Unsupervised low-dose CT denoising using bidirectional contrastive network.

BACKGROUND AND OBJECTIVE: Low-dose computed tomography (LDCT) scans significantly reduce radiation exposure, but introduce higher levels of noise and artifacts that compromise image quality and diagnostic accuracy. Supervised learning methods have proven effective in denoising LDCT images, but are hampered by the need for large, paired datasets, which pose significant challenges in data acquisition. This study aims to develop a robust unsupervised LDCT denoising method that overcomes the reliance on paired LDCT and normal-dose CT (NDCT) samples, paving the way for more accessible and practical denoising techniques. METHODS: We propose a novel unsupervised network model, Bidirectional Contrastive Unsupervised Denoising (BCUD), for LDCT denoising. This model innovatively combines a bidirectional network structure with contrastive learning theory to map the precise mutual correspondence between the noisy LDCT image domain and the clean NDCT image domain. Specifically, we employ dual encoders and discriminators for domain-specific data generation, and use unique projection heads for each domain to adaptively learn customized embedded representations. We then align corresponding features across domains within the learned embedding spaces to achieve effective noise reduction. This approach fundamentally improves the model's ability to match features in latent space, thereby improving noise reduction while preserving fine image detail. RESULTS: Through extensive experimental validation on the AAPM-Mayo public dataset and real-world clinical datasets, the proposed BCUD method demonstrated superior performance. It achieved a peak signal-to-noise ratio (PSNR) of 31.387 dB, a structural similarity index measure (SSIM) of 0.886, an information fidelity criterion (IFC) of 2.305, and a visual information fidelity (VIF) of 0.373. Notably, subjective evaluation by radiologists resulted in a mean score of 4.23, highlighting its advantages over existing methods in terms of clinical applicability. CONCLUSIONS: This paper presents an innovative unsupervised LDCT denoising method using a bidirectional contrastive network, which greatly improves clinical applicability by eliminating the need for perfectly matched image pairs. The method sets a new benchmark in unsupervised LDCT image denoising, excelling in noise reduction and preservation of fine structural details.

Multi-scale feature aggregation and fusion network with self-supervised multi-level perceptual loss for textures preserving low-dose CT denoising.

Objective. The textures and detailed structures in computed tomography (CT) images are highly desirable for clinical diagnosis. This study aims to expand the current body of work on textures and details preserving convolutional neural networks for low-dose CT (LDCT) image denoising task.Approach. This study proposed a novel multi-scale feature aggregation and fusion network (MFAF-net) for LDCT image denoising. Specifically, we proposed a multi-scale residual feature aggregation module to characterize multi-scale structural information in CT images, which captures regional-specific inter-scale variations using learned weights. We further proposed a cross-level feature fusion module to integrate cross-level features, which adaptively weights the contributions of features from encoder to decoder by using a spatial pyramid attention mechanism. Moreover, we proposed a self-supervised multi-level perceptual loss module to generate multi-level auxiliary perceptual supervision for recovery of salient textures and structures of tissues and lesions in CT images, which takes advantage of abundant semantic information at various levels. We introduced parameters for the perceptual loss to adaptively weight the contributions of auxiliary features of different levels and we also introduced an automatic parameter tuning strategy for these parameters.Main results. Extensive experimental studies were performed to validate the effectiveness of the proposed method. Experimental results demonstrate that the proposed method can achieve better performance on both fine textures preservation and noise suppression for CT image denoising task compared with other competitive convolutional neural network (CNN) based methods.Significance. The proposed MFAF-net takes advantage of multi-scale receptive fields, cross-level features integration and self-supervised multi-level perceptual loss, enabling more effective recovering of fine textures and detailed structures of tissues and lesions in CT images.

WSA-MP-Net: Weak-signal-attention and multi-scale perception network for microvascular extraction in optical-resolution photoacoustic microcopy.

