Edge feature extraction-based dual CNN for LDCT denoising.

Computer algorithms that simulate lower-doses computed tomography (CT) images from clinical-dose images are widely available. However, most operate in the projection domain and assume access to the reconstruction method. Access to commercial reconstruction methods may often not be available in medical research, making image-domain noise simulation methods useful. However, the introduction of non-linear reconstruction methods, such as iterative and deep learning-based reconstruction, makes noise insertion in the image domain intractable, as it is not possible to determine the noise textures analytically. To develop a deep learning-based image-domain method to generate low-dose CT images from clinical-dose CT (CDCT) images for non-linear reconstruction methods. We propose a fully image domain-based method, utilizing a series of three convolutional neural networks (CNNs), which, respectively, denoise CDCT images, predict the standard deviation map of the low-dose image, and generate the noise power spectra (NPS) of local patches throughout the low-dose image. All three models have U-net-based architectures and are partly or fully three-dimensional. As a use case for this study and with no loss of generality, we use paired low-dose and clinical-dose brain CT scans. A dataset of paired scans was retrospectively obtained. All images were acquired with a wide-area detector clinical system and reconstructed using its standard clinical iterative algorithm. Each pair was registered using rigid registration to correct for motion between acquisitions. The data was randomly partitioned into training ( samples), validation ( samples), and test ( samples) sets. The performance of each of these three CNNs was validated separately. For the denoising CNN, the local standard deviation decrease, and bias were determined. For the standard deviation map CNN, the real and estimated standard deviations were compared locally. Finally, for the NPS CNN, the NPS of the synthetic and real low-dose noise were compared inside and outside the skull. Two proof-of-concept denoising studies were performed to determine if the performance of a CNN- or a gradient-based denoising filter on the synthetic low-dose data versus real data differed. The denoising network had a median decrease in noise in the cerebrospinal fluid by a factor of and introduced a median bias of HU. The network for standard deviation map estimation had a median error of HU. The noise power spectrum estimation network was able to capture the anisotropic and shift-variant nature of the noise structure by showing good agreement between the synthetic and real low-dose noise and their corresponding power spectra. The two proof of concept denoising studies showed only minimal difference in standard deviation improvement ratio between the synthetic and real low-dose CT images with the median difference between the two being 0.0 and +0.05 for the CNN- and gradient-based filter, respectively. The proposed method demonstrated good performance in generating synthetic low-dose brain CT scans without access to the projection data or to the reconstruction method. This method can generate multiple low-dose image realizations from one clinical-dose image, so it is useful for validation, optimization, and repeatability studies of image-processing algorithms.

Noise is inherent to low-dose CT acquisition. We propose to train a convolutional neural network (CNN) jointly with an adversarial CNN to estimate routine-dose CT images from low-dose CT images and hence reduce noise. A generator CNN was trained to transform low-dose CT images into routine-dose CT images using voxelwise loss minimization. An adversarial discriminator CNN was simultaneously trained to distinguish the output of the generator from routine-dose CT images. The performance of this discriminator was used as an adversarial loss for the generator. Experiments were performed using CT images of an anthropomorphic phantom containing calcium inserts, as well as patient non-contrast-enhanced cardiac CT images. The phantom and patients were scanned at 20% and 100% routine clinical dose. Three training strategies were compared: the first used only voxelwise loss, the second combined voxelwise loss and adversarial loss, and the third used only adversarial loss. The results showed that training with only voxelwise loss resulted in the highest peak signal-to-noise ratio with respect to reference routine-dose images. However, CNNs trained with adversarial loss captured image statistics of routine-dose images better. Noise reduction improved quantification of low-density calcified inserts in phantom CT images and allowed coronary calcium scoring in low-dose patient CT images with high noise levels. Testing took less than 10 s per CT volume. CNN-based low-dose CT noise reduction in the image domain is feasible. Training with an adversarial network improves the CNNs ability to generate images with an appearance similar to that of reference routine-dose CT images.

