866,R2= 0.751) between CBF and EEG in initial response during the active task, but no significant correlation (p> 0.05) was found during the passive task. The similar relations were also found between regional brain waves and blood flow.Significance.The asynchronization and correlation between the two measurements indicates the necessity of monitoring both variables for comprehensive understanding of cerebral physiology. Deep exploration of their relationships provides promising implications for DCS/EEG integration in the diagnosis of various neurovascular and psychiatric diseases.
Assuntos
Encéfalo , Circulação Cerebrovascular , Circulação Cerebrovascular/fisiologia , Eletroencefalografia , Espectroscopia de Luz Próxima ao Infravermelho/métodos , HemodinâmicaRESUMO
BACKGROUND: Recently, one promising approach to suppress noise/artifacts in low-dose CT (LDCT) images is the CNN-based approach, which learns the mapping function from LDCT to normal-dose CT (NDCT). However, most CNN-based methods are purely data-driven, thus lacking sufficient interpretability and often losing details. OBJECTIVE: To solve this problem, we propose a deep convolutional dictionary learning method for LDCT denoising, in which a novel convolutional dictionary learning model with adaptive window (CDL-AW) is designed, and a corresponding enhancement-based convolutional dictionary learning network (called ECDAW-Net) is constructed to unfold the CDL-AW model iteratively using the proximal gradient descent technique. METHODS: In detail, the adaptive window-constrained convolutional dictionary atom is proposed to alleviate spectrum leakage caused by data truncation during convolution. Furthermore, in the ECDAW-Net, a multi-scale edge extraction module that consists of LoG and Sobel convolution layers is proposed in the unfolding iteration, to supplement lost textures and details. Additionally, to further improve the detail retention ability, the ECDAW-Net is trained by the compound loss function of the pixel-level MSE loss and the proposed patch-level loss, which can assist to retain richer structural information. RESULTS: Applying ECDAW-Net to the Mayo dataset, we obtained the highest peak signal-to-noise ratio (33.94) and sub-optimal structural similarity (0.92). CONCLUSIONS: Compared with some state-of-art methods, the interpretable ECDAW-Net performs well in suppressing noise/artifacts and preserving textures of tissue.
Assuntos
Tomografia Computadorizada por Raios X , Razão Sinal-RuídoRESUMO
X-ray images frequently have low contrast and lost edge features because of the complexity of objects, attenuation of reflected light, and scattering superposition of rays. Image features are frequently lost in traditional enhancement methods. In this paper, we use a ray scattering model to estimate coarsely clear images and an encoder-decoder network and multi-scale feature extraction module to add multi-scale and detail information to the images. To selectively emphasize useful features, a dual attention module and UnsharpMasking with learnable correction factors are used. The results of the experiments demonstrate that the method may significantly enhance the quality of x-ray images.
RESUMO
Objective.Various deep learning methods have recently been used for low dose CT (LDCT) denoising. Aggressive denoising may destroy the edge and fine anatomical structures of CT images. Therefore a key issue in LDCT denoising tasks is the difficulty of balancing noise/artifact suppression and edge/structure preservation.Approach.We proposed an LDCT denoising network based on the encoder-decoder structure, namely the Learnable PM diffusion coefficient and efficient attention network (PMA-Net). First, using the powerful feature modeling capability of partial differential equations, we constructed a multiple learnable edge module to generate precise edge information, incorporating the anisotropic image processing idea of Perona-Malik (PM) model into the neural network. Second, a multiscale reformative coordinate attention module was designed to extract multiscale information. Non-overlapping dilated convolution capturing abundant contextual content was combined with coordinate attention which could embed the spatial location information of important features into the channel attention map. Finally, we imposed additional constraints on the edge information using edge-enhanced multiscale perceptual loss to avoid structure loss and over-smoothing.Main results.Experiments are conducted on simulated and real datasets. The quantitative and qualitative results show that the proposed method has better performance in suppressing noise/artifacts and preserving edges/structures.Significance.This work proposes a novel edge feature extraction method that unfolds partial differential equation into neural networks, which contributes to the interpretability and clinical application value of neural network.