The unique advantage of optical-resolution photoacoustic microscopy (OR-PAM) is its ability to achieve high-resolution microvascular imaging without exogenous agents. This ability has excellent potential in the study of tissue microcirculation. However, tracing and monitoring microvascular morphology and hemodynamics in tissues is challenging because the segmentation of microvascular in OR-PAM images is complex due to the high density, structure complexity, and low contrast of vascular structures. Various microvasculature extraction techniques have been developed over the years but have many limitations: they cannot consider both thick and thin blood vessel segmentation simultaneously, they cannot address incompleteness and discontinuity in microvasculature, there is a lack of open-access datasets for DL-based algorithms. We have developed a novel segmentation approach to extract vascularity in OR-PAM images using a deep learning network incorporating a weak signal attention mechanism and multi-scale perception (WSA-MP-Net) model. The proposed WSA network focuses on weak and tiny vessels, while the MP module extracts features from different vessel sizes. In addition, Hessian-matrix enhancement is incorporated into the pre-and post-processing of the input and output data of the network to enhance vessel continuity. We constructed normal vessel (NV-ORPAM, 660 data pairs) and tumor vessel (TV-ORPAM, 1168 data pairs) datasets to verify the performance of the proposed method. We developed a semi-automatic annotation algorithm to obtain the ground truth for our network optimization. We applied our optimized model successfully to monitor glioma angiogenesis in mouse brains, thus demonstrating the feasibility and excellent generalization ability of our model. Compared to previous works, our proposed WSA-MP-Net extracts a significant number of microvascular while maintaining vessel continuity and signal fidelity. In quantitative analysis, the indicator values of our method improved by about 1.3% to 25.9%. We believe our proposed approach provides a promising way to extract a complete and continuous microvascular network of OR-PAM and enables its use in many microvascular-related biological studies and medical diagnoses.

Deep Learning-Based Reconstruction Improves the Image Quality of Low-Dose CT Colonography.

RATIONALE AND OBJECTIVES: To evaluate the image quality of low-dose CT colonography (CTC) using deep learning-based reconstruction (DLR) compared to iterative reconstruction (IR). MATERIALS AND METHODS: Adults included in the study were divided into four groups according to body mass index (BMI). Routine-dose (RD: 120 kVp) CTC images were reconstructed with IR (RD-IR); low-dose (LD: 100kVp) images were reconstructed with IR (LD-IR) and DLR (LD-DLR). The subjective image quality was rated on a 5-point scale by two radiologists independently. The parameters for objective image quality included noise, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). The Friedman test was used to compare the image quality among RD-IR, LD-IR and LD-DLR. The KruskalWallis test was used to compare the results among different BMI groups. RESULTS: A total of 270 volunteers (mean age: 47.94 years ± 11.57; 115 men) were included. The effective dose of low-dose CTC was decreased by approximately 83.18% (5.18mSv ± 0.86 vs. 0.86mSv ± 0.05, P < 0.001). The subjective image quality score of LD-DLR was superior to that of LD-IR (3.61 ± 0.56 vs. 2.70 ± 0.51, P < 0.001) and on par with the RD- IR's (3.61 ± 0.56 vs. 3.74 ± 0.52, P = 0.486). LD-DLR exhibited the lowest noise, and the maximum SNR and CNR compared to RD-IR and LD-IR (all P < 0.001). No statistical difference was found in the noise of LD-DLR images between different BMI groups (all P > 0.05). CONCLUSION: Compared to IR, DLR provided low-dose CTC with superior image quality at an average radiation dose of 0.86mSv, which may be promising in future colorectal cancer screening.

Two-mode sensing strategies based on tunable cobalt metal organic framework active sites to detect Hg2.

