Feature shared multi-decoder network using complementary learning for Photon counting CT ring artifact suppression.

BACKGROUND: Photon-counting computed tomography (Photon counting CT) utilizes photon-counting detectors to precisely count incident photons and measure their energy. These detectors, compared to traditional energy integration detectors, provide better image contrast and material differentiation. However, Photon counting CT tends to show more noticeable ring artifacts due to limited photon counts and detector response variations, unlike conventional spiral CT. OBJECTIVE: To comprehensively address this issue, we propose a novel feature shared multi-decoder network (FSMDN) that utilizes complementary learning to suppress ring artifacts in Photon counting CT images. METHODS: Specifically, we employ a feature-sharing encoder to extract context and ring artifact features, facilitating effective feature sharing. These shared features are also independently processed by separate decoders dedicated to the context and ring artifact channels, working in parallel. Through complementary learning, this approach achieves superior performance in terms of artifact suppression while preserving tissue details. RESULTS: We conducted numerous experiments on Photon counting CT images with three-intensity ring artifacts. Both qualitative and quantitative results demonstrate that our network model performs exceptionally well in correcting ring artifacts at different levels while exhibiting superior stability and robustness compared to the comparison methods. CONCLUSIONS: In this paper, we have introduced a novel deep learning network designed to mitigate ring artifacts in Photon counting CT images. The results illustrate the viability and efficacy of our proposed network model as a new deep learning-based method for suppressing ring artifacts.

Natural variation of ZmCGT1 is responsible for isoorientin accumulation in maize silk.

Maize (Zea mays L.) silk contains high levels of flavonoids and is widely used to promote human health. Isoorientin, a natural C-glycoside flavone abundant in maize silk, has attracted considerable attention due to its potential value. Although different classes of flavonoid have been well characterized in plants, the genes involved in the biosynthesis of isoorientin in maize are largely unknown. Here, we used targeted metabolic profiling of isoorientin on the silks in an association panel consisting of 294 maize inbred lines. We identified the gene ZmCGT1 by genome-wide association analysis. The ZmCGT1 protein was characterized as a 2-hydroxyflavanone C-glycosyltransferase that can C-glycosylate 2-hydroxyflavanone to form flavone-C-glycoside after dehydration. Moreover, ZmCGT1 overexpression increased isoorientin levels and RNA interference-mediated ZmCGT1 knockdown decreased accumulation of isoorientin in maize silk. Further, two nucleotide polymorphisms, A502C and A1022G, which led to amino acid changes I168L and E341G, respectively, were identified to be functional polymorphisms responsible for the natural variation in isoorientin levels. In summary, we identified the gene ZmCGT1, which plays an important role in isoorientin biosynthesis, providing insights into the genetic basis of the natural variation in isoorientin levels in maize silk. The identified favorable CG allele of ZmCGT1 may be further used for genetic improvement of nutritional quality in maize.

Isoorientin Affects Markers of Alzheimer's Disease via Effects on the Oral and Gut Microbiota in APP/PS1 Mice.