Assuntos
Processamento de Imagem Assistida por Computador , Redes Neurais de Computação , Anisotropia , Tomografia Computadorizada por Raios X , Razão Sinal-RuídoRESUMO
BACKGROUND: Low-dose CT (LDCT) images usually contain serious noise and artifacts, which weaken the readability of the image. OBJECTIVE: To solve this problem, we propose a compound feature attention network with edge enhancement for LDCT denoising (CFAN-Net), which consists of an edge-enhanced module and a proposed compound feature attention block (CFAB). METHODS: The edge enhancement module extracts edge details with the trainable Sobel convolution. CFAB consists of an interactive feature learning module (IFLM), a multi-scale feature fusion module (MFFM), and a joint attention module (JAB), which removes noise from LDCT images in a coarse-to-fine manner. First, in IFLM, the noise is initially removed by cross-latitude interactive judgment learning. Second, in MFFM, multi-scale and pixel attention are integrated to explore fine noise removal. Finally, in JAB, we focus on key information, extract useful features, and improve the efficiency of network learning. To construct a high-quality image, we repeat the above operation by cascading CFAB. RESULTS: By applying CFAN-Net to process the 2016 NIH AAPM-Mayo LDCT challenge test dataset, experiments show that the peak signal-to-noise ratio value is 33.9692 and the structural similarity value is 0.9198. CONCLUSIONS: Compared with several existing LDCT denoising algorithms, CFAN-Net effectively preserves the texture of CT images while removing noise and artifacts.
Assuntos
Algoritmos , Tomografia Computadorizada por Raios X , Tomografia Computadorizada por Raios X/métodos , Razão Sinal-Ruído , Artefatos , Processamento de Imagem Assistida por ComputadorRESUMO
Sparse-view CT is an efficient way for low dose scanning but degrades image quality. Inspired by the successful use of non-local attention in natural image denoising and compression artifact removal, we proposed a network combining integrated attention and iterative optimization learning for sparse-view CT reconstruction (CAIR). Specifically, we first unrolled the proximal gradient descent into a deep network and added an enhanced initializer between the gradient term and the approximation term. It can enhance the information flow between different layers, fully preserve the image details, and improve the network convergence speed. Secondly, the integrated attention module was introduced into the reconstruction process as a regularization term. It adaptively fuses the local and non-local features of the image which are used to reconstruct the complex texture and repetitive details of the image, respectively. Note that we innovatively designed a one-shot iteration strategy to simplify the network structure and reduce the reconstruction time while maintaining image quality. Experiments showed that the proposed method is very robust and outperforms state-of-the-art methods in terms of both quantitative and qualitative, greatly improving the preservation of structures and the removal of artifacts.
Assuntos
Compressão de Dados , Tomografia Computadorizada por Raios X , Tomografia Computadorizada por Raios X/métodos , Processamento de Imagem Assistida por Computador/métodos , Algoritmos , Imagens de Fantasmas , ArtefatosRESUMO
BACKGROUND: In view of the underlying health risks posed by X-ray radiation, the main goal of the present research is to achieve high-quality CT images at the same time as reducing x-ray radiation. In recent years, convolutional neural network (CNN) has shown excellent performance in removing low-dose CT noise. However, previous work mainly focused on deepening and feature extraction work on CNN without considering fusion of features from frequency domain and image domain. OBJECTIVE: To address this issue, we propose to develop and test a new LDCT image denoising method based on a dual-domain fusion deep convolutional neural network (DFCNN). METHODS: This method deals with two domains, namely, the DCT domain and the image domain. In the DCT domain, we design a new residual CBAM network to enhance the internal and external relations of different channels while reducing noise to promote richer image structure information. For the image domain, we propose a top-down multi-scale codec network as a denoising network to obtain more acceptable edges and textures while obtaining multi-scale information. Then, the feature images of the two domains are fused by a combination network. RESULTS: The proposed method was validated on the Mayo dataset and the Piglet dataset. The denoising algorithm is optimal in both subjective and objective evaluation indexes as compared to other state-of-the-art methods reported in previous studies. CONCLUSIONS: The study results demonstrate that by applying the new fusion model denoising, denoising results in both image domain and DCT domain are better than other models developed using features extracted in the single image domain.