Heavy metal pollution poses a major threat to human health, and developing a user-deliverable heavy metal detection strategy remains a major challenge. In this work, two-mode Hg2+ sensing platforms based on the tunable cobalt metal-organic framework (Co-MOF) active site strategy are constructed, including a colorimetric, and an electrochemical assay using a personal glucose meter (PGM) as the terminal device. Specifically, thymine (T), a single, adaptable nucleotide, is chosen to replace typical T-rich DNA aptamers. The catalytic sites of Co-MOF are tuned competitively by the specific binding of T-Hg2+-T, and different signal output platforms are developed based on the different enzyme-like activities of Co-MOF. DFT calculations are utilized to analyze the interaction mechanism between T and Co-MOF with defect structure. Notably, the two-mode sensing platforms exhibit outstanding detection performance, with LOD values as low as 0.5 nM (colorimetric) and 3.69 nM (PGM), respectively, superior to recently reported nanozyme-based Hg2+ sensors. In real samples of tap water and lake water, this approach demonstrates an effective recovery rate and outstanding selectivity. Surprisingly, the method is potentially versatile and, by exchanging out T-Hg2+-T, can also detect Ag+. This simple, portable, and user-friendly Hg2+ detection approach shows plenty of promise for application in the future.

Effect of partial substitution of wheat flour with kiwi starch on dough rheology, microstructure, the quality attributes and shelf life of Chinese steamed bread.

Chinese steamed bread (CSB), a conventional high-GI staple food, with a short shelf life and a single flavor. In this work, 10-20 % kiwi starch (KS) was used to substitute wheat flour for the production of CSB and the effects of different substitution ratios on the quality and shelf life of mixed flour, dough, and CSB were explored. The results showed that the substitution of KS could improve the water binding capacity of mixed flour and lead to easier pasting in the system, lower the cooking power consumption, increase and improve the viscoelasticity and gas holding capacity of the dough, and make the microstructure more compact and uniform. As the substitution ratio increased, the reduction in protein content within the system further affected the formation of the gluten network, leading to a significant decrease in the CSB's specific volume and cohesiveness, whereas the chewiness and hardness were significantly improved. Meanwhile, KS substitution significantly reduced the starch hydrolysis rate and estimated glycemic index of CSB. 10 % KS substitution enriched the aroma and color of CSB, improved its internal organizational structure, and became more popular among consumers. A substitution ratio of 15-20 % was beneficial for extending the shelf life of CSB.

Structure-preserving low-dose computed tomography image denoising using a deep residual adaptive global context attention network.

Background: Low-dose computed tomography (LDCT) scans can effectively reduce the radiation damage to patients, but this is highly detrimental to CT image quality. Deep convolutional neural networks (CNNs) have shown their potential in improving LDCT image quality. However, the conventional CNN-based approaches rely fundamentally on the convolution operations, which are ineffective for modeling the correlations among nonlocal similar structures and the regionally distinct statistical properties in CT images. This modeling deficiency hampers the denoising performance for CT images derived in this manner. Methods: In this paper, we propose an adaptive global context (AGC) modeling scheme to describe the nonlocal correlations and the regionally distinct statistics in CT images with negligible computation load. We further propose an AGC-based long-short residual encoder-decoder (AGC-LSRED) network for efficient LDCT image noise artifact-suppression tasks. Specifically, stacks of residual AGC attention blocks (RAGCBs) with long and short skip connections are constructed in the AGC-LSRED network, which allows valuable structural and positional information to be bypassed through these identity-based skip connections and thus eases the training of the deep denoising network. For training the AGC-LSRED network, we propose a compound loss that combines the L1 loss, adversarial loss, and self-supervised multi-scale perceptual loss. Results: Quantitative and qualitative experimental studies were performed to verify and validate the effectiveness of the proposed method. The simulation experiments demonstrated the proposed method exhibits the best result in terms of noise suppression [root-mean-square error (RMSE) =9.02; peak signal-to-noise ratio (PSNR) =33.17] and fine structure preservation [structural similarity index (SSIM) =0.925] compared with other competitive CNN-based methods. The experiments on real data illustrated that the proposed method has advantages over other methods in terms of radiologists' subjective assessment scores (averaged scores =4.34). Conclusions: With the use of the AGC modeling scheme to characterize the structural information in CT images and of residual AGC-attention blocks with long and short skip connections to ease the network training, the proposed AGC-LSRED method achieves satisfactory results in preserving fine anatomical structures and suppressing noise in LDCT images.