BACKGROUND: There is growing evidence of strong associations between the pathogenesis of Alzheimer's disease (AD) and dysbiotic oral and gut microbiota. Recent studies demonstrated that isoorientin (ISO) is anti-inflammatory and alleviates markers of AD, which were hypothesized to be mediated by the oral and gut microbiota. OBJECTIVES: We studied the effects of oral administration of ISO on AD-related markers and the oral and gut microbiota in mice. METHODS: Eight-month-old amyloid precursor protein/presenilin-1 (AP) transgenic male mice were randomly allocated to 3 groups of 15 mice each: vehicle (AP) alone or with a low dose of ISO (AP + ISO-L; 25 mg/kg) or a high dose of ISO (AP + ISO-H; 50 mg/kg). Age-matched wild-type (WT) C57BL/6 male littermates were used as controls. The 4 groups were treated intragastrically with ISO or sterilized ultrapure water for 2 months. AD-related markers in the brain, serum, colon, and liver were analyzed with immunohistochemical and histochemical staining, Western blotting, and ELISA. Oral and gut microbiotas were analyzed using 16S ribosomal RNA gene sequencing. RESULTS: The high-dose ISO treatment significantly decreased amyloid beta 42-positive deposition by 38.1% and 45.2% in the cortex and hippocampus, respectively, of AP mice (P < 0.05). Compared with the AP group, both ISO treatments reduced brain phospho-Tau, phosphor-p65, phosphor-inhibitor of NF-κB, and brain and serum LPS and TNF-α by 17.9%-72.5% and increased brain and serum IL-4 and IL-10 by 130%-210% in the AP + ISO-L and AP + ISO-H groups (P < 0.05). Abundances of 26, 25, and 23 microbial taxa in oral, fecal and cecal samples, respectively, were increased in both the AP + ISO-L and AP + ISO-H groups relative to the AP group [linear discriminant analysis (LDA) >3.0; P < 0.05]. Gram-negative bacteria, Alteromonas, Campylobacterales, and uncultured Bacteroidales bacterium were positively correlated (rho = 0.28-0.59; P < 0.05) with the LPS levels and responses of inflammatory cytokines. CONCLUSIONS: The microbiota-gut-brain axis is a potential mechanism by which ISO reduces AD-related markers in AP mice.

Efficient and genotype independent maize transformation using pollen transfected by DNA-coated magnetic nanoparticles.

Current gene delivery methods for maize are limited to specific genotypes and depend on time-consuming and labor-intensive tissue culture techniques. Here, we report a new method to transfect maize that is culture-free and genotype independent. To enhance efficiency of DNA entry and maintain high pollen viability of 32%-55%, transfection was performed at cool temperature using pollen pretreated to open the germination aperture (40%-55%). Magnetic nanoparticles (MNPs) coated with DNA encoding either red fluorescent protein (RFP), ß-glucuronidase gene (GUS), enhanced green fluorescent protein (EGFP) or bialaphos resistance (bar) was delivered into pollen grains, and female florets of maize inbred lines were pollinated. Red fluorescence was detected in 22% transfected pollen grains, and GUS stained 55% embryos at 18 d after pollination. Green fluorescence was detected in both silk filaments and immature kernels. The T1 generation of six inbred lines showed considerable EGFP or GUS transcripts (29%-74%) quantitated by polymerase chain reaction, and 5%-16% of the T1 seedlings showed immunologically active EGFP or GUS protein. Moreover, 1.41% of the bar transfected T1 plants were glufosinate resistant, and heritable bar gene was integrated into the maize genome effectively as verified by DNA hybridization. These results demonstrate that exogenous DNA could be delivered efficiently into elite maize inbred lines recalcitrant to tissue culture-mediated transformation and expressed normally through our genotype-independent pollen transfection system.

Identifying key regulatory genes of maize root growth and development by RNA sequencing.

Root system architecture (RSA), the spatio-temporal configuration of roots, plays vital roles in maize (Zea mays L.) development and productivity. We sequenced the maize root transcriptome of four key growth and development stages: the 6th leaf stage, the 12th leaf stage, the tasseling stage and the milk-ripe stage. Differentially expressed genes (DEGs) were detected. 81 DEGs involved in plant hormone signal transduction pathway and 26 transcription factor (TF) genes were screened. These DEGs and TFs were predicted to be potential candidate genes during maize root growth and development. Several of these genes are homologous to well-known genes regulating root architecture or development in Arabidopsis or rice, such as, Zm00001d005892 (AtERF109), Zm00001d027925 (AtERF73/HRE1), Zm00001d047017 (AtMYC2, OsMYC2), Zm00001d039245 (AtWRKY6). Identification of these key genes will provide a further understanding of the molecular mechanisms responsible for maize root growth and development, it will be beneficial to increase maize production and improve stress resistance by altering RSA traits in modern breeding.

Material decomposition for simulated dual-energy breast computed tomography via hybrid optimization method.

