Self-supervised tomographic image noise suppression via residual image prior network.

Computed tomography (CT) denoising is a challenging task in medical imaging that has garnered considerable attention. Supervised networks require a lot of noisy-clean image pairs, which are always unavailable in clinical settings. Existing self-supervised algorithms for suppressing noise with paired noisy images have limitations, such as ignoring the residual between similar image pairs during training and insufficiently learning the spectrum information of images. In this study, we propose a Residual Image Prior Network (RIP-Net) to sufficiently model the residual between the paired similar noisy images. Our approach offers new insights into the field by addressing the limitations of existing methods. We first establish a mathematical theorem clarifying the non-equivalence between similar-image-based self-supervised learning and supervised learning. It helps us better understand the strengths and limitations of self-supervised learning. Secondly, we introduce a novel regularization term to model a low-frequency residual image prior. This can improve the accuracy and robustness of our model. Finally, we design a well-structured denoising network capable of exploring spectrum information while simultaneously sensing context messages. The network has dual paths for modeling high and low-frequency compositions in the raw noisy image. Additionally, context perception modules capture local and global interactions to produce high-quality images. The comprehensive experiments on preclinical photon-counting CT, clinical brain CT, and low-dose CT datasets, demonstrate that our RIP-Net is superior to other unsupervised denoising methods.

How to update esophageal masses imaging using literature review (MRI and CT features).

MRI offers new opportunities for detailed visualization of the different layers of the esophageal wall, as well as early detection and accurate characterization of esophageal lesions. Staging of esophageal tumors including extramural extent of disease, and status of the adjacent organ can also be performed by MRI with higher accuracy compared to other imaging modalities including CT and esophageal endoscopy. Although MDCT appears to be the primary imaging modality that is indicated for preoperative staging of esophageal cancer to assess tumor resectability, MDCT is considered less accurate in T staging. This review aims to update radiologists about emerging imaging techniques and the imaging features of various esophageal masses, emphasizing the imaging features that differentiate between esophageal masses, demonstrating the critical role of MRI in esophageal masses. CRITICAL RELEVANCE STATEMENT: MRI features may help differentiate mucosal high-grade neoplasia from early invasive squamous cell cancer of the esophagus, also esophageal GISTs from leiomyomas, and esophageal malignant melanoma has typical MR features. KEY POINTS: MRI can accurately visualize different layers of the esophagus potentially has a role in T staging. MR may accurately delineate esophageal fistulae, especially small mediastinal fistulae. MRI features of various esophageal masses are helpful in the differentiation.

One-step inverse generation network for sparse-view dual-energy CT reconstruction and material imaging.

Objective.Sparse-view dual-energy spectral computed tomography (DECT) imaging is a challenging inverse problem. Due to the incompleteness of the collected data, the presence of streak artifacts can result in the degradation of reconstructed spectral images. The subsequent material decomposition task in DECT can further lead to the amplification of artifacts and noise.Approach.To address this problem, we propose a novel one-step inverse generation network (OIGN) for sparse-view dual-energy CT imaging, which can achieve simultaneous imaging of spectral images and materials. The entire OIGN consists of five sub-networks that form four modules, including the pre-reconstruction module, the pre-decomposition module, and the following residual filtering module and residual decomposition module. The residual feedback mechanism is introduced to synchronize the optimization of spectral CT images and materials.Main results.Numerical simulation experiments show that the OIGN has better performance on both reconstruction and material decomposition than other state-of-the-art spectral CT imaging algorithms. OIGN also demonstrates high imaging efficiency by completing two high-quality imaging tasks in just 50 seconds. Additionally, anti-noise testing is conducted to evaluate the robustness of OIGN.Significance.These findings have great potential in high-quality multi-task spectral CT imaging in clinical diagnosis.

Multiple diffusion models for predicting pathologic response of esophageal squamous cell carcinoma to neoadjuvant chemotherapy.