Effects of Seven Sterilization Methods on the Functional Characteristics and Color of Yan 73 (Vitis vinifera) Grape Juice.

Yan 73 (Vitis vinifera) is a dyed grape variety cultivated in China. Currently, most studies have focused on the mechanism of anthocyanins or the impact of anthocyanins as auxiliary color varieties on wine color. There is little research on its direct use or direct processing of products such as juice. In order to investigate the effects of different processing methods on the juice of Yan 73 grapes, the physicochemical and functional properties, as well as the sensory indexes of the juice, were analyzed by using thermal pasteurization (TP), thermosonication (TS), TS combined with nisin (TSN), TS combined with ε-Polylysine (TSε), irradiation (IR), and high hydrostatic pressure (HHP). The physicochemical indexes, functional properties, and sensory indexes of Smoke 73 grape juice were determined and analyzed. The results of the study showed that among the seven sterilization methods, total polyphenol content (TPC) in juice was significantly increased in all treatments except HHP. TPC was the highest in TP (3773.33 mg GAE/L). Total anthocyanin content (TAC) was increased except IR5, and TSN (1202.67 mg/L) had the highest TAC. In terms of color, TP (a* = 36.57, b* = 19.70, L* = 14.81, C* = 41.55, h° = 28.30, ΔE = 5.9) promotes the dissolution of anthocyanins because of high temperatures, which basically improves all the color indicators of grape juice and makes the color of grape juice more vivid. After HHP treatment, the color (ΔE = 1.72) and aroma indicators are closer to the grape juice itself. The Entropy weight-TOPSIS, CRITIC-Topsis, and PCA integrated quality evaluation models showed that all selected TP as the best integrated quality.

Effects of Vitamin A on Immune Responses and Vitamin A Metabolism in Broiler Chickens Challenged with Necrotic Enteritis.

Necrotic enteritis (NE) is an important enteric inflammatory disease of poultry, and the effects of vitamin A (VitA) on NE birds are largely unknown. The present study was conducted to investigate the effects of VitA on the immune responses and VitA metabolism of NE broilers as well as the underlying mechanisms. Using a 2 × 2 factorial arrangement, 336 1-day-old Ross 308 broiler chicks were randomly assigned to 4 groups with 7 replicates. Broilers in the control (Ctrl) group were fed a basal diet without extra VitA supplementation. Broilers in the VitA group were fed a basal diet supplemented with 12,000 IU/kg of VitA. Birds in NE and VitA + NE groups were fed corresponding diets and, in addition, co-infected with Eimeria spp. and Clostridium perfringens on days 14 to 20. Samples of the blood, jejunum, spleen and liver were obtained on day 28 for analysis, and meanwhile, lesion scores were also recorded. The results showed that NE challenge increased lesion score in the jejunum and decreased serum glucose, total glyceride, calcium, phosphorus and uric acid levels (p < 0.05). VitA supplementation reduced the levels of serum phosphorus, uric acid and alkaline phosphatase in NE-challenged birds and increased serum low-density lipoprotein content and the activity of aspartate aminotransferase and creatine kinase (p < 0.05). Compared with the Ctrl group, the VitA and NE groups had higher mRNA expression of interferon-γ in the jejunum (p < 0.05). NE challenge up-regulated mRNA expression of interleukin (IL)-13, transforming growth factor-ß4, aldehyde dehydrogenase (RALDH)-2 and RALDH-3 in the jejunum, while VitA supplementation increased jejunal IL-13 mRNA expression and hepatic VitA content, but down-regulated splenic IL-13 mRNA expression (p < 0.05). The VitA + NE group had higher serum prostaglandin E2 levels and the Ctrl group had higher splenic RALDH-3 mRNA expression than that of the other three groups (p < 0.05). NE challenge up-regulated jejunal retinoic acid receptor (RAR)-ß and retinoid X receptor (RXR)-α as well as splenic RAR-α and RAR-ß mRNA expression (p < 0.05). VitA supplementation up-regulated jejunal RAR-ß expression but down-regulated mRNA expression of RXR-α, RXR-γ, signal transducers and activators of transcription (STAT) 5 and STAT6 in the spleen (p < 0.05). Moreover, compared with the Ctrl group, the VitA and NE groups had down-regulated mRNA expression of jejunal and splenic Janus kinase (JAK) 1 (p < 0.05). In conclusion, NE challenge induced jejunal injury and expression of Th2 and Treg cell-related cytokines and enhanced RALDH and RAR/RXR mRNA expression, mainly in the jejunum of broilers. VitA supplementation did not alleviate jejunal injury or Th2 cell-related cytokine expression; however, it improved hepatic VitA deposition and inhibited the expression of RALDH-3, RXR and the JAK/STAT signaling pathway in the spleen of broilers. In short, the present study suggested the modulatory effects of vitamin A on the immune responses and vitamin A metabolism in broiler chickens challenged with necrotic enteritis.

