Journal of X-Ray Science and Technology最新文献

{"title":"An effective COVID-19 classification in X-ray images using a new deep learning framework.","authors":"P Thilagavathi, R Geetha, S Jothi Shri, K Somasundaram","doi":"10.1177/08953996241290893","DOIUrl":"10.1177/08953996241290893","url":null,"abstract":"<p><p>BackgroundThe global concern regarding the diagnosis of lung-related diseases has intensified due to the rapid transmission of coronavirus disease 2019 (COVID-19). Artificial Intelligence (AI) based methods are emerging technologies that help to identify COVID-19 in chest X-ray images quickly.MethodIn this study, the publically accessible database COVID-19 Chest X-ray is used to diagnose lung-related disorders using a hybrid deep-learning approach. This dataset is pre-processed using an Improved Anisotropic Diffusion Filtering (IADF) method. After that, the features extraction methods named Grey-level Co-occurrence Matrix (GLCM), uniform Local Binary Pattern (uLBP), Histogram of Gradients (HoG), and Horizontal-vertical neighbourhood local binary pattern (hvnLBP) are utilized to extract the useful features from the pre-processed dataset. The dimensionality of a feature set is subsequently reduced through the utilization of an Adaptive Reptile Search Optimization (ARSO) algorithm, which optimally selects the features for flawless classification. Finally, the hybrid deep learning algorithm, Multi-head Attention-based Bi-directional Gated Recurrent unit with Deep Sparse Auto-encoder Network (MhA-Bi-GRU with DSAN), is developed to perform the multiclass classification problem. Moreover, a Dynamic Levy-Flight Chimp Optimization (DLF-CO) algorithm is applied to minimize the loss function in the hybrid algorithm.ResultsThe whole simulation is performed using the Python language in which the 0.001 learning rate accomplishes the proposed method's higher classification accuracy of 0.95%, and 0.98% is obtained for a 0.0001 learning rate. Overall, the performance of the proposed methodology outperforms all existing methods employing different performance parameters.ConclusionThe proposed hybrid deep-learning approach with various feature extraction, and optimal feature selection effectively diagnoses disease using Chest X-ray images demonstrated through classification accuracy.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"297-316"},"PeriodicalIF":1.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460408","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 cross-type multi-dimensional network based on feature enhancement and triple interactive attention for LDCT denoising.","authors":"Lina Jia, Beibei Jia, Zongyang Li, Yizhuo Zhang, Zhiguo Gui","doi":"10.1177/08953996241306696","DOIUrl":"10.1177/08953996241306696","url":null,"abstract":"<p><p>BackgroundNumerous deep leaning methods for low-dose computed technology (CT) image denoising have been proposed, achieving impressive results. However, issues such as loss of structure and edge information and low denoising efficiency still exist.ObjectiveTo improve image denoising quality, an enhanced multi-dimensional hybrid attention LDCT image denoising network based on edge detection is proposed in this paper.MethodsIn our network, we employ a trainable Sobel convolution to design an edge enhancement module and fuse an enhanced triplet attention network (ETAN) after each <math><mn>3</mn><mo>×</mo><mn>3</mn></math> convolutional layer to extract richer features more comprehensively and suppress useless information. During the training process, we adopt a strategy that combines total variation loss (TVLoss) with mean squared error (MSE) loss to reduce high-frequency artifacts in image reconstruction and balance image denoising and detail preservation.ResultsCompared with other advanced algorithms (CT-former, REDCNN and EDCNN), our proposed model achieves the best PSNR and SSIM values in CT image of the abdomen, which are 34.8211and 0.9131, respectively.ConclusionThrough comparative experiments with other related algorithms, it can be seen that the algorithm proposed in this article has achieved significant improvements in both subjective vision and objective indicators.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"393-404"},"PeriodicalIF":1.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460298","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 multi-model machine learning framework for breast cancer risk stratification using clinical and imaging data.","authors":"Lu Miao, Zidong Li, Jinnan Gao","doi":"10.1177/08953996241308175","DOIUrl":"10.1177/08953996241308175","url":null,"abstract":"<p><p>PurposeThis study presents a comprehensive machine learning framework for assessing breast cancer malignancy by integrating clinical features with imaging features derived from deep learning.MethodsThe dataset included 1668 patients with documented breast lesions, incorporating clinical data (e.g., age, BI-RADS category, lesion size, margins, and calcifications) alongside mammographic images processed using four CNN architectures: EfficientNet, ResNet, DenseNet, and InceptionNet. Three predictive configurations were developed: an imaging-only model, a hybrid model combining imaging and