BACKGROUND: To assess the feasibility and diagnostic performance of the fractional order calculus (FROC), continuous-time random-walk (CTRW), diffusion kurtosis imaging (DKI), intravoxel incoherent motion (IVIM), mono-exponential (MEM) and stretched exponential models (SEM) for predicting response to neoadjuvant chemotherapy (NACT) in patients with esophageal squamous cell carcinoma (ESCC). MATERIALS AND METHODS: This study prospectively included consecutive ESCC patients with baseline and follow up MR imaging and pathologically confirmed cT1-4aN + M0 or T3-4aN0M0 and underwent radical resection after neoadjuvant chemotherapy (NACT) between July 2019 and January 2023. Patients were divided into pCR (TRG 0) and non-pCR (TRG1 + 2 + 3) groups according to tumor regression grading (TRG). The Pre-, Post- and Delta-treatment models were built. 18 predictive models were generated according to different feature categories, based on six models by five-fold cross-validation. Areas under the curve (AUCs) of the models were compared by using DeLong method. RESULTS: Overall, 90 patients (71 men, 19 women; mean age, 64 years ± 6 [SD]) received NACT and underwent baseline and Post-NACT esophageal MRI, with 29 patients in the pCR group and 61 patients in the non-pCR group. Among 18 predictive models, The Pre-, Post-, and Delta-CTRW model showed good predictive efficacy (AUC = 0.722, 0.833 and 0.790). Additionally, the Post-FROC model (AUC = 0.907) also exhibited good diagnostic performance. CONCLUSIONS: Our study indicates that the CTRW model, along with the Post-FROC model, holds significant promise for the future of NACT efficacy prediction in ESCC patients.

Quantitative assessment of preoperative brain development in pediatric congenital heart disease patients by synthetic MRI.

OBJECTIVES: This study investigated the quantitative assessment and application of Synthetic MRI (SyMRI) for preoperative brain development in children with congenital heart disease (CHD). METHODS: Forty-three CHD patients aged 2-24 months were prospectively included in the observation group, and 43 healthy infants were included in the control group. The SyMRI scans were processed by postprocessing software to obtain T1, T2, and PD maps. The values of T1, T2, and PD in different brain regions were compared with the scores of the five ability areas of the Gesell Development Scale by Pearson correlation analysis. RESULTS: In the observation group, the T1 values of the posterior limb of the internal capsule (PLIC), Optic radiation (PTR), cerebral peduncle, centrum semiovale, occipital white matter, temporal white matter, and dentate nucleus were greater than those in the control group. In the observation group, the T2 values of the PLIC, PTR, frontal white matter, occipital white matter, temporal white matter, and dentate nucleus were greater than those in the control group. Pearson correlation analysis revealed that the observation group had significantly lower Development Scale scores. In the observation group, the T2 value of the splenium of the corpus callosum was significantly positively correlated with the personal social behavior score. The AUCs for diagnosing preoperative brain developmental abnormalities in children with CHD using T1 values of the temporal white matter and dentate nucleus were both greater than 0.60. CONCLUSIONS: Quantitative assessment using SyMRI can aid in the early detection of preoperative brain development abnormalities in children with CHD. CRITICAL RELEVANCE STATEMENT: T1 and T2 relaxation values from SyMRI can be considered as a quantitative imaging marker to detect abnormalities, allowing for early clinical evaluation and timely intervention, thereby reducing neurodevelopmental disorders in these children. KEY POINTS: T1 and T2 relaxation values by SyMRI are related to myelin development. Evaluated development quotient markers were lower in the observation compared to the control group. SyMRI can act as a reference indicator for brain development in CHD children.

MISD-IR: material-image subspace decomposition-based iterative reconstruction with spectrum estimation for dual-energy computed tomography.