BACKGROUND: Dual-energy breast CT reconstruction has a potential application that includes separation of microcalcification from healthy breast tissue for assisting early breast cancer detection. OBJECTIVE: To investigate and validate the noise suppression algorithm applied in the decomposition of the simulated breast phantom into microcalcification and healthy breast. METHODS: The proposed hybrid optimization method (HOM) uses a simultaneous algebraic reconstruction technique (SART) output as a prior image, which is then incorporated into the self-adaptive dictionary learning. This self-adaptive dictionary learning seeks each group of patches to faithfully represent the learned dictionary, and the sparsity and non-local similarity of group patches are used to enforce the image regularization term of the prior image. We simulate a numerical phantom by adding different levels of Gaussian noise to test performance of the proposed method. RESULTS: The mean value of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and root mean square error (RMSE) for the proposed method are (49.043±1.571), (0.997±0.002), (0.003±0.001) and (51.329±1.998), (0.998±0.002), (0.003±0.001) for 35 kVp and 49 kVp, respectively. The PSNR of the proposed method shows greater improvement over TWIST (5.2%), SART (34.6%), FBP (40.4%) and TWIST (3.7%), SART (39.9%), FBP (50.3%) for 35 kVp and 49 kVp energy images, respectively. For the proposed method, the signal-to-noise ratio (SNR) of decomposed normal breast tissue (NBT) is (22.036±1.535), which exceeded that of TWIST, SART, and FBP by 7.5%, 49.6%, and 96.4%, respectively. The results reveal that the proposed algorithm achieves the best performance in both reconstructed and decomposed images under different levels of noise and the performance is due to the high sparsity and good denoising ability of minimization exploited to solve the convex optimization problem. CONCLUSIONS: This study demonstrates the potential of applying dual-energy reconstruction in breast CT to detect and separate clustered MCs from healthy breast tissues without noise amplification. Compared to other competing methods, the proposed algorithm achieves the best noise suppression performance for both reconstructed and decomposed images.

The complete genome sequence of Bacillus halotolerans ZB201702 isolated from a drought- and salt-stressed rhizosphere soil.

Bacillus halotolerans is a rhizobacterium with the potential to promote plant growth and tolerance to drought and salinity stress. Here, we present the complete genome sequence of B. halotolerans ZB201702, which consists of 4,150,000 bp in a linear chromosome, including 3074 protein-coding sequences, 30 rRNAs, and 85 tRNAs. Genome analysis revealed many putative gene clusters involved in defense mechanisms. Activity analysis of the strain under salt and simulated drought stress suggests tolerance to abiotic stresses. The complete genome information of B. halotolerans ZB201702 could provide valuable insights into rhizobacteria-mediated plant salt and drought tolerance and rhizobacteria-based solutions for abiotic stress agriculture.

Gaussian diffusion sinogram inpainting for X-ray CT metal artifact reduction.

BACKGROUND: Metal objects implanted in the bodies of patients usually generate severe streaking artifacts in reconstructed images of X-ray computed tomography, which degrade the image quality and affect the diagnosis of disease. Therefore, it is essential to reduce these artifacts to meet the clinical demands. METHODS: In this work, we propose a Gaussian diffusion sinogram inpainting metal artifact reduction algorithm based on prior images to reduce these artifacts for fan-beam computed tomography reconstruction. In this algorithm, prior information that originated from a tissue-classified prior image is used for the inpainting of metal-corrupted projections, and it is incorporated into a Gaussian diffusion function. The prior knowledge is particularly designed to locate the diffusion position and improve the sparsity of the subtraction sinogram, which is obtained by subtracting the prior sinogram of the metal regions from the original sinogram. The sinogram inpainting algorithm is implemented through an approach of diffusing prior energy and is then solved by gradient descent. The performance of the proposed metal artifact reduction algorithm is compared with two conventional metal artifact reduction algorithms, namely the interpolation metal artifact reduction algorithm and normalized metal artifact reduction algorithm. The experimental datasets used included both simulated and clinical datasets. RESULTS: By evaluating the results subjectively, the proposed metal artifact reduction algorithm causes fewer secondary artifacts than the two conventional metal artifact reduction algorithms, which lead to severe secondary artifacts resulting from impertinent interpolation and normalization. Additionally, the objective evaluation shows the proposed approach has the smallest normalized mean absolute deviation and the highest signal-to-noise ratio, indicating that the proposed method has produced the image with the best quality. CONCLUSIONS: No matter for the simulated datasets or the clinical datasets, the proposed algorithm has reduced the metal artifacts apparently.