clinical data, and a stacking-based ensemble model that aggregates both data types to enhance predictive accuracy. Twelve feature selection techniques, including ReliefF and Fisher Score, were applied to identify key predictive features. Model performance was evaluated using accuracy and AUC, with 5-fold cross-valida tion and hyperparameter tuning to ensure robustness.ResultsThe imaging-only models demonstrated strong predictive performance, with EfficientNet achieving an AUC of 0.76. The hybrid model combining imaging and clinical data reached the highest accuracy of 83% and an AUC of 0.87, underscoring the benefits of data integration. The stacking-based ensemble model further optimized accuracy, reaching a peak AUC of 0.94, demonstrating its potential as a reliable tool for malignancy risk assessment.ConclusionThis study highlights the importance of integrating clinical and deep imaging features for breast cancer risk stratification, with the stacking-based model.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"360-375"},"PeriodicalIF":1.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460382","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":"Proximal femur segmentation and quantification in dual-energy subtraction tomosynthesis: A novel approach to fracture risk assessment.","authors":"Akari Matsushima, Tai-Been Chen, Koharu Kimura, Mizuki Sato, Shih-Yen Hsu, Takahide Okamoto","doi":"10.1177/08953996241312594","DOIUrl":"10.1177/08953996241312594","url":null,"abstract":"<p><p>BackgroundOsteoporosis is a major public health concern, especially among older adults, due to its association with an increased risk of fractures, particularly in the proximal femur. These fractures severely impact mobility and quality of life, leading to significant economic and health burdens.ObjectiveThis study aims to enhance bone density assessment in the proximal femur by addressing the limitations of conventional dual-energy X-ray absorptiometry through the integration of tomosynthesis with dual-energy applications and advanced segmentation models.Methods and MaterialsThe imaging capability of a radiography/fluoroscopy system with dual-energy subtraction was evaluated. Two phantoms were included in this study: a tomosynthesis phantom (PH-56) was used to measure the quality of the tomosynthesis images, and a torso phantom (PH-4) was used to obtain proximal femur images. Quantification of bone images was achieved by optimizing the energy subtraction (ene-sub) and scale factors to isolate bone pixel values while nullifying soft tissue pixel values. Both the faster region-based convolutional neural network (Faster R-CNN) and U-Net were used to segment the proximal femoral region. The performance of these models was then evaluated using the intersection-over-union (IoU) metric with a torso phantom to ensure controlled conditions.ResultsThe optimal ene-sub-factor ranged between 1.19 and 1.20, and a scale factor of around 0.1 was found to be suitable for detailed bone image observation. Regarding segmentation performance, a VGG19-based Faster R-CNN model achieved the highest mean IoU, outperforming the U-Net model (0.865 vs. 0.515, respectively).ConclusionsThese findings suggest that the integration of tomosynthesis with dual-energy applications significantly enhances the accuracy of bone density measurements in the proximal femur, and that the Faster R-CNN model provides superior segmentation performance, thereby offering a promising tool for bone density and osteoporosis management. Future research should focus on refining these models and validating their clinical applicability to improve patient outcomes.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"405-419"},"PeriodicalIF":1.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460451","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":"DR-ConvNeXt: DR classification method for reconstructing ConvNeXt model structure.","authors":"Pengfei Song, Yun Wu","doi":"10.1177/08953996241311190","DOIUrl":"10.1177/08953996241311190","url":null,"abstract":"<p><p>BackgroundDiabetic retinopathy (DR) is a major complication of diabetes and a leading cause of blindness among the working-age population. However, the complex distribution and variability of lesion characteristics within the dataset present significant challenges for achieving high-precision classification of DR images.ObjectiveWe propose an automatic classification method for DR images, named DR-ConvNeXt, which aims to achieve accurate diagnosis of lesion types.MethodsThe method involves designing a dual-branch addition convolution structure and appropriately increasing the number of stacked ConvNeXt Block convolution layers. Additionally, a unique primary-auxiliary loss function is introduced, contributing to a significant enhancement in DR classification accuracy within the DR-ConvNeXt model.ResultsThe model achieved an accuracy of 91.8%,sensitivity of 81.6%, and specificity of 97.9% on the APTOS dataset. On the Messidor-2 dataset, the model achieved an accuracy of 83.6%, sensitivity of 74.0%, and specificity of 94.6%.ConclusionsThe DR-ConvNeXt model's classification results on the two publicly available datasets illustrate the significant advantages in all evaluation indexes for DR classification.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"448-460"},"PeriodicalIF":1.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460439","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 detail-enhanced wavelet domain feature compensation network for sparse-view X-ray computed laminography.","authors":"Yawu Long, Qianglong Zhong, Jin Lu, Chengke Xiong","doi":"10.1177/08953996251319183","DOIUrl":"10.1177/08953996251319183","url":null,"abstract":"<p><p>BackgroundX-ray Computed Laminography (CL) is a popular industrial tool for non-destructive visualization of flat objects. However, high-quality CL imaging requires a large number of projections, resulting in a long imaging time. Reducing the number of projections allows acceleration of the imaging process, but decreases the quality of reconstructed images.ObjectiveOur objective is to build a deep learning network for sparse-view CL reconstruction.MethodsConsidering complementarities of feature extraction in different domains, we design an encoder-decoder network that enables to compensate the missing information during spatial domain feature extraction in wavelet domain. Also, a detail-enhanced module is developed to highlight details. Additionally, Swin Transformer and convolution operators are combined to better capture features.ResultsA total of 3200 pairs of 16-view and 1024-view CL images (2880 pairs for training, 160 pairs for validation, and 160 pairs for testing) of solder joints have been employed to investigate the performance of the proposed network. It is observed that the proposed network obtains the highest image quality with PSNR and SSIM of 37.875 ± 0.908 dB, 0.992 ± 0.002, respectively. Also, it achieves competitive results on the AAPM dataset.ConclusionsThis study demonstrates the effectiveness and generalization of the proposed network for sparse-view CL reconstruction.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"488-498"},"PeriodicalIF":1.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460401","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":"Research on ring artifact reduction method for CT images of nuclear graphite components.","authors":"Tianchen Zeng, Jintao Fu, Peng Cong, Ximing Liu, Guangduo Xu, Yuewen Sun","doi":"10.1177/08953996241308760","DOIUrl":"10.1177/08953996241308760","url":null,"abstract":"<p><p>BackgroundThe supporting structure of high-temperature gas-cooled reactors (HTGR) comprises over 3000 carbon/graphite components, necessitating computed tomography (CT) non-destructive testing before operational deployment as per reactor technical specifications. However, CT images are frequently marred by severe ring artifacts due to the response non-uniformity and non-linearity of detector units, which diminishes the ability to detect defects effectively.MethodsTo address this issue, we propose a physics-based ring artifacts reduction method for CT that employs pixel response correction. This method physically accounts for the cause of ring artifacts and leverages the prior knowledge of the detected object to enhance the accuracy of the detection process.ResultsOur proposed method achieved a notable reduction in ring artifacts, as evidenced by a 37.7% decrease in ring total variation (RTV) values compared to the originals, significantly enhancing image quality. It also surpassed traditional and machine learning methods in artifact reduction while maintaining image details. The lower RTV scores confirm our method's superior effectiveness in minimizing ring artifacts.ConclusionWe believe that our research contributes to the enhancement of defect inspection performance in detection systems, which is crucial for ensuring the safety of reactors. The proposed method's effectiveness in mitigating ring artifacts while maintaining image quality highlights its potential impact on the reliability of non-destructive testing in the context of HTGR components.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"317-324"},"PeriodicalIF":1.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460453","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":"Comparative analysis of machine learning and deep learning algorithms for knee arthritis detection using YOLOv8 models.","authors":"Ilkay Cinar","doi":"10.1177/08953996241308770","DOIUrl":"https://doi.org/10.1177/08953996241308770","url":null,"abstract":"<p><p>Knee arthritis is a prevalent joint condition that affects many people worldwide. Early detection and appropriate treatment are essential to slow the disease's progression and enhance patients' quality of life. In this study, various machine learning and deep learning algorithms were used to detect knee arthritis. The machine learning models included k-NN, SVM, and GBM, while DenseNet, EfficientNet, and InceptionV3 were used as deep learning models. Additionally, YOLOv8 classification models (YOLOv8n-cls, YOLOv8s-cls, YOLOv8m-cls, YOLOv8l-cls, and YOLOv8x-cls) were employed. The \"Annotated Dataset for Knee Arthritis Detection\" with five classes (Normal, Doubtful, Mild, Moderate, Severe) and 1650 images were divided into 80% training, 10% validation, and 10% testing using the Hold-Out method. YOLOv8 models outperformed both machine learning and deep learning algorithms. k-NN, SVM, and GBM achieved success rates of 63.61%, 64.14%, and 67.36%, respectively. Among deep learning models, DenseNet, EfficientNet, and InceptionV3 achieved 62.35%, 70.59%, and 79.41%. The highest success was seen in the YOLOv8x-cls model at 86.96%, followed by YOLOv8l-cls at 86.79%, YOLOv8m-cls at 83.65%, YOLOv8s-cls at 80.37%, and YOLOv8n-cls at 77.91%.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"8953996241308770"},"PeriodicalIF":1.7,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143517168","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":"DML-MFCM: A multimodal fine-grained classification model based on deep metric learning for Alzheimer's disease diagnosis.","authors":"Heng Wang, Tiejun Yang, Jiacheng Fan, Huiyao Zhang, Wenjie Zhang, Mingzhu Ji, Jianyu Miao","doi":"10.1177/08953996241300023","DOIUrl":"10.1177/08953996241300023","url":null,"abstract":"<p><strong>Background: </strong>Alzheimer's disease (AD) is a neurodegenerative disorder. There are no drugs and methods for the treatment of AD, but early intervention can delay the deterioration of the disease. Therefore, the early diagnosis of AD and mild cognitive impairment (MCI) is significant. Structural magnetic resonance imaging (sMRI) is widely used to present structural changes in the subject's brain tissue. The relatively mild structural changes in the brain with MCI have led to ongoing challenges in the task of conversion prediction in MCI. Moreover, many multimodal AD diagnostic models proposed in recent years ignore the potential relationship between multimodal information.</p><p><strong>Objective: </strong>To solve these problems, we propose a multimodal fine-grained classification model based on deep metric learning for AD diagnosis (DML-MFCM), which can fully exploit the fine-grained feature information of sMRI and learn the potential relationships between multimodal feature information.</p><p><strong>Methods: </strong>First, we propose a fine-grained feature extraction module that can effectively capture the fine-grained feature information of the lesion area. Then, we introduce a multimodal cross-attention module to learn the potential relationships between multimodal data. In addition, we design a hybrid loss function based on deep metric learning. It can guide the model to learn the feature representation method between samples, which improves the model's performance in disease diagnosis.</p><p><strong>Results: </strong>We have extensively evaluated the proposed models on the ADNI and AIBL datasets. The ACC of AD vs. NC, MCI vs. NC, and sMCI vs. pMCI tasks in the ADNI dataset are 98.75%, 95.88%, and 88.00%, respectively. The ACC on the AD vs. NC and MCI vs. NC tasks in the AIBL dataset are 94.33% and 91.67%.</p><p><strong>Conclusions: </strong>The results demonstrate that our method has excellent performance in AD diagnosis.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"211-228"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460331","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":"Bonevoyage: Navigating the depths of osteoporosis detection with a dual-core ensemble of cascaded ShuffleNet and neural networks.","authors":"Dhamodharan Srinivasan, Ajmeera Kiran, S Parameswari, Jeevanantham Vellaichamy","doi":"10.1177/08953996241289314","DOIUrl":"10.1177/08953996241289314","url":null,"abstract":"<p><strong>Background: </strong>Osteoporosis (OP) is a condition that significantly decreases bone density and strength, often remaining undetected until the occurrence of a fracture. Timely identification of OP is essential for preventing fractures, reducing morbidity, and enhancing the quality of life.</p><p><strong>Objective: </strong>This study aims to improve the accuracy, speed, and reliability of early-stage osteoporosis detection by integrating the compact architecture of Cascaded ShuffleNet with the pattern recognition prowess of Artificial Neural Networks (ANNs).</p><p><strong>Methods: </strong>BoneVoyage leverages the efficiency of ShuffleNet and the analytical capabilities of ANNs to extract and analyze complex features from bone density scans. The framework was trained and validated on a comprehensive dataset containing thousands of bone density images, ensuring robustness across diverse cases.</p><p><strong>Results: </strong>This model achieving an accuracy of 97.2%, with high sensitivity and specificity. These results significantly surpass those of existing OP detection methods, highlighting the effectiveness of the BoneVoyage framework in identifying subtle changes in bone density indicative of early-stage osteoporosis.</p><p><strong>Conclusions: </strong>BoneVoyage represents a significant advancement in the early detection of osteoporosis, offering a reliable tool for healthcare providers to identify at-risk individuals prematurely. The early detection facilitated by BoneVoyage allows for the implementation of preventive measures and targeted treatments.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"3-25"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460289","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}