Background: Dual-energy computed tomography (DECT) is a promising technique, which can provide unique capability for material quantification. The iterative reconstruction of material maps requires spectral information and its accuracy is affected by spectral mismatch. Simultaneously estimating the spectra and reconstructing material maps avoids extra workload on spectrum estimation and the negative impact of spectral mismatch. However, existing methods are not satisfactory in image detail preservation, edge retention, and convergence rate. The purpose of this paper was to mine the similarity between the reconstructed images and the material images to improve the imaging quality, and to design an effective iteration strategy to improve the convergence efficiency. Methods: The material-image subspace decomposition-based iterative reconstruction (MISD-IR) with spectrum estimation was proposed for DECT. MISD-IR is an optimized model combining spectral estimation and material reconstruction with fast convergence speed and promising noise suppression capability. We proposed to reconstruct the material maps based on extended simultaneous algebraic reconstruction techniques and estimation of the spectrum with model spectral. To stabilize the iteration and alleviate the influence of errors, we introduced a weighted proximal operator based on the block coordinate descending algorithm (WP-BCD). Furthermore, the reconstructed computed tomography (CT) images were introduced to suppress the noise based on subspace decomposition, which relies on non-local regularization to prevent noise accumulation. Results: In numerical experiments, the results of MISD-IR were closer to the ground truth compared with other methods. In real scanning data experiments, the results of MISD-IR showed sharper edges and details. Compared with other one-step iterative methods in the experiment, the running time of MISD-IR was reduced by 75%. Conclusions: The proposed MISD-IR can achieve accurate material decomposition (MD) without known energy spectrum in advance, and has good retention of image edges and details. Compared with other one-step iterative methods, it has high convergence efficiency.

Knowledge domain and emerging trends in anxiety and depression after myocardial infarction research during 2002-2022: Bibliometric and visualized analysis.

Purpose: This study aimed to analyze developmental trends in anxiety and depression after myocardial infarction (ADMI) research in the past 20 years through bibliometrics analysis and predict future research directions. Methods: ADMI-related publications were retrieved from the Web of Science Core Collection. Bibliometric, VOSviewer, CiteSpace, and Bibliometrix software packages were used for bibliometric analysis and visualization. Results: Overall, 3220 ADMI-related publications were identified. The United States, China, and the Netherlands were the countries with the most publications. Carney RM, De Jonge P, and Blumenthal JA were the most influential researchers. In 2004, Van Melle JP, from the University of Groningen, published in Psychosomatic Medicine the most cited article. "Cardiac rehabilitation" was the primary focus area. "Cardiac rehabilitation," "management," "acute coronary syndrome," and "outcome" were the top four keywords in emerging research hotspots. Notably, the effect of traditional Chinese medicine on ADMI is an area of potential research value. Conclusion: Numerous studies have underscored the significance of cardiac rehabilitation. Present research focuses on managing anxiety and depression post-acute coronary syndrome and enhancing clinical outcomes through cardiac rehabilitation technology. Additionally, the therapeutic potential of traditional Chinese medicine for ADMI is expected to attract increased attention from researchers in the future.

Structural changes in corticospinal tract profiling via multishell diffusion models and their relation to overall survival in glioblastoma.

PURPOSE: Advanced MR fiber tracking imaging reflects fiber bundle invasion by glioblastoma, particularly of the corticospinal tract (CST), which is more susceptible as the largest downstream fiber tracts. We aimed to investigate whether CST features can predict the overall survival of glioblastoma. METHODS: In this prospective secondary analysis, 40 participants (mean age, 58 years; 16 male) pathologically diagnosed with glioblastoma were enrolled. Diffusion spectrum MRI was used for CST reconstruction. Fifty morphological and diffusion indicators (DTI, DKI, NODDI, MAP and Q-space) were used to characterize the CST. Optimal parameters capturing fiber bundle damage were obtained through various grouping methods. Eventually, the correlation with overall survival was determined by the hazard ratios (HRs) from various Cox proportional hazard model combinations. RESULTS: Only intracellular volume fraction (ICVF) and non-Gaussianity (NG) values on the affected tumor level were significant in all four groups or stratified comparisons (all P < .05). During the median follow-up 698 days, only the ICVF on the affected tumor level was independently associated with overall survival, even after adjusting for all classic prognostic factors (HR [95 % CI]: 0.611 [0.403, 0.927], P = .021). Moreover, stratification by the ICVF on the affected tumor level successfully predicted risk (P < .01) and improved the C-index of the multivariate model (from 0.695 to 0.736). CONCLUSIONS: This study demonstrates a relationship between NODDI-derived CST features, ICVF on the affected tumor level, and overall survival in glioblastoma. Independent of classical prognostic factors for glioblastoma, a lower ICVF on the affected tumor level might predict a lower overall survival.