Isolation, structural analysis, and expression characteristics of the maize nuclear factor Y gene families.

NUCLEAR FACTOR-Y (NF-Y) has been shown to play an important role in growth, development, and response to environmental stress. A NF-Y complex, which consists of three subunits, NF-YA, NF-YB, and, NF-YC, binds to CCAAT sequences in a promoter to control the expression of target genes. Although NF-Y proteins have been reported in Arabidopsis and rice, a comprehensive and systematic analysis of ZmNF-Y genes has not yet been performed. To examine the functions of ZmNF-Y genes in this family, we isolated and characterized 50 ZmNF-Y (14 ZmNF-YA, 18 ZmNF-YB, and 18 ZmNF-YC) genes in an analysis of the maize genome. The 50 ZmNF-Y genes were distributed on all 10 maize chromosomes, and 12 paralogs were identified. Multiple alignments showed that maize ZmNF-Y family proteins had conserved regions and relatively variable N-terminal or C-terminal domains. The comparative syntenic map illustrated 40 paralogous NF-Y gene pairs among the 10 maize chromosomes. Microarray data showed that the ZmNF-Y genes had tissue-specific expression patterns in various maize developmental stages and in response to biotic and abiotic stresses. The results suggested that ZmNF-YB2, 4, 8, 10, 13, and 16 and ZmNF-YC6, 8, and 15 were induced, while ZmNF-YA1, 3, 4, 6, 7, 10, 12, and 13, ZmNF-YB15, and ZmNF-YC3 and 9 were suppressed by drought stress. ZmNF-YA3, ZmNF-YA8 and ZmNF-YA12 were upregulated after infection by the three pathogens, while ZmNF-YA1 and ZmNF-YB2 were suppressed. These results indicate that the ZmNF-Ys may have significant roles in the response to abiotic and biotic stresses.

Isolation, structural analysis, and expression characteristics of the maize TIFY gene family.

TIFY, previously known as ZIM, comprises a plant-specific family annotated as transcription factors that might play important roles in stress response. Despite TIFY proteins have been reported in Arabidopsis and rice, a comprehensive and systematic survey of ZmTIFY genes has not yet been conducted. To investigate the functions of ZmTIFY genes in this family, we isolated and characterized 30 ZmTIFY (1 TIFY, 3 ZML, and 26 JAZ) genes in an analysis of the maize (Zea mays L.) genome in this study. The 30 ZmTIFY genes were distributed over eight chromosomes. Multiple alignment and motif display results indicated that all ZmTIFY proteins share two conserved TIFY and Jas domains. Phylogenetic analysis revealed that the ZmTIFY family could be divided into two groups. Putative cis-elements, involved in abiotic stress response, phytohormones, pollen grain, and seed development, were detected in the promoters of maize TIFY genes. Microarray data showed that the ZmTIFY genes had tissue-specific expression patterns in various maize developmental stages and in response to biotic and abiotic stresses. The results indicated that ZmTIFY4, 5, 8, 26, and 28 were induced, while ZmTIFY16, 13, 24, 27, 18, and 30 were suppressed, by drought stress in the maize inbred lines Han21 and Ye478. ZmTIFY1, 19, and 28 were upregulated after infection by three pathogens, whereas ZmTIFY4, 13, 21, 23, 24, and 26 were suppressed. These results indicate that the ZmTIFY family may have vital roles in response to abiotic and biotic stresses. The data presented in this work provide vital clues for further investigating the functions of the genes in the ZmTIFY family.