Assuntos
Redes Neurais de Computação , Tomografia Computadorizada por Raios X , Animais , Suínos , Tomografia Computadorizada por Raios X/métodos , Razão Sinal-Ruído , Algoritmos , Processamento de Imagem Assistida por Computador/métodosRESUMO
A passive substrate integrated waveguide (SIW) sensor based on the complementary split ring resonator (CSRR) is presented for pressure detection in high-temperature environments. The sensor pressure sensing mechanism is described through circuit analysis and the electromagnetic coupling principle. The pressure sensor is modeled in high frequency structure simulator (HFSS), designed through parameter optimization. According to the optimized parameters, the sensor was customized and fabricated on a high temperature co-fired ceramic (HTCC) substrate using the three-dimensional co-fired technology and screen-printing technology. The pressure sensor was tested in the high-temperature pressure furnace and can work stably in the ambient environment of 25-500 °C and 10-300 kPa. The pressure sensitivity is 139.77 kHz/kPa at 25 °C, and with increasing temperature, the sensitivity increases to 191.97 kHz/kPa at 500 °C. The temperature compensation algorithm is proposed to achieve accurate acquisition of pressure signals in a high-temperature environment.
RESUMO
BACKGROUND: Low-Dose computed tomography (LDCT) reduces radiation damage to patients, however, the reconstructed images contain severe noise, which affects doctors' diagnosis of the disease. The convolutional dictionary learning has the advantage of the shift-invariant property. The deep convolutional dictionary learning algorithm (DCDicL) combines deep learning and convolutional dictionary learning, which has great suppression effects on Gaussian noise. However, applying DCDicL to LDCT images cannot get satisfactory results. OBJECTIVE: To address this challenge, this study proposes and tests an improved deep convolutional dictionary learning algorithm for LDCT image processing and denoising. METHODS: First, we use a modified DCDicL algorithm to improve the input network and make it do not need to input noise intensity parameter. Second, we use DenseNet121 to replace the shallow convolutional network to learn the prior on the convolutional dictionary, which can obtain more accurate convolutional dictionary. Last, in the loss function, we add MSSIM to enhance the detail retention ability of the model. RESULTS: The experimental results on the Mayo dataset show that the proposed model obtained an average value of 35.2975âdB in PSNR, which is 0.2954 -1.0573âdB higher than the mainstream LDCT algorithm, indicating the excellent denoising performance. CONCLUSION: The study demonstrates that the proposed new algorithm can effectively improve the quality of LDCT images acquired in the clinical practice.
Assuntos
Processamento de Imagem Assistida por Computador , Tomografia Computadorizada por Raios X , Humanos , Razão Sinal-Ruído , Processamento de Imagem Assistida por Computador/métodos , Tomografia Computadorizada por Raios X/métodos , Algoritmos , Redes Neurais de ComputaçãoRESUMO
Computed tomography (CT) is an imaging technique extensively used in medical treatment, but too much radiation dose in a CT scan will cause harm to the human body. Decreasing the dose of radiation will result in increased noise and artifacts in the reconstructed image, blurring the internal tissue and edge details. To get high-quality CT images, we present a multi-scale feature fusion network (MSFLNet) for low-dose CT (LDCT) denoising. In our MSFLNet, we combined multiple feature extraction modules, effective noise reduction modules, and fusion modules constructed using the attention mechanism to construct a horizontally connected multi-scale structure as the overall architecture of the network, which is used to construct different levels of feature maps at all scales. We innovatively define a composite loss function composed of pixel-level loss based on MS-SSIM-L1 and edge-based edge loss for LDCT denoising. In short, our approach learns a rich set of features that combine contextual information from multiple scales while maintaining the spatial details of denoised CT images. Our laboratory results indicate that compared with the existing methods, the peak signal-to-noise ratio (PSNR) value of CT images of the AAPM dataset processed by the new model is 33.6490, and the structural similarity (SSIM) value is 0.9174, which also achieves good results on the Piglet dataset with different doses. The results also show that the method removes noise and artifacts while effectively preserving CT images' architecture and grain information.