Staging liver fibrosis with various diffusion-weighted magnetic resonance imaging models.

BACKGROUND: Diffusion-weighted imaging (DWI) has been developed to stage liver fibrosis. However, its diagnostic performance is inconsistent among studies. Therefore, it is worth studying the diagnostic value of various diffusion models for liver fibrosis in one cohort. AIM: To evaluate the clinical potential of six diffusion-weighted models in liver fibrosis staging and compare their diagnostic performances. METHODS: This prospective study enrolled 59 patients suspected of liver disease and scheduled for liver biopsy and 17 healthy participants. All participants underwent multi-b value DWI. The main DWI-derived parameters included Mono-apparent diffusion coefficient (ADC) from mono-exponential DWI, intravoxel incoherent motion model-derived true diffusion coefficient (IVIM-D), diffusion kurtosis imaging-derived apparent diffusivity (DKI-MD), stretched exponential model-derived distributed diffusion coefficient (SEM-DDC), fractional order calculus (FROC) model-derived diffusion coefficient (FROC-D) and FROC model-derived microstructural quantity (FROC-µ), and continuous-time random-walk (CTRW) model-derived anomalous diffusion coefficient (CTRW-D) and CTRW model-derived temporal diffusion heterogeneity index (CTRW-α). The correlations between DWI-derived parameters and fibrosis stages and the parameters' diagnostic efficacy in detecting significant fibrosis (SF) were assessed and compared. RESULTS: CTRW-D (r = -0.356), CTRW-α (r = -0.297), DKI-MD (r = -0.297), FROC-D (r = -0.350), FROC-µ (r = -0.321), IVIM-D (r = -0.251), Mono-ADC (r = -0.362), and SEM-DDC (r = -0.263) were significantly correlated with fibrosis stages. The areas under the ROC curves (AUCs) of the combined index of the six models for distinguishing SF (0.697-0.747) were higher than each of the parameters alone (0.524-0.719). The DWI models' ability to detect SF was similar. The combined index of CTRW model parameters had the highest AUC (0.747). CONCLUSION: The DWI models were similarly valuable in distinguishing SF in patients with liver disease. The combined index of CTRW parameters had the highest AUC.

Multi-channel Optimization Generative Model for Stable Ultra-Sparse-View CT Reconstruction.

Score-based generative model (SGM) has risen to prominence in sparse-view CT reconstruction due to its impressive generation capability. The consistency of data is crucial in guiding the reconstruction process in SGM-based reconstruction methods. However, the existing data consistency policy exhibits certain limitations. Firstly, it employs partial data from the reconstructed image of iteration process for image updates, which leads to secondary artifacts with compromising image quality. Moreover, the updates to the SGM and data consistency are considered as distinct stages, disregarding their interdependent relationship. Additionally, the reference image used to compute gradients in the reconstruction process is derived from intermediate result rather than ground truth. Motivated by the fact that a typical SGM yields distinct outcomes with different random noise inputs, we propose a Multi-channel Optimization Generative Model (MOGM) for stable ultra-sparse-view CT reconstruction by integrating a novel data consistency term into the stochastic differential equation model. Notably, the unique aspect of this data consistency component is its exclusive reliance on original data for effectively confining generation outcomes. Furthermore, we pioneer an inference strategy that traces back from the current iteration result to ground truth, enhancing reconstruction stability through foundational theoretical support. We also establish a multi-channel optimization reconstruction framework, where conventional iterative techniques are employed to seek the reconstruction solution. Quantitative and qualitative assessments on 23 views datasets from numerical simulation, clinical cardiac and sheep's lung underscore the superiority of MOGM over alternative methods. Reconstructing from just 10 and 7 views, our method consistently demonstrates exceptional performance.

