{"title":"Enhancing brain tumor classification by integrating radiomics and deep learning features: A comprehensive study utilizing ensemble methods on MRI scans.","authors":"Liang Yin, Jing Wang","doi":"10.1177/08953996241299996","DOIUrl":"10.1177/08953996241299996","url":null,"abstract":"<p><strong>Background and objective: </strong>This study aims to assess the effectiveness of combining radiomics features (RFