Journal of X-Ray Science and Technology最新文献

{"title":"A novel high order directional total variation algorithm of EPR imaging for fast scan.","authors":"Chenyun Fang, Yarui Xi, Rui Hu, Peng Liu, Yanjun Zhang, Wenjian Wang, Boris Epel, Howard Halpern, Zhiwei Qiao","doi":"10.1177/08953996251355885","DOIUrl":"https://doi.org/10.1177/08953996251355885","url":null,"abstract":"<p><p>BackgroundPulsed Electron paramagnetic resonance (EPR) imaging (EPRI) is an advanced oxygen imaging modality for precision radiotherapy, typically acquires high signal-to-noise ratio (SNR) data by averaging the repeatedly collected projections at the corresponding angle to suppress the random noise. This scan mode is the reason for the slow scan speed. The present mitigation is to reduce the repetition times (termed 'shots') for each projection, which leads to noisy projections.ObjectiveAlthough the directional total variation (DTV) algorithm could reconstruct the image from these noisy projections, it may appear staircase artifacts. To solve this problem, we further propose a novel high order DTV (HODTV) algorithm for fast 3D pulsed EPRI.MethodsThe HODTV model has introduced the regularization of high order derivatives, in which the objective term and the high order derivate regularization aim for data fidelity and detail recovery, respectively. Then, we derive its Chambolle-Pock (CP) solving algorithm and verify the correctness. To evaluate the HODTV algorithm, both qualitative and quantitative results are performed with real-world data.ResultsCompared with the filtered back projection (FBP), total variation (TV), and DTV algorithms, the results demonstrate that our method can achieve higher accurate reconstruction. In specific cases, our algorithm only requires 100 shots of scan acquisitions in <math><mo>∼</mo></math>6 seconds, whereas the FBP algorithm needs 2000 shots of scan acquisitions taking <math><mo>∼</mo></math>120 seconds.ConclusionsThe practical development of clinical imaging workflow, including but not limited to fast 3D pulsed EPRI, may make use of our work.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"8953996251355885"},"PeriodicalIF":1.4,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145208166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A discrete grayscale prior-based exterior reconstruction algorithm for polychromatic X-ray CT.","authors":"Haifang Fu, Zhiting Liu, Yunsong Zhao","doi":"10.1177/08953996251370578","DOIUrl":"https://doi.org/10.1177/08953996251370578","url":null,"abstract":"<p><p>Exterior CT imaging is a special X-ray imaging problem that allows for nondestructive testing of relatively large tubular samples by using smaller detectors. However, due to the incomplete nature of the exterior projection data, the exterior CT imaging problem is highly challenging. In this study, we introduce a new CT reconstruction model for polychromatic spectrum exterior problems, called the Polychromatic Exterior Discrete Grayscale PAEDS (PE-DG-PAEDS) model. This model is based on the prior of discrete grayscale values in images and introduces a radial regularization term using polychromatic spectrum information for exterior CT reconstruction. Additionally, an alternating minimization method and the Discrete Algebraic Reconstruction Technique (DART) algorithm are used for alternating iterations to provide a solution algorithm for this model. Experiments conducted with both simulated and real data have validated the proposed model and algorithm. The results indicate that the method effectively suppresses artifacts associated with polychromatic X-ray CT exterior problem.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"8953996251370578"},"PeriodicalIF":1.4,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145180216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel scatter correction method for energy-resolving photon-counting detector based CBCT imaging.","authors":"Xin Zhang, Heran Wang, Yuhang Tan, Jiongtao Zhu, Hairong Zheng, Dong Liang, Yongshuai Ge","doi":"10.1177/08953996251351618","DOIUrl":"https://doi.org/10.1177/08953996251351618","url":null,"abstract":"<p><p>BackgroundTo generate high-quality CT images for an energy-resolving photon-counting detector (PCD) based cone beam CT (CBCT) system, it is essential to mitigate the scatter shading artifacts.ObjectiveThe aim of this study is to explore the capability of an energy-modulated scatter correction method, named e-Grid, in removing the scatter shading artifacts in energy-resolving PCD CBCT imaging.MethodsIn the e-Grid method, a linear approximation is assumed between the high-energy primary/scatter signals and the low-energy primary/scatter signals acquired from the two energy windows of a PCD. Calibration experiments were conducted to determine the parameters used in the aforementioned signal model. Physical validation experiments with head and abdominal phantoms were performed on a PCD CBCT imaging benchtop system.ResultsIt was found that the e-Grid method could significantly eliminate scatter cupping artifacts in both low-energy and high-energy PCD CBCT imaging for objects with varying dimensions. Quantitatively, results demonstrated that the e-Grid method reduced scatter artifacts by more than 70% in both low-energy and high-energy PCD CBCT images.ConclusionsIn this study, it is demonstrated that the e-Grid scatter correction method has great potential for reducing scatter shading artifacts in energy-resolving PCD CBCT imaging.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"8953996251351618"},"PeriodicalIF":1.4,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145151327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adversarial consistency-based semi-supervised pneumonia segmentation using dual multiscale feature selection and fusion mean teacher model and triple-attention dynamic convolution in chest CTs.","authors":"Yu Gu, Jianning Zang, Lidong Yang, Baohua Zhang, Jing Wang, Xiaoqi Lu, Jianjun Li, Xin Liu, Ying Zhao, Dahua Yu, Siyuan Tang, Qun He","doi":"10.1177/08953996251367210","DOIUrl":"https://doi.org/10.1177/08953996251367210","url":null,"abstract":"<p><p>Recently, semi-supervised learning has demonstrated significant potential in the field of medical image segmentation. However, the majority of the methods fail to establish connections among diverse sample data. Moreover, segmentation networks that utilize fixed parameters can impede model training and even amplify the risk of overfitting. To address these challenges, this paper proposes an adversarial consistency-based semi-supervised segmentation method, leveraging a dual multiscale mean teacher model. First, by designing a discriminator network with adaptive feature selection and training it alternately with the segmentation network, the method enhances the segmentation network's ability to transfer knowledge from the limited labeled data to the unlabeled data. The discriminator evaluates the quality of the segmentation network's results for both labeled and unlabeled data, while simultaneously guiding the network to learn consistency in segmentation performance throughout the training process. Second, we design a Triple-attention dynamic convolutional (TADC) module, which allows the convolution kernel parameters to be adjusted flexibly according to different input data. This improves the feature representation capability of the network model and helps reduce the risk of overfitting. Finally, we propose a novel feature selection and fusion module (FSFM) within the segmentation network, which dynamically selects and integrates important features to enhance the saliency of key information, improving the overall performance of the model. The proposed adversarial consistency-based semi-supervised segmentation method is applied to the MosMedData dataset. The results demonstrate that the segmentation network outperforms the baseline model, achieving improvements of 3.83%, 3.97%, 3.14% in terms of Dice, Jaccard, and NSD scores, respectively, for the segmentation of pneumonia lesions. The proposed segmentation method outperforms state-of-the-art segmentation networks and demonstrates superior potential for segmenting pneumonia lesions, as evidenced by extensive experiments conducted on the MosMedData and COVID-19-P20 datasets.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"8953996251367210"},"PeriodicalIF":1.4,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145070997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"M²KD-Net: A multimodal multi-domain knowledge-driven framework for Parkinson's disease diagnosis.","authors":"Xiangze Teng, Xiang Li, Benzheng Wei","doi":"10.1177/08953996251358141","DOIUrl":"https://doi.org/10.1177/08953996251358141","url":null,"abstract":"<p><p>Parkinson's disease (PD) is a challenging neurodegenerative condition often prone to diagnostic errors, where early and accurate diagnosis is critical for effective clinical management. However, existing diagnostic methods often fail to fully exploit multimodal data or systematically incorporate expert domain knowledge. To address these limitations, we propose M²KD-Net, a multimodal and knowledge-driven diagnostic framework that integrates imaging and non-imaging clinical data with structured expert insights to enhance diagnostic performance. The framework consists of three key modules: (1) a contrastive learning-based multimodal feature extractor for improved alignment between imaging and non-imaging data. (2) an expert feature modeling module that encodes domain-specific knowledge through structured annotations, and (3) a cross-modal interaction module that enhances the integration of heterogeneous features across modalities. Experimental results on the Parkinson's Progression Markers Initiative (PPMI) dataset show that M²KD-Net achieves a classification accuracy of 89.6% and an AUC of 0.935 in distinguishing PD patients from healthy controls. This evidence suggests that the developed method provides a dependable, interpretable, and clinically useful solution for PD diagnosis.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"8953996251358141"},"PeriodicalIF":1.4,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145024700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prescriptive analytics decision-making system for cardiovascular disease prediction in long COVID patients using advanced reinforcement learning algorithms.","authors":"Diana Juliet S, Banumathi J","doi":"10.1177/08953996251335115","DOIUrl":"10.1177/08953996251335115","url":null,"abstract":"<p><p>In recent years Covid-19 impact is causing unprecedented difficulties worldwide, affecting lifestyle choices. The post-pandemic era has made this even more critical.COVID-19 triggers widespread inflammation throughout the body, potentially causing damage to the heart and other vital organs. Mortality data from COVID-19 clearly show that the highest death rates occur in individuals with chronic conditions, such as diabetes, pneumonia, cardiovascular disease (CVD), and acute renal failure.CVD is a particular concern in the medical field. The early detection of CVD remains a significant challenge, as early identification can prompt lifestyle changes and ensure appropriate medical interventions when needed. Individuals with CVD are at an increased risk for heart attack and other serious complications. There is a limited amount of data available to study the effects of COVID-19 on CVD in COVID-19 patients. However, it is essential to monitor these patients to ensure full recovery without complications. The proposed system is specifically designed for individuals experiencing prolonged symptoms following a COVID-19 infection, commonly referred to as long COVID patients. This research introduces a novel Decision-Making System for CVD Prediction, utilizing an improved dual-attention residual bi-directional gated recurrent neural network unit (DA-ResBiGRU) algorithm with AI-Biruni Earth Radius Optimization (ABER). The proposed system employs state-of-the-art predictive algorithms and real-time monitoring to assess individual patient risk profiles accurately. This research addresses the critical need for personalized risk assessment in patients with long-term COVID, aiming to assist healthcare providers in timely and targeted interventions. By analyzing intricate patterns in patient data, the decision-making system enhances the precision of CVD prediction. Additionally, the system's adaptive nature allows it to continuously learn from new patient data, ensuring that its predictions remain up-to-date and reflective of the evolving understanding of long COVID-related cardiovascular risks. The simulation findings of this research highlight the potential of the proposed algorithm to be integrated into clinical decision-making, helping healthcare professionals identify high-risk patients more effectively. The proposed method outperformed existing algorithms, such as Deep Neural Network (DNN), Long short-term memory (LSTM), Inception-v3, Xception, and MobileNetV2, achieving the highest accuracy (97.88%), sensitivity (95.50%), specificity (94.29%), precision (96.68%), and F-measure (95.85%).</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"879-900"},"PeriodicalIF":1.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144028985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A directional relative TV algorithm for sparse-view CT reconstruction.","authors":"Yanan Wang, Yu Wang, Peng Liu, Chenyun Fang, Yanjun Zhang, Ruotong Yang, Zhiwei Qiao","doi":"10.1177/08953996251337909","DOIUrl":"10.1177/08953996251337909","url":null,"abstract":"<p><strong>Objective: </strong>Computed tomography (CT) is a widely used medical imaging modality, but its radiation exposure poses potential risks to human health. Sparse-view scanning has emerged as an effective approach to reduce radiation dose; however, images reconstructed using the filtered back-projection (FBP) algorithm from sparse-view projections often suffer from severe streak artifacts. Achieving high-quality CT image reconstructed from sparse-view projections remains a challenging task.</p><p><strong>Methods: </strong>Building on compressed sensing (CS), the total variation (TV) algorithm is applied for high-quality sparse-view reconstruction. We further propose a relative total variation (RTV) algorithm to enhance the accuracy of sparse-view reconstruction. Experimental results indicate that while the RTV algorithm improves accuracy, it has limitations in edge preservation. To address this, inspired by the success of directional TV (DTV) in limited-angle reconstruction, we develop a directional relative TV (DRTV) model. This model applies the RTV technique in both x and y directions independently, and we derive its adaptive steepest descent projection onto convex set (ASD-POCS) solution algorithm.</p><p><strong>Results: </strong>Experiments conducted on simulated phantoms and real CT images demonstrate the correctness, convergence, and superior performance of the DRTV algorithm in sparse-view reconstruction. Compared with the TV, DTV, and RTV algorithm, the DRTV algorithm exhibits superior preservation of structural features and texture details.</p><p><strong>Significance: </strong>The DRTV algorithm represents an advanced method for high-precision sparse-view CT reconstruction, providing stable and accurate results. Moreover, the approach is applicable to other medical imaging modalities.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"866-878"},"PeriodicalIF":1.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144037493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Time-frequency domain prior constrained deep unfolding network for low-dose CT reconstruction.","authors":"Xiong Zhang, Xinbo Zhang, Xinzhong Li, Zulfiqur Ali, Yue Wang, Hong Shangguan, Xueying Cui","doi":"10.1177/08953996251319187","DOIUrl":"https://doi.org/10.1177/08953996251319187","url":null,"abstract":"<p><strong>Background: </strong>Low-dose computed tomography (LDCT) effectively reduces the risk of malignant disease; however, reducing the radiation dose introduces additional noise and stripe artifacts in the CT imaging process. While Convolutional Neural Networks (CNN) have demonstrated performance advantages in LDCT imaging tasks, their end-to-end network architecture limits adaptability to CT reconstruction tasks, leaving room for further performance improvement.</p><p><strong>Objective: </strong>To propose a low-dose CT reconstruction network based on the iterative algorithms, incorporating an interpretable network architecture to achieve superior reconstruction performance.</p><p><strong>Methods: </strong>To better adapt to CT reconstruction tasks, we proposed an interpretable deep unfolding network leveraging time-frequency and image domain priors to fully exploit the features extracted in the transform domain. The iterative optimization process of the proposed algorithm is mapped into a deep unfolding network, and a Stage Information Memory Network (SIMN) is designed to address information loss between adjacent stages and within each stage.</p><p><strong>Results: </strong>Experimental results on Mayo and Piglet datasets show that the proposed model outperforms state-of-the-art techniques in both quantitative metrics and visual quality.</p><p><strong>Conclusions: </strong>The proposed network effectively removes artifacts and noise from low-dose CT images, achieving excellent reconstruction performance.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":"33 5","pages":"819-830"},"PeriodicalIF":1.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning-based multi-material CBCT image reconstruction with ultra-slow kV switching.","authors":"Chenchen Ma, Jiongtao Zhu, Xin Zhang, Han Cui, Yuhang Tan, Jinchuan Guo, Hairong Zheng, Dong Liang, Ting Su, Yi Sun, Yongshuai Ge","doi":"10.1177/08953996251331790","DOIUrl":"10.1177/08953996251331790","url":null,"abstract":"<p><p>ObjectiveThe purpose of this study is to perform multiple (<math><mo>≥</mo><mn>3</mn></math>) material decomposition with deep learning method for spectral cone-beam CT (CBCT) imaging based on ultra-slow kV switching.ApproachIn this work, a novel deep neural network called SkV-Net is developed to reconstruct multiple material density images from the ultra-sparse spectral CBCT projections acquired using the ultra-slow kV switching technique. In particular, the SkV-Net has a backbone structure of U-Net, and a multi-head axial attention module is adopted to enlarge the perceptual field. It takes the CT images reconstructed from each kV as input, and output the basis material images automatically based on their energy-dependent attenuation characteristics. Numerical simulations and experimental studies are carried out to evaluate the performance of this new approach.Main ResultsIt is demonstrated that the SkV-Net is able to generate four different material density images, i.e., fat, muscle, bone and iodine, from five spans of kV switched spectral projections. Physical experiments show that the decomposition errors of iodine and CaCl<math><msub><mrow></mrow><mn>2</mn></msub></math> are less than 6<math><mi>%</mi></math>, indicating high precision of this novel approach in distinguishing materials.SignificanceSkV-Net provides a promising multi-material decomposition approach for spectral CBCT imaging systems implemented with the ultra-slow kV switching scheme.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"831-843"},"PeriodicalIF":1.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144056865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Erratum to \"Mask R-CNN assisted diagnosis of spinal tuberculosis\".","authors":"","doi":"10.1177/08953996251346352","DOIUrl":"10.1177/08953996251346352","url":null,"abstract":"","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"1012"},"PeriodicalIF":1.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144133174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}