Parallel processing model for low-dose computed tomography image denoising.

Low-dose computed tomography (LDCT) has gained increasing attention owing to its crucial role in reducing radiation exposure in patients. However, LDCT-reconstructed images often suffer from significant noise and artifacts, negatively impacting the radiologists' ability to accurately diagnose. To address this issue, many studies have focused on denoising LDCT images using deep learning (DL) methods. However, these DL-based denoising methods have been hindered by the highly variable feature distribution of LDCT data from different imaging sources, which adversely affects the performance of current denoising models. In this study, we propose a parallel processing model, the multi-encoder deep feature transformation network (MDFTN), which is designed to enhance the performance of LDCT imaging for multisource data. Unlike traditional network structures, which rely on continual learning to process multitask data, the approach can simultaneously handle LDCT images within a unified framework from various imaging sources. The proposed MDFTN consists of multiple encoders and decoders along with a deep feature transformation module (DFTM). During forward propagation in network training, each encoder extracts diverse features from its respective data source in parallel and the DFTM compresses these features into a shared feature space. Subsequently, each decoder performs an inverse operation for multisource loss estimation. Through collaborative training, the proposed MDFTN leverages the complementary advantages of multisource data distribution to enhance its adaptability and generalization. Numerous experiments were conducted on two public datasets and one local dataset, which demonstrated that the proposed network model can simultaneously process multisource data while effectively suppressing noise and preserving fine structures. The source code is available at https://github.com/123456789ey/MDFTN .

Cloning, Expression, and Functional Characterization of Two Highly Efficient Flavonoid-di-O-glycosyltransferases ZmUGT84A1 and ZmUGT84A2 from Maize (Zea mays L.).

The maize (Zea mays L.) glycosyltransferase family 1 comprises many uridine diphosphate glycosyltransferase (UGT) members. However, UGT activities and biochemical functions have seldom been revealed. In this study, the genes of two flavonoid di-O-glycosyltransferases ZmUGT84A1 and ZmUGT84A2 were cloned from maize plant and expressed in Escherichia coli. Phylogenetic analysis showed that the two enzymes were homologous to AtUGT84A1 and AtUGT84A3. The two recombinant enzymes showed a high conversion rate of luteolin to its glucosides, mainly 4',7-di-O-glucoside and minorly 3',7-di-O-glucoside in two-step glycosylation reactions in vitro. Moreover, the recombinant ZmUGT84A1 and ZmUGT84A2 had a broad substrate spectrum, converting eriodictyol, naringenin, apigenin, quercetin, and kaempferol to monoglucosides and diglucosides. The highly efficient ZmUGT84A1 and ZmUGT84A2 may be used as a tool for the effective synthesis of various flavonoid O-glycosides and as markers for crop breeding to increase O-glycosyl flavonoid content in food.

Purification and characterization of ZmRIP1, a novel reductant-inhibited protein tyrosine phosphatase from maize.

Protein tyrosine phosphatases (PTPases) have long been thought to be activated by reductants and deactivated by oxidants, owing to the presence of a crucial sulfhydryl group in their catalytic centers. In this article, we report the purification and characterization of Reductant-Inhibited PTPase1 (ZmRIP1) from maize (Zea mays) coleoptiles, and show that this PTPase has a unique mode of redox regulation and signaling. Surprisingly, ZmRIP1 was found to be deactivated by a reductant. A cysteine (Cys) residue (Cys-181) near the active center was found to regulate this unique mode of redox regulation, as mutation of Cys-181 to arginine-181 allowed ZmRIP1 to be activated by a reductant. In response to oxidant treatment, ZmRIP1 was translocated from the chloroplast to the nucleus. Expression of ZmRIP1 in Arabidopsis (Arabidopsis thaliana) plants and maize protoplasts altered the expression of genes encoding enzymes involved in antioxidant catabolism, such as At1g02950, which encodes a glutathione transferase. Thus, the novel PTPase identified in this study is predicted to function in redox signaling in maize.