Model-based type iterative reconstruction algorithms with fast reconstruction times are now available. The clinical feasibility of their reconstruction has not been evaluated adequately. To investigate the effects of model-based type iterative reconstruction, i.e. iterative model reconstruction (IMR), with fast reconstruction time on the qualitative and quantitative image quality at low-dose chest computed tomography (CT). Thirty-one patients undergoing low-dose screening chest CT were enrolled. Images were reconstructed using filtered back projection (FBP), hybrid iterative reconstruction (HIR), and IMR algorithms. The CT attenuation and image noise for all reconstructions were calculated at the lung apex, middle, and base. Using a 4-point scale, two reviewers visually evaluated the image quality with respect to vessel sharpness, streak artifact, the mediastinum, and the overall image quality of each reconstruction method. The mean estimated effective dose was 1.0 ± 0.3 mSv. There was no significant difference in the CT attenuation among the three reconstructions. The mean image noise of FBP, HIR, and IMR images was 124.3 ± 57.3, 34.8 ± 10.2, and 22.9 ± 5.8 HU, respectively. There were significant differences for all comparison combinations among the three methods (P < 0.01). The best subjective overall image quality for the lung and mediastinum was obtained with IMR (P < 0.01). The reconstruction time for IMR was within 3 min in all cases. At low-dose chest CT, IMR can improve the qualitative and quantitative visualization of both lung and mediastinal structures especially in the lung apex at a clinically acceptable reconstruction time. Its application may improve diagnostic performance.

Low-dose computed tomography (LDCT) is an effective way to reduce radiation exposure for patients. However, it will increase the noise of reconstructed CT images and affect the precision of clinical diagnosis. The majority of the current deep learning-based denoising methods are built on convolutional neural networks (CNNs), which concentrate on local information and have little capacity for multiple structures modeling. Transformer structures are capable of computing each pixel's response on a global scale, but their extensive computation requirements prevent them from being widely used in medical image processing. To reduce the impact of LDCT scans on patients, this paper aims to develop an image post-processing method by combining CNN and Transformer structures. This method can obtain a high-quality images from LDCT. A hybrid CNN-Transformer (HCformer) codec network model is proposed for LDCT image denoising. A neighborhood feature enhancement (NEF) module is designed to introduce the local information into the Transformer's operation, and the representation of adjacent pixel information in the LDCT image denoising task is increased. The shifting window method is utilized to lower the computational complexity of the network model and overcome the problems that come with computing the MSA (Multi-head self-attention) process in a fixed window. Meanwhile, W/SW-MSA (Windows/Shifted window Multi-head self-attention) is alternately used in two layers of the Transformer to gain the information interaction between various Transformer layers. This approach can successfully decrease the Transformer's overall computational cost. The AAPM 2016 LDCT grand challenge dataset is employed for ablation and comparison experiments to demonstrate the viability of the proposed LDCT denoising method. Per the experimental findings, HCformer can increase the image quality metrics SSIM, HuRMSE and FSIM from 0.8017, 34.1898, and 0.6885 to 0.8507, 17.7213, and 0.7247, respectively. Additionally, the proposed HCformer algorithm will preserves image details while it reduces noise. In this paper, an HCformer structure is proposed based on deep learning and evaluated by using the AAPM LDCT dataset. Both the qualitative and quantitative comparison results confirm that the proposed HCformer outperforms other methods. The contribution of each component of the HCformer is also confirmed by the ablation experiments. HCformer can combine the advantages of CNN and Transformer, and it has great potential for LDCT image denoising and other tasks.

The excellent feature extraction ability of deep convolutional neural networks (DCNNs) has been demonstrated in many image processing tasks, by which image classification can achieve high accuracy with only raw input images. However, the specific image features that influence the classification results are not readily determinable and what lies behind the predictions is unclear. This study proposes a method combining the Sobel and Canny operators and an Inception module for ship classification. The Sobel and Canny operators obtain enhanced edge features from the input images. A convolutional layer is replaced with the Inception module, which can automatically select the proper convolution kernel for ship objects in different image regions. The principle is that the high-level features abstracted by the DCNN, and the features obtained by multi-convolution concatenation of the Inception module must ultimately derive from the edge information of the preprocessing input images. This indicates that the classification results are based on the input edge features, which indirectly interpret the classification results to some extent. Experimental results show that the combination of the edge features and the Inception module improves DCNN ship classification performance. The original model with the raw dataset has an average accuracy of 88.72%, while when using enhanced edge features as input, it achieves the best performance of 90.54% among all models. The model that replaces the fifth convolutional layer with the Inception module has the best performance of 89.50%. It performs close to VGG-16 on the raw dataset and is significantly better than other deep neural networks. The results validate the functionality and feasibility of the idea posited.