Crown-ether threaded covalent organic polyrotaxane framework (COPF) towards synergistic crown/Zn2+/photothermal/photodynamic antibacterial and infected wound healing therapy.

Controllable preparation of materials with new structure has always been the top priority of polymer materials science research. Here, the supramolecular binding strategy is adopted to develop covalent organic frameworks (COFs) with novel structures and functions. Based on this, a two-dimensional crown-ether ring threaded covalent organic framework (COF), denoted as Crown-COPF with intrinsic photothermal (PTT) and photodynamic (PDT) therapeutic capacity, was facilely developed using crown-ether threaded rotaxane and porphyrin as building blocks. Crown-COPF with discrete mechanically interlocked blocks in the open pore could be used as a molecular machine, in which crown-ether served as the wheel sliding along the axle under the laser stimulation. As a result, Crown-COPF combining with the bactericidal power of crown ether displayed a significant photothermal and photodynamic antibacterial activity towards both the Gram-negative (Escherichia coli) and Gram-positive (Staphylococcus aureus), far exceeding the traditional Crown-free COF. Noteworthily, the bactericidal performance could be further enhanced via impregnation of Zn2+ ions (Crown-COPF-Zn) flexible coordinated with the multiple coordination sites (crown-ether, bipyridine, and porphyrin), which not only endow the positive charge with the skeleton, enhancing its ability to bind to the bacterial membrane, but also introduce the bactericidal ability of zinc ions. Notably, in vivo experiments on mice with back infections indicates Crown-COPF-Zn with self-adaptive multinuclear zinc center, could effectively promote the repairing of wounds. This study paves a new avenue for the effectively preparation of porous polymers with brand new structure, which provides opportunities for COF and mechanically interlocked polymers (MIPs) research and applications.

Coalescence-Induced Jumping of Nanodroplets in a Perpendicular Electric Field: A Molecular Dynamics Study.

Coalescence-induced jumping has promised a substantial reduction in the droplet detachment size and consequently shows great potential for heat-transfer enhancement in dropwise condensation. In this work, using molecular dynamics simulations, the evolution dynamics of the liquid bridge and the jumping velocity during coalescence-induced nanodroplet jumping under a perpendicular electric field are studied for the first time to further promote jumping. It is found that using a constant electric field, the jumping performance at the small intensity is weakened owing to the continuously decreased interfacial tension. There is a critical intensity above which the electric field can considerably enhance the stretching effect with a stronger liquid-bridge impact and, hence, improve the jumping performance. For canceling the inhibition effect of the interfacial tension under the condition of the weak electric field, a square-pulsed electric field with a paused electrical effect at the expansion stage of the liquid bridge is proposed and presents an efficient nanodroplet jumping even using the weak electric field.

Genome-wide analysis of the switchgrass YABBY family and functional characterization of PvYABBY14 in response to ABA and GA stress in Arabidopsis.

BACKGROUND: The small YABBY plant-specific transcription factor has a prominent role in regulating plant growth progress and responding to abiotic stress. RESULTS: Here, a total of 16 PvYABBYs from switchgrass (Panicum virgatum L.) were identified and classified into four distinct subgroups. Proteins within the same subgroup exhibited similar conserved motifs and gene structures. Synteny analyses indicated that segmental duplication contributed to the expansion of the YABBY gene family in switchgrass and that complex duplication events occurred in rice, maize, soybean, and sorghum. Promoter regions of PvYABBY genes contained numerous cis-elements related to stress responsiveness and plant hormones. Expression profile analysis indicated higher expression levels of many PvYABBY genes during inflorescence development and seed maturation, with lower expression levels during root growth. Real-time quantitative PCR analysis demonstrated the sensitivity of multiple YABBY genes to PEG, NaCl, ABA, and GA treatments. The overexpression of PvYABBY14 in Arabidopsis resulted in increased root length after treatment with GA and ABA compared to wild-type plants. CONCLUSIONS: Taken together, our study provides the first genome-wide overview of the YABBY transcription factor family, laying the groundwork for understanding the molecular basis and regulatory mechanisms of PvYABBY14 in response to ABA and GA responses in switchgrass.

A dual-energy CT reconstruction method based on anchor network from dual quarter scans.

Compared with conventional single-energy computed tomography (CT), dual-energy CT (DECT) provides better material differentiation but most DECT imaging systems require dual full-angle projection data at different X-ray spectra. Relaxing the requirement of data acquisition is an attractive research to promote the applications of DECT in wide range areas and reduce the radiation dose as low as reasonably achievable. In this work, we design a novel DECT imaging scheme with dual quarter scans and propose an efficient method to reconstruct the desired DECT images from the dual limited-angle projection data. We first study the characteristics of limited-angle artifacts under dual quarter scans scheme, and find that the negative and positive artifacts of DECT images are complementarily distributed in image domain because the corresponding X-rays of high- and low-energy scans are symmetric. Inspired by this finding, a fusion CT image is generated by integrating the limited-angle DECT images of dual quarter scans. This strategy enhances the true image information and suppresses the limited-angle artifacts, thereby restoring the image edges and inner structures. Utilizing the capability of neural network in the modeling of nonlinear problem, a novel Anchor network with single-entry double-out architecture is designed in this work to yield the desired DECT images from the generated fusion CT image. Experimental results on the simulated and real data verify the effectiveness of the proposed method. This work enables DECT on imaging configurations with half-scan and largely reduces scanning angles and radiation doses.

Spectrum learning for super-resolution tomographic reconstruction.

Objective. Computed Tomography (CT) has been widely used in industrial high-resolution non-destructive testing. However, it is difficult to obtain high-resolution images for large-scale objects due to their physical limitations. The objective is to develop an improved super-resolution technique that preserves small structures and details while efficiently capturing high-frequency information.Approach. The study proposes a new deep learning based method called spectrum learning (SPEAR) network for CT images super-resolution. This approach leverages both global information in the image domain and high-frequency information in the frequency domain. The SPEAR network is designed to reconstruct high-resolution images from low-resolution inputs by considering not only the main body of the images but also the small structures and other details. The symmetric property of the spectrum is exploited to reduce weight parameters in the frequency domain. Additionally, a spectrum loss is introduced to enforce the preservation of both high-frequency components and global information.Main results. The network is trained using pairs of low-resolution and high-resolution CT images, and it is fine-tuned using additional low-dose and normal-dose CT image pairs. The experimental results demonstrate that the proposed SPEAR network outperforms state-of-the-art networks in terms of image reconstruction quality. The approach successfully preserves high-frequency information and small structures, leading to better results compared to existing methods. The network's ability to generate high-resolution images from low-resolution inputs, even in cases of low-dose CT images, showcases its effectiveness in maintaining image quality.Significance. The proposed SPEAR network's ability to simultaneously capture global information and high-frequency details addresses the limitations of existing methods, resulting in more accurate and informative image reconstructions. This advancement can have substantial implications for various industries and medical diagnoses relying on accurate imaging.

Intramuscular therapeutic doses of enrofloxacin affect microbial community structure but not the relative abundance of fluoroquinolones resistance genes in swine manure.