MFCNet: A multi-modal fusion and calibration networks for 3D pancreas tumor segmentation on PET-CT images.

In clinical diagnosis, positron emission tomography and computed tomography (PET-CT) images containing complementary information are fused. Tumor segmentation based on multi-modal PET-CT images is an important part of clinical diagnosis and treatment. However, the existing current PET-CT tumor segmentation methods mainly focus on positron emission tomography (PET) and computed tomography (CT) feature fusion, which weakens the specificity of the modality. In addition, the information interaction between different modal images is usually completed by simple addition or concatenation operations, but this has the disadvantage of introducing irrelevant information during the multi-modal semantic feature fusion, so effective features cannot be highlighted. To overcome this problem, this paper propose a novel Multi-modal Fusion and Calibration Networks (MFCNet) for tumor segmentation based on three-dimensional PET-CT images. First, a Multi-modal Fusion Down-sampling Block (MFDB) with a residual structure is developed. The proposed MFDB can fuse complementary features of multi-modal images while retaining the unique features of different modal images. Second, a Multi-modal Mutual Calibration Block (MMCB) based on the inception structure is designed. The MMCB can guide the network to focus on a tumor region by combining different branch decoding features using the attention mechanism and extracting multi-scale pathological features using a convolution kernel of different sizes. The proposed MFCNet is verified on both the public dataset (Head and Neck cancer) and the in-house dataset (pancreas cancer). The experimental results indicate that on the public and in-house datasets, the average Dice values of the proposed multi-modal segmentation network are 74.14% and 76.20%, while the average Hausdorff distances are 6.41 and 6.84, respectively. In addition, the experimental results show that the proposed MFCNet outperforms the state-of-the-art methods on the two datasets.

X-ray CT image denoising with MINF: A modularized iterative network framework for data from multiple dose levels.

In clinical applications, multi-dose scan protocols will cause the noise levels of computed tomography (CT) images to fluctuate widely. The popular low-dose CT (LDCT) denoising network outputs denoised images through an end-to-end mapping between an LDCT image and its corresponding ground truth. The limitation of this method is that the reduced noise level of the image may not meet the diagnostic needs of doctors. To establish a denoising model adapted to the multi-noise levels robustness, we proposed a novel and efficient modularized iterative network framework (MINF) to learn the feature of the original LDCT and the outputs of the previous modules, which can be reused in each following module. The proposed network can achieve the goal of gradual denoising, outputting clinical images with different denoising levels, and providing the reviewing physicians with increased confidence in their diagnosis. Moreover, a multi-scale convolutional neural network (MCNN) module is designed to extract as much feature information as possible during the network's training. Extensive experiments on public and private clinical datasets were carried out, and comparisons with several state-of-the-art methods show that the proposed method can achieve satisfactory results for noise suppression of LDCT images. In further comparisons with modularized adaptive processing neural network (MAP-NN), the proposed network shows superior step-by-step or gradual denoising performance. Considering the high quality of gradual denoising results, the proposed method can obtain satisfactory performance in terms of image contrast and detail protection as the level of denoising increases, which shows its potential to be suitable for a multi-dose levels denoising task.

A self-supervised guided knowledge distillation framework for unpaired low-dose CT image denoising.

Low-dose computed tomography (LDCT) can significantly reduce the damage of X-ray to the human body, but the reduction of CT dose will produce images with severe noise and artifacts, which will affect the diagnosis of doctors. Recently, deep learning has attracted more and more attention from researchers. However, most of the denoising networks applied to deep learning-based LDCT imaging are supervised methods, which require paired data for network training. In a realistic imaging scenario, obtaining well-aligned image pairs is challenging due to the error in the table re-positioning and the patient's physiological movement during data acquisition. In contrast, the unpaired learning method can overcome the drawbacks of supervised learning, making it more feasible to collect unpaired training data in most real-world imaging applications. In this study, we develop a novel unpaired learning framework, Self-Supervised Guided Knowledge Distillation (SGKD), which enables the guidance of supervised learning using the results generated by self-supervised learning. The proposed SGKD scheme contains two stages of network training. First, we can achieve the LDCT image quality improvement by the designed self-supervised cycle network. Meanwhile, it can also produce two complementary training datasets from the unpaired LDCT and NDCT images. Second, a knowledge distillation strategy with the above two datasets is exploited to further improve the LDCT image denoising performance. To evaluate the effectiveness and feasibility of the proposed method, extensive experiments were performed on the simulated AAPM challenging and real-world clinical LDCT datasets. The qualitative and quantitative results show that the proposed SGKD achieves better performance in terms of noise suppression and detail preservation compared with some state-of-the-art network models.