Effects of Dietary Supplementation with Vitamin A on Antioxidant and Intestinal Barrier Function of Broilers Co-Infected with Coccidia and Clostridium perfringens.

Necrotic enteritis (NE) impairs poultry production and causes great economic loss. The nutritional regulation of diets has the potential to alleviate NE. The present study was conducted to investigate the effects of dietary supplementation with vitamin A (VA) on the antioxidant and intestinal barrier function of broilers co-infected with coccidia and C. perfringens (CCP). In a 2 × 2 factorial arrangement, 336 one-day-old Ross 308 broilers were divided into four treatments with two levels of VA (0 or 12,000 IU/kg) and challenged with or without CCP. The animal trial lasted for 42 days. The results showed that dietary supplemental VA improved body weight gain (BWG) and the feed intake (FI), and the FI was negatively affected by CCP. Additionally, the levels of catalase (CAT) in the serum, total superoxide dismutase (T-SOD), and CAT in the jejunum and glutathione peroxidase (GSH-Px) in the liver decreased with the CCP challenge (p < 0.05). The mRNA levels of SOD, CAT, GSH-Px1, and GSH-Px3 in the liver and jejunum were upregulated by the CCP challenge (p < 0.05). In addition, the level of serum diamine oxidase (DAO), and the mRNA level of ZO-1 were also upregulated with the CCP challenge. Dietary supplementation with VA contributed to the intestinal villi height and the mRNA level of Mucin-2 in the jejunum (p < 0.05). Additionally, dietary VA had the ability to alleviate the upregulation of SOD in the liver and SOD, CAT, GSH-Px1, GSH-Px3, ZO-1, and claudin-1 in the jejunum with the CCP challenge (p < 0.05). However, the mRNA level of GSH-Px3 and the levels of SOD in the liver and jejunum were downregulated with the VA supplementation in the diet. In conclusion, dietary VA improved the growth performance and the intestinal barrier function; nonetheless, it failed to alleviate the negative effects of CCP on the antioxidant function in broilers.

Classification-based framework for binarization on mice eye image in vivo with optical coherence tomography.

Optical coherence tomography (OCT) angiography has drawn much attention in the medical imaging field. Binarization plays an important role in quantitative analysis of eye with optical coherence tomography. To address the problem of few training samples and contrast-limited scene, we proposed a new binarization framework with specific-patch SVM (SPSVM) for low-intensity OCT image, which is open and classification-based framework. This new framework contains two phases: training model and binarization threshold. In the training phase, firstly, the patches of target and background from few training samples are extracted as the ROI and the background, respectively. Then, PCA is conducted on all patches to reduce the dimension and learn the eigenvector subspace. Finally, the classification model is trained from the features of patches to get the target value of different patches. In the testing phase, the learned eigenvector subspace is conducted on the pixels of each patch. The binarization threshold of patch is obtained with the learned SVM model. We acquire a new OCT mice eye (OCT-ME) database, which is publicly available at https://mip2019.github.io/spsvm. Extensive experiments were performed to demonstrate the effectiveness of the proposed SPSVM framework.