Livestock manure is a major source of veterinary antibiotics and antibiotic resistance genes (ARGs). Elucidation of the residual characteristics of ARGs in livestock manure following the administration of veterinary antibiotics is critical to assess their ecotoxicological effects and environmental contamination risks. Here, we investigated the effects of enrofloxacin (ENR), a fluoroquinolone antibiotic commonly used as a therapeutic drug in animal husbandry, on the characteristics of ARGs, mobile genetic elements, and microbial community structure in swine manure following its intramuscular administration for 3 days and a withdrawal period of 10 days. The results revealed the highest concentrations of ENR and ciprofloxacin (CIP) in swine manure at the end of the administration period, ENR concentrations in swine manure in groups L and H were 88.67 ± 45.46 and 219.75 ± 88.05 mg/kg DM, respectively. Approximately 15 fluoroquinolone resistance genes (FRGs) and 48 fluoroquinolone-related multidrug resistance genes (F-MRGs) were detected in swine manure; the relative abundance of the F-MRGs was considerably higher than that of the FRGs. On day 3, the relative abundance of qacA was significantly higher in group H than in group CK, and no significant differences in the relative abundance of other FRGs, F-MRGs, or MGEs were observed between the three groups on day 3 and day 13. The microbial community structure in swine manure was significantly altered on day 3, and the altered community structure was restored on day 13. The FRGs and F-MRGs with the highest relative abundance were qacA and adeF, respectively, and Clostridium and Lactobacillus were the dominant bacterial genera carrying these genes in swine manure. In summary, a single treatment of intramuscular ENR transiently increased antibiotic concentrations and altered the microbial community structure in swine manure; however, this treatment did not significantly affect the abundance of FRGs and F-MRGs.

Iterative Residual Optimization Network for Limited-Angle Tomographic Reconstruction.

Limited-angle tomographic reconstruction is one of the typical ill-posed inverse problems, leading to edge divergence with degraded image quality. Recently, deep learning has been introduced into image reconstruction and achieved great results. However, existing deep reconstruction methods have not fully explored data consistency, resulting in poor performance. In addition, deep reconstruction methods are still mathematically inexplicable and unstable. In this work, we propose an iterative residual optimization network (IRON) for limited-angle tomographic reconstruction. First, a new optimization objective function is established to overcome false negative and positive artifacts induced by limited-angle measurements. We integrate neural network priors as a regularizer to explore deep features within residual data. Furthermore, the block-coordinate descent is employed to achieve a novel iterative framework. Second, a convolution assisted transformer is carefully elaborated to capture both local and long-range pixel interactions simultaneously. Regarding the visual transformer, the multi-head attention is further redesigned to reduce computational costs and protect reconstructed image features. Third, based on the relative error convergence property of the convolution assisted transformer, a mathematical convergence analysis is also provided for our IRON. Both numerically simulated and clinically collected real cardiac datasets are employed to validate the effectiveness and advantages of the proposed IRON. The results show that IRON outperforms other state-of-the-art methods.

Visual Exploratory Analysis for Designing Large-Scale Network-on-Chip Architectures: A Domain Expert-Led Design Study.

Visualization design studies bring together visualization researchers and domain experts to address yet unsolved data analysis challenges stemming from the needs of the domain experts. Typically, the visualization researchers lead the design study process and implementation of any visualization solutions. This setup leverages the visualization researchers' knowledge of methodology, design, and programming, but the availability to synchronize with the domain experts can hamper the design process. We consider an alternative setup where the domain experts take the lead in the design study, supported by the visualization experts. In this study, the domain experts are computer architecture experts who simulate and analyze novel computer chip designs. These chips rely on a Network-on-Chip (NOC) to connect components. The experts want to understand how the chip designs perform and what in the design led to their performance. To aid this analysis, we develop Vis4Mesh, a visualization system that provides spatial, temporal, and architectural context to simulated NOC behavior. Integration with an existing computer architecture visualization tool enables architects to perform deep-dives into specific architecture component behavior. We validate Vis4Mesh through a case study and a user study with computer architecture researchers. We reflect on our design and process, discussing advantages, disadvantages, and guidance for engaging in a domain expert-led design studies.