A multidomain fusion model of radiomics and deep learning to discriminate between PDAC and AIP based on 18F-FDG PET/CT images.

PURPOSE: To explore a multidomain fusion model of radiomics and deep learning features based on 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) images to distinguish pancreatic ductal adenocarcinoma (PDAC) and autoimmune pancreatitis (AIP), which could effectively improve the accuracy of diseases diagnosis. MATERIALS AND METHODS: This retrospective study included 48 patients with AIP (mean age, 65 ± 12.0 years; range, 37-90 years) and 64 patients with PDAC patients (mean age, 66 ± 11.3 years; range, 32-88 years). Three different methods were discussed to identify PDAC and AIP based on 18F-FDG PET/CT images, including the radiomics model (RAD_model), the deep learning model (DL_model), and the multidomain fusion model (MF_model). We also compared the classification results of PET/CT, PET, and CT images in these three models. In addition, we explored the attributes of deep learning abstract features by analyzing the correlation between radiomics and deep learning features. Five-fold cross-validation was used to calculate receiver operating characteristic (ROC), area under the roc curve (AUC), accuracy (Acc), sensitivity (Sen), and specificity (Spe) to quantitatively evaluate the performance of different classification models. RESULTS: The experimental results showed that the multidomain fusion model had the best comprehensive performance compared with radiomics and deep learning models, and the AUC, accuracy, sensitivity, specificity were 96.4% (95% CI 95.4-97.3%), 90.1% (95% CI 88.7-91.5%), 87.5% (95% CI 84.3-90.6%), and 93.0% (95% CI 90.3-95.6%), respectively. And our study proved that the multimodal features of PET/CT were superior to using either PET or CT features alone. First-order features of radiomics provided valuable complementary information for the deep learning model. CONCLUSION: The preliminary results of this paper demonstrated that our proposed multidomain fusion model fully exploits the value of radiomics and deep learning features based on 18F-FDG PET/CT images, which provided competitive accuracy for the discrimination of PDAC and AIP.

Domain-adaptive denoising network for low-dose CT via noise estimation and transfer learning.

BACKGROUND: In recent years, low-dose computed tomography (LDCT) has played an important role in the diagnosis CT to reduce the potential adverse effects of X-ray radiation on patients, while maintaining the same diagnostic image quality. PURPOSE: Deep learning (DL)-based methods have played an increasingly important role in the field of LDCT imaging. However, its performance is highly dependent on the consistency of feature distributions between training data and test data. Due to patient's breathing movements during data acquisition, the paired LDCT and normal dose CT images are difficult to obtain from realistic imaging scenarios. Moreover, LDCT images from simulation or clinical CT examination often have different feature distributions due to the pollution by different amounts and types of image noises. If a network model trained with a simulated dataset is used to directly test clinical patients' LDCT data, its denoising performance may be degraded. Based on this, we propose a novel domain-adaptive denoising network (DADN) via noise estimation and transfer learning to resolve the out-of-distribution problem in LDCT imaging. METHODS: To overcome the previous adaptation issue, a novel network model consisting of a reconstruction network and a noise estimation network was designed. The noise estimation network based on a double branch structure is used for image noise extraction and adaptation. Meanwhile, the U-Net-based reconstruction network uses several spatially adaptive normalization modules to fuse multi-scale noise input. Moreover, to facilitate the adaptation of the proposed DADN network to new imaging scenarios, we set a two-stage network training plan. In the first stage, the public simulated dataset is used for training. In the second transfer training stage, we will continue to fine-tune the network model with a torso phantom dataset, while some parameters are frozen. The main reason using the two-stage training scheme is based on the fact that the feature distribution of image content from the public dataset is complex and diverse, whereas the feature distribution of noise pattern from the torso phantom dataset is closer to realistic imaging scenarios. RESULTS: In an evaluation study, the trained DADN model is applied to both the public and clinical patient LDCT datasets. Through the comparison of visual inspection and quantitative results, it is shown that the proposed DADN network model can perform well in terms of noise and artifact suppression, while effectively preserving image contrast and details. CONCLUSIONS: In this paper, we have proposed a new DL network to overcome the domain adaptation problem in LDCT image denoising. Moreover, the results demonstrate the feasibility and effectiveness of the application of our proposed DADN network model as a new DL-based LDCT image denoising method.