Contrast-Medium Anisotropy-Aware Tensor Total Variation Model for Robust Cerebral Perfusion CT Reconstruction with Low-Dose Scans.

Perfusion computed tomography (PCT) is critical in detecting cerebral ischemic lesions. PCT examination with low-dose scans can effectively reduce radiation exposure to patients at the cost of degraded images with severe noise and artifacts. Tensor total variation (TTV) models are powerful tools that can encode the regional continuous structures underlying a PCT object. In a TTV model, the sparsity structures of the contrast-medium concentration (CMC) across PCT frames are assumed to be isotropic with identical and independent distribution. However, this assumption is inconsistent with practical PCT tasks wherein the sparsity has evident variations and correlations. Such modeling deviation hampers the performance of TTV-based PCT reconstructions. To address this issue, we developed a novel contrast-medium anisotropy-aware tensor total variation (CMAA-TTV) model to describe the intrinsic anisotropy sparsity of the CMC in PCT imaging tasks. Instead of directly on the difference matrices, the CMAA-TTV model characterizes sparsity on a low-rank subspace of the difference matrices which are calculated from the input data adaptively, thus naturally encoding the intrinsic variant and correlated anisotropy sparsity structures of the CMC. We further proposed a robust and efficient PCT reconstruction algorithm to improve low-dose PCT reconstruction performance using the CMAA-TTV model. Experimental studies using a digital brain perfusion phantom, patient data with low-dose simulation and clinical patient data were performed to validate the effectiveness of the presented algorithm. The results demonstrate that the CMAA-TTV algorithm can achieve noticeable improvements over state-of-the-art methods in low-dose PCT reconstruction tasks.

Partial Substitution of Fermented Soybean Meal for Soybean Meal Influences the Carcass Traits and Meat Quality of Broiler Chickens.

The usage of fermented soybean meal (FSBM) in poultry feed is limited due to the high cost. The present study was conducted to examine the carcass traits and meat quality of broiler chickens that were fed diets with partial replacement of soybean meal (SBM) with FSBM. The 336 one-day-old chicks were assigned to four groups with 0% (control), 2.5%, 5.0%, and 7.5% FSBM addition in corn-SBM-based diets. Compared with the control, 2.5% and 5.0% FSBM decreased leg muscle yield, breast drip loss, and cooking loss (p < 0.05). The 7.5% FSBM increased the ultimate pH of breast and thigh muscles, and all FSBM treatments decreased muscle lightness and breast malondialdehyde content (p < 0.05). The 2.5% FSBM increased breast total superoxide dismutase activity, while 7.5% FSBM reduced breast hydrogen peroxide level (p < 0.05). All FSBM treatments elevated breast contents of bitter and sour tasting amino acids, and 2.5% and 7.5% FSBM increased breast glutamic acid and total free amino acids (p < 0.05). The 5.0% and 7.5% FSBM elevated thigh isoleucine and leucine contents (p < 0.05). In conclusion, FSBM replacing SBM affected meat quality with the decrease of lightness and increase of pH, water-holding capacity, antioxidant properties, and free amino acids.

[Correlative analysis of agronomic traits and quality of Panax ginseng saponins cultivation in farmland].