GDAFormer: Gradient-guided Dual Attention Transformer for Low-Dose CT image denoising

In recent years, health risks concerning high-dose x-ray radiation have become a major concern in dental computed tomography (CT) examinations. Therefore, adopting low-dose computed tomography (LDCT) technology has become a major focus in the CT imaging field. One of these LDCT technologies is downsampling data acquisition during low-dose x-ray imaging processes. However, reducing the radiation dose can adversely affect CT image quality by introducing noise and artifacts in the resultant image that can compromise diagnostic information. In this paper, we propose an artifact correction method for downsampling CT reconstruction based on deep learning. We used clinical dental CT data with low-dose artifacts reconstructed by conventional filtered back projection (FBP) as inputs to a deep neural network and corresponding high-quality labeled normal-dose CT data during training. We trained a generative adversarial network (GAN) with Wasserstein distance (WGAN) and mean squared error (MSE) loss, called m-WGAN, to remove artifacts and obtain high-quality CT dental images in a clinical dental CT examination environment. The experimental results confirmed that the proposed algorithm effectively removes low-dose artifacts from dental CT scans. In addition, we showed that the proposed method is efficient for removing noise from low-dose CT scan images compared to existing approaches. We compared the performances of the general GAN, convolutional neural networks, and m-WGAN. Through quantitative and qualitative analysis of the results, we concluded that the proposed m-WGAN method resulted in better artifact correction performance preserving the texture in dental CT scanning. The image quality evaluation metrics indicated that the proposed method effectively improves image quality when used as a postprocessing technique for dental CT images. To the best of our knowledge, this work is the first deep learning architecture used with a commercial cone-beam dental CT scanner. The artifact correction performance was rigorously evaluated and demonstrated to be effective. Therefore, we believe that the proposed algorithm represents a new direction in the research area of low-dose dental CT artifact correction.

Markov random field (MRF) model-based penalty is widely used in statistical iterative reconstruction (SIR) of low dose CT (LDCT) reconstruction for noise suppression and edge-preserving. In this strategy, normal dose CT scans are usually used as a priori information to further improve the LDCT quality. However, repeated CT scans are needed and registration or segmentation is usually applied first when misalignment between the low-dose and normal-dose scans exists. The study aims to propose a new MRF prior model of SIR based on the NDCT database without registration. In the proposed model, MRF weights are predicted using optimal similar patch samples from the NDCT database. The patch samples are determined by evaluating the similarity with Euclidean distance between patches from NDCT and the target patch of LDCT. The proposed prior term is incorporated into the SIR cost function, which is to be minimized for LDCT reconstruction. The proposed method is tested on an artificial LDCT data based on a high-dose patient data. Preliminary result has proved its potential performance in edge and structure detail preservation.

Recent advances in deep convolutional neural networks (CNNs) have motivated researchers to adapt CNNs to directly model points in 3D point clouds. Modeling local structure has been proven to be important for the success of convolutional architectures, and researchers exploited the modeling of local point sets in the feature extraction hierarchy. However, limited attention has been paid to explicitly model the geometric structure amongst points in a local region. To address this problem, we propose Geo-CNN, which applies a generic convolution-like operation dubbed as GeoConv to each point and its local neighborhood. Local geometric relationships among points are captured when extracting edge features between the center and its neighboring points. We first decompose the edge feature extraction process onto three orthogonal bases, and then aggregate the extracted features based on the angles between the edge vector and the bases. This encourages the network to preserve the geometric structure in Euclidean space throughout the feature extraction hierarchy. GeoConv is a generic and efficient operation that can be easily integrated into 3D point cloud analysis pipelines for multiple applications. We evaluate Geo-CNN on ModelNet40 and KITTI and achieve state-of-the-art performance.

The deep convolutional neural network has been extensively studied for medical images denoising, specifically for low dose CT (LDCT) denoising. However, most of them disregard that medical images have a large dynamic range. After normalizing the input image, the difference between two nearby HU levels becomes minimal; furthermore, after multiplying it with the floating-point weight vector, the feature response becomes insensitive to small changes in the input images. As a consequence, the denoised image becomes visually smooth. With this observation, we propose to use HU level slicing for improving the performance of the vanilla convolutional network. In our method, we first use different CT windows to slice the input image into a separate HU range. Then different CNN network is used to process each generated input slice separately. Finally, a feature fusion module combines the feature learned by each network and produces the denoised image. Extensive experiments with different state of the art methods in different training settings (both supervised and unsupervised) in three benchmark low dose CT databases validates HU level slicing can significantly improve the denoising performance of the existing methods.KeywordsLow dose CT denoisingCT windowingDynamic range

Segmentation ability map: Interpret deep features for medical image segmentation.