Assuntos
Artefatos , Tomografia Computadorizada por Raios X , Animais , Humanos , Suínos , Doses de Radiação , Tomografia Computadorizada por Raios X/métodos , Razão Sinal-Ruído , Processamento de Imagem Assistida por Computador/métodos , AlgoritmosRESUMO
Low-dose computed tomography (LDCT) can effectively reduce radiation exposure in patients. However, with such dose reductions, large increases in speckled noise and streak artifacts occur, resulting in seriously degraded reconstructed images. The non-local means (NLM) method has shown potential for improving the quality of LDCT images. In the NLM method, similar blocks are obtained using fixed directions over a fixed range. However, the denoising performance of this method is limited. In this paper, a region-adaptive NLM method is proposed for LDCT image denoising. In the proposed method, pixels are classified into different regions according to the edge information of the image. Based on the classification results, the adaptive searching window, block size and filter smoothing parameter could be modified in different regions. Furthermore, the candidate pixels in the searching window could be filtered based on the classification results. In addition, the filter parameter could be adjusted adaptively based on intuitionistic fuzzy divergence (IFD). The experimental results showed that the proposed method performed better in LDCT image denoising than several of the related denoising methods in terms of numerical results and visual quality.
RESUMO
Intravesical instillation has been considered an efficient route for detecting bladder cancer. However, only a small fraction of administered dose permeates into tumor tissues, and insufficient retention time limits their application. In this work, a novel intravesical bidirectional perfusion-like administered mode was developed to improve diagnostic accuracy of bladder tumor imaging. Specifically, the ultrasmall AuPd-P-FA Nanoprobe exhibit excellent NIR-II FL imaging performance due to electronic structure perturbation. Benefiting from the size advantage for kidney metabolism and FA targeting specificity, AuPd-P-FA could effectively administration to bladder tumor. When AuPd-P-FA reached maximum enrichment at 1 h post-injection, the localized and mild thermal energy produced upon laser irradiation activated a phase transition. This thermo-sensitive characteristic could prolong the retention time in bladder and the fluorescence signal could be clearly observed at 6 h post-injection with high accuracy. This novel intravesical bidirectional perfusion-like administered mode is expected to achieve a non-invasive diagnosis of early bladder cancer.
Assuntos
Neoplasias da Bexiga Urinária , Humanos , Neoplasias da Bexiga Urinária/diagnóstico por imagem , Bexiga Urinária/diagnóstico por imagem , Administração Intravesical , Perfusão , Imagem ÓpticaRESUMO
BACKGROUND: With the rapid development of deep learning technology, deep neural networks can effectively enhance the performance of computed tomography (CT) reconstructions. One kind of commonly used method to construct CT reconstruction networks is to unroll the conventional iterative reconstruction (IR) methods to convolutional neural networks (CNNs). However, most unrolling methods primarily unroll the fidelity term of IR methods to CNNs, without unrolling the prior terms. The prior terms are always directly replaced by neural networks. PURPOSE: In conventional IR methods, the prior terms play a vital role in improving the visual quality of reconstructed images. Unrolling the hand-crafted prior terms to CNNs may provide a more specialized unrolling approach to further improve the performance of CT reconstruction. In this work, a primal-dual network (PD-Net) was proposed by unrolling both the data fidelity term and the total variation (TV) prior term, which effectively preserves the image edges and textures in the reconstructed images. METHODS: By further deriving the Chambolle-Pock (CP) algorithm instance for CT reconstruction, we discovered that the TV prior updates the reconstructed images with its divergences in each iteration of the solution process. Based on this discovery, CNNs were applied to yield the divergences of the feature maps for the reconstructed image generated in each iteration. Additionally, a loss function was applied to the predicted divergences of the reconstructed image to guarantee that the CNNs' results were the divergences of the corresponding feature maps in the iteration. In this manner, the proposed CNNs seem to play the same roles in the PD-Net as the TV prior in the IR methods. Thus, the TV prior in the CP algorithm instance can be directly unrolled to CNNs. RESULTS: The datasets from the Low-Dose CT Image and Projection Data and the Piglet dataset were employed to assess the effectiveness of our proposed PD-Net. Compared with conventional CT reconstruction methods, our proposed method effectively preserves the structural and textural information in reference to ground truth. CONCLUSIONS: The experimental results show that our proposed PD-Net framework is feasible for the implementation of CT reconstruction tasks. Owing to the promising results yielded by our proposed neural network, this study is intended to inspire further development of unrolling approaches by enabling the direct unrolling of hand-crafted prior terms to CNNs.