Cultivated ginseng in the farmland would become the mainly planting mode of Panax ginseng. However,there are relatively few cultivation ginseng varieties for farmland in China. Correlative analysis of qualitity and agronomic traits of P. ginseng cultivation in the farmland could provide a reference for the selection of excellent germplasm and new variety breeding of P. ginseng. In this study,the main index of saponin and agronomic traits of 4-6 years' samples were analyzed by UPLC and measured. The results show that there was significant difference in agronomic indexes of Damaya. The coefficient of variation of the root length( CV = 41. 97%) and fresh weight( CV = 31. 81%) were maximum,and the coefficient of variation of the stems thickness( 16. 72%) and root thickness were minimum. There was a significant correlation between yield and root thickness( P<0. 05). There was significant difference in drug yield of different harvest years( P<0. 05),and the yield of 6-years was 31. 52%-39. 69% higher than 4-years. However,there wasn't significant difference in total ginsenosides between 4 and 6 years old P. ginseng,but there was significant difference in ginseng Rg2,Rc and Rb2( P<0. 05),and the ginsenoside contents of different harvesting years were accorded with the criterion standards of 2015 Chinese Pharmacopoeia. There was no significant correlation between the saponin and the agronomic trait,while there was positive correlation with root thickness( P < 0. 05). Therefore,the stem diameter was positive correlation with yield of P. ginseng. Selection of the stem thickness of seedlings is beneficial to the increase of the yield and breeding of P. ginseng.

Multi-energy computed tomography reconstruction using a nonlocal spectral similarity model.

Multi-energy computed tomography (MECT) is able to acquire simultaneous multi-energy measurements from one scan. In addition, it allows material differentiation and quantification effectively. However, due to the limited energy bin width, the number of photons detected in an energy-specific channel is smaller than that in traditional CT, which results in image quality degradation. To address this issue, in this work, we develop a statistical iterative reconstruction algorithm to acquire high-quality MECT images and high-accuracy material-specific images. Specifically, this algorithm fully incorporates redundant self-similarities within nonlocal regions in the MECT image at one bin and rich spectral similarities among MECT images at all bins. For simplicity, the presented algorithm is referred to as 'MECT-NSS'. Moreover, an efficient optimization algorithm is developed to solve the MECT-NSS objective function. Then, a comprehensive evaluation of parameter selection for the MECT-NSS algorithm is conducted. In the experiment, the datasets include images from three phantoms and one patient to validate and evaluate the MECT-NSS reconstruction performance. The qualitative and quantitative results demonstrate that the presented MECT-NSS can successfully yield better MECT image quality and more accurate material estimation than the competing algorithms.

Statistical CT reconstruction using region-aware texture preserving regularization learning from prior normal-dose CT image.

In some clinical applications, prior normal-dose CT (NdCT) images are available, and the valuable textures and structure features in them may be used to promote follow-up low-dose CT (LdCT) reconstruction. This study aims to learn texture information from the NdCT images and leverage it for follow-up LdCT image reconstruction to preserve textures and structure features. Specifically, the proposed reconstruction method first learns the texture information from those patches with similar structures in NdCT image, and the similar patches can be clustered by searching context features efficiently from the surroundings of the current patch. Then it utilizes redundant texture information from the similar patches as a priori knowledge to describe specific regions in the LdCT image. The advanced region-aware texture preserving prior is termed as 'RATP'. The main advantage of the PATP prior is that it can properly learn the texture features from available NdCT images and adaptively characterize the region-specific structures in the LdCT image. The experiments using patient data were performed to evaluate the performance of the proposed method. The proposed RATP method demonstrated superior performance in LdCT imaging compared to the filtered back projection (FBP) and statistical iterative reconstruction (SIR) methods using Gaussian regularization, Huber regularization and the original texture preserving regularization.

Iterative quality enhancement via residual-artifact learning networks for low-dose CT.