The classification of hyperspectral images (HSIs) is one of the most popular topics in the remote sensing community. Numerous feature extraction methods have been proposed to improve the classification accuracy of HSIs. Recently, deep features extracted by convolution neural network (CNN) have been introduced into the classification process of HSIs. Due to the nonlinear and invariant advantages of the features, CNN methods provide a powerful tool for representing geographic objects and classifying HSIs. However, traditional deep features only extracted at pixel-level and often neglect multiscale characteristics of geographic objects. In this study, a new deep feature extraction method is proposed, which takes advantage of multi-scale object analysis and the CNN model. Firstly, multiscale image objects are obtained by the multiscale segmentation algorithm and multiscale low-level features of objects are extracted. Secondly, the CNN is devoted to obtain deep features from low-level object features at each scale, respectively. Thirdly, the obtained deep features at all scales are stacked and fed to one fully connected layer to extract the multiscale deep learning features for classification. Finally, the logistic regression classifier is applied to hyperspectral image (HSI) classification based on object-oriented multiscale deep features. The proposed method was carried out on three widely used hyperspectral data sets: University of Pavia, Salinas, and Washington DC. The results reveal that the proposed method provides better results than other state-of-the-art methods.

Steganography, a technique for concealing information, often faces challenges such as low decoding accuracy and inadequate extraction of edge and global features. To overcome these limitations, we propose a dual-stream U-Net framework with integrated edge enhancement for image steganography. Our main contributions include the adoption of a dual-stream U-Net structure in the encoder, integrating an edge-enhancement stream with the InceptionDMK module for multi-scale edge detail extraction, and incorporating a multi-scale median attention (MSMA) module into the original input stream to enhance feature representation. This dual-stream design promotes deep feature fusion, thereby improving the edge details and embedding capacity of stego images. Moreover, an iterative optimization strategy is employed to progressively refine the selection of cover images and the embedding process, achieving enhanced stego quality and decoding performance. Experiments show that our method produces high-quality stego images across multiple public datasets, achieving near-100% decoding accuracy. It also surpasses existing methods in visual quality metrics like PSNR and SSIM. This framework offers a promising approach for enhancing steganographic security in real-world applications such as secure communication and data protection.

One-stage pulmonary nodule detection using 3-D DCNN with feature fusion and attention mechanism in CT image

Positron emission tomography (PET) and computed tomography (CT) play a vital role in tumor-related medical diagnosis, assessment, and treatment planning. However, full-dose PET and CT pose the risk of excessive radiation exposure to patients, whereas low-dose images compromise image quality, impacting subsequent tumor recognition and diseasediagnosis. To solve such problems, we propose a Noise-Assisted Hybrid Attention Network (NAHANet) to reconstruct full-dose PET and CT images from low-dose PET (LDPET) and CT (LDCT) images to reduce patient radiation risks while ensuring the performance of subsequent tumor recognition. NAHANet contains two branches: the noise feature prediction branch (NFPB) and the cascaded reconstruction branch. Among them, NFPB providing noise features for the cascade reconstruction branch. The cascaded reconstruction branch comprises a shallow feature extraction module and a reconstruction module which contains a series of cascaded noise feature fusion blocks (NFFBs). Among these, the NFFB fuses the features extracted from low-dose images with the noise features obtained by NFPB to improve the feature extraction capability. To validate the effectiveness of the NAHANet method, we performed experiments using two public available datasets: the Ultra-low Dose PET Imaging Challenge dataset and Low Dose CT Grand Challengedataset. As a result, the proposed NAHANet achieved higher performance on common indicators. For example, on the CT dataset, the PSNR and SSIM indicators were improved by 4.1dB and 0.06 respectively, and the rMSE indicator was reduced by 5.46 compared with the LDCT; on the PET dataset, the PSNR and SSIM was improved by 3.37dB and 0.02, and the rMSE was reduced by 9.04 compared with theLDPET. This paper proposes a transformer-based denoising algorithm, which utilizes hybrid attention to extract high-level features of low dose images and fuses noise features to optimize the denoising performance of the network, achieving good performance improvements on low-dose CT and PETdatasets.