Low-Dose CT Image Synthesis for Domain Adaptation Imaging Using a Generative Adversarial Network With Noise Encoding Transfer Learning.

Deep learning (DL) based image processing methods have been successfully applied to low-dose x-ray images based on the assumption that the feature distribution of the training data is consistent with that of the test data. However, low-dose computed tomography (LDCT) images from different commercial scanners may contain different amounts and types of image noise, violating this assumption. Moreover, in the application of DL based image processing methods to LDCT, the feature distributions of LDCT images from simulation and clinical CT examination can be quite different. Therefore, the network models trained with simulated image data or LDCT images from one specific scanner may not work well for another CT scanner and image processing task. To solve such domain adaptation problem, in this study, a novel generative adversarial network (GAN) with noise encoding transfer learning (NETL), or GAN-NETL, is proposed to generate a paired dataset with a different noise style. Specifically, we proposed a method to perform noise encoding operator and incorporate it into the generator to extract a noise style. Meanwhile, with a transfer learning (TL) approach, the image noise encoding operator transformed the noise type of the source domain to that of the target domain for realistic noise generation. One public and two private datasets are used to evaluate the proposed method. Experiment results demonstrated the feasibility and effectiveness of our proposed GAN-NETL model in LDCT image synthesis. In addition, we conduct additional image denoising study using the synthesized clinical LDCT data, which verified the merit of the proposed synthesis in improving the performance of the DL based LDCT processing method.

Transcriptomic analysis of wheat reveals possible resistance mechanism mediated by Yr10 to stripe rust.

Stripe rust, caused by Puccinia striiformis f. sp. tritici (Pst), is a catastrophic disease that threatens global wheat yield. Yr10 is a race-specific all-stage disease resistance gene in wheat. However, the resistance mechanism of Yr10 is poorly characterized. Therefore, to elucidate the potential molecular mechanism mediated by Yr10, transcriptomic sequencing was performed at 0, 18, and 48 h post-inoculation (hpi) of compatible wheat Avocet S (AvS) and incompatible near-isogenic line (NIL) AvS + Yr10 inoculated with Pst race CYR32. Respectively, 227, 208, and 4050 differentially expressed genes (DEGs) were identified at 0, 18, and 48 hpi between incompatible and compatible interaction. The response of Yr10 to stripe rust involved various processes and activities, as indicated by the results of Gene Ontology (GO) enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis. Specifically, the response included photosynthesis, defense response to fungus, metabolic processes related to salicylic acid (SA) and jasmonic acid (JA), and activities related to reactive oxygen species (ROS). Ten candidate genes were selected for qRT-PCR verification and the results showed that the transcriptomic data was reliable. Through the functional analysis of candidate genes by the virus-induced gene silencing (VIGS) system, it was found that the gene TaHPPD (4-hydroxyphenylpyruvate dioxygenase) negatively regulated the resistance of wheat to stripe rust by affecting SA signaling, pathogenesis-related (PR) gene expression, and ROS clearance. Our study provides insight into Yr10-mediated resistance in wheat.