Radiation exposure and the associated risk of cancer for patients in computed tomography (CT) scans have been major clinical concerns. The radiation exposure can be reduced effectively via lowering the x-ray tube current (mA). However, this strategy may lead to excessive noise and streak artifacts in the conventional filtered back-projection reconstructed images. To address this issue, some deep convolutional neural network (ConvNet) based approaches have been developed for low-dose CT imaging inspired by the recent development of machine learning. Nevertheless, some of the image textures reconstructed by the ConvNet could be corrupted by the severe streaks, especially in ultra-low-dose cases, which could be close to prostheses and hamper diagnosis. Therefore, in this work, we propose an iterative residual-artifact learning ConvNet (IRLNet) approach to improve the reconstruction performance over the ConvNet based approaches. Specifically, the proposed IRLNet estimates the high-frequency details within the noise and then removes them iteratively; after eliminating severe streaks in the low-dose CT images, the residual low-frequency details can be processed through the conventional network. Moreover, the proposed IRLNet scheme can be extended for robust handling of quantitative dual energy CT/cerebral perfusion CT imaging, and statistical iterative reconstruction. Real patient data are used to evaluate the proposed IRLNet, and the experimental results demonstrate that the proposed IRLNet approach outperforms the previous ConvNet based approaches in reducing the image noise and streak artifacts efficiently at the same time as preserving edge details well, suggesting that the proposed IRLNet approach can be used to improve the CT image quality, especially in ultra-low-dose cases.

Cone-beam x-ray luminescence computed tomography based on x-ray absorption dosage.

With the advances of x-ray excitable nanophosphors, x-ray luminescence computed tomography (XLCT) has become a promising hybrid imaging modality. In particular, a cone-beam XLCT (CB-XLCT) system has demonstrated its potential in in vivo imaging with the advantage of fast imaging speed over other XLCT systems. Currently, the imaging models of most XLCT systems assume that nanophosphors emit light based on the intensity distribution of x-ray within the object, not completely reflecting the nature of the x-ray excitation process. To improve the imaging quality of CB-XLCT, an imaging model that adopts an excitation model of nanophosphors based on x-ray absorption dosage is proposed in this study. To solve the ill-posed inverse problem, a reconstruction algorithm that combines the adaptive Tikhonov regularization method with the imaging model is implemented for CB-XLCT reconstruction. Numerical simulations and phantom experiments indicate that compared with the traditional forward model based on x-ray intensity, the proposed dose-based model could improve the image quality of CB-XLCT significantly in terms of target shape, localization accuracy, and image contrast. In addition, the proposed model behaves better in distinguishing closer targets, demonstrating its advantage in improving spatial resolution.

A Robust Manifold Graph Regularized Nonnegative Matrix Factorization Algorithm for Cancer Gene Clustering.

Detecting genomes with similar expression patterns using clustering techniques plays an important role in gene expression data analysis. Non-negative matrix factorization (NMF) is an effective method for clustering the analysis of gene expression data. However, the NMF-based method is performed within the Euclidean space, and it is usually inappropriate for revealing the intrinsic geometric structure of data space. In order to overcome this shortcoming, Cai et al. proposed a novel algorithm, called graph regularized non-negative matrices factorization (GNMF). Motivated by the topological structure of the GNMF-based method, we propose improved graph regularized non-negative matrix factorization (GNMF) to facilitate the display of geometric structure of data space. Robust manifold non-negative matrix factorization (RM-GNMF) is designed for cancer gene clustering, leading to an enhancement of the GNMF-based algorithm in terms of robustness. We combine the l 2 , 1 -norm NMF with spectral clustering to conduct the wide-ranging experiments on the three known datasets. Clustering results indicate that the proposed method outperforms the previous methods, which displays the latest application of the RM-GNMF-based method in cancer gene clustering.

Resolving adjacent nanophosphors of different concentrations by excitation-based cone-beam X-ray luminescence tomography.

Cone-beam X-ray luminescence computed tomography (CB-XLCT) has been proposed as a new molecular imaging modality recently. It can obtain both anatomical and functional tomographic images of an object efficiently, with the excitation of nanophosphors in vivo or in vitro by cone-beam X-rays. However, the ill-posedness of the CB-XLCT inverse problem degrades the image quality and makes it difficult to resolve adjacent luminescent targets with different concentrations, which is essential in the monitoring of nanoparticle metabolism and drug delivery. To address this problem, a multi-voltage excitation imaging scheme combined with principal component analysis is proposed in this study. Imaging experiments performed on physical phantoms by a custom-made CB-XLCT system demonstrate that two adjacent targets, with different concentrations and an edge-to-edge distance of 0 mm, can be effectively resolved.