Assuntos
Processamento de Imagem Assistida por Computador , Tomografia Computadorizada por Raios X , Animais , Suínos , Processamento de Imagem Assistida por Computador/métodos , Tomografia Computadorizada por Raios X/métodos , Redes Neurais de Computação , Algoritmos , Imagens de FantasmasRESUMO
Photodynamic therapy (PDT) has emerged as a promising strategy with higher selectivity and spatiotemporal control than conventional therapies. However, deep hypoxia in tumours has hampered the clinical use of PDT. In this study, a novel multifunctional cluster nanotheranostic agent (AuPd-BSA CN) was fabricated to generate a high amount of reactive oxygen species, regardless of oxygen dependence under 660 nm laser irradiation. The structure and properties of the AuPd-BSA CN were characterised using various technologies. The synthesised AuPd-BSA CN with high biocompatibility served as a superior photodynamic agent, showing prominent antitumour properties under laser irradiation. Additionally, the glucose oxidase-like activity of the AuPd-BSA CN synergistically enhanced the therapeutic performance. Notably, the intrinsic characteristics of the AuPd-BSA CN include dual-modal second near-infrared window fluorescence/photoacoustic imaging capabilities for monitoring and tracking the in vivo tumour therapeutic process. This work provides innovative insights into the AuPd-BSA CN as an "all-in-one" nanoplatform for cancer therapy.
Assuntos
Neoplasias , Fotoquimioterapia , Humanos , Fotoquimioterapia/métodos , Nanomedicina Teranóstica/métodos , Fototerapia/métodos , Neoplasias/tratamento farmacológico , Oxirredução , Microambiente TumoralRESUMO
BACKGROUND: Low-dose computed tomography (LDCT) is an effective method for reducing radiation exposure. However, reducing radiation dose leads to considerable noise in the reconstructed image that can affect doctor's judgment. OBJECTIVE: To solve this problem, this study proposes a local total variation and improved wavelet residual convolutional neural network (LTV-WRCNN) denoising model. METHODS: The model first introduces local total variation (LTV) to decompose the LDCT image into cartoon and texture image. Next, the texture image is filtered using the non-local mean (NLM). Then, the cartoon image is added to the filtered texture image to obtain the preprocessing image. Finally, the pre-processed image is fed into the improved wavelet residual neural network (WRCNN) to obtain an improved image. Additionally, we also introduce a compound loss in wavelet domain that combines mean squared error loss and directional regularization loss to separate the structural details from noise more thoroughly. RESULTS: Compared with state-of-the-art methods, the peak-signal-to-noise ratio (PSNR) value and the structure similarity (SSIM) value of the processed CT images using the new proposed model are 33.4229âdB and 0.9158. Study also shows that applying new model obtains better results visually and numerically, especially in terms of the preservation of structural details. CONCLUSIONS: The proposed new model is feasible and effective in improving the quality of LDCT images.
Assuntos
Redes Neurais de Computação , Tomografia Computadorizada por Raios X , Humanos , Razão Sinal-Ruído , Tomografia Computadorizada por Raios X/métodos , Progressão da Doença , Processamento de Imagem Assistida por Computador/métodos , AlgoritmosRESUMO
In low-dose computed tomography (LDCT) denoising tasks, it is often difficult to balance edge/detail preservation and noise/artifact reduction. To solve this problem, we propose a dual convolutional neural network (CNN) based on edge feature extraction (Ed-DuCNN) for LDCT. Ed-DuCNN consists of two branches. One branch is the edge feature extraction subnet (Edge_Net) that can fully extract the edge details in the image. The other branch is the feature fusion subnet (Fusion_Net) that introduces an attention mechanism to fuse edge features and noisy image features. Specifically, first, shallow edge-specific detail features are extracted by trainable Sobel convolutional blocks and then are integrated into Edge_Net together with the LDCT images to obtain deep edge detail features. Finally, the input image, shallow edge detail, and deep edge detail features are fused in Fusion_Net to generate the final denoised image. The experimental results show that the proposed Ed-DuCNN can achieve competitive performance in terms of quantitative metrics and visual perceptual quality compared with that of state-of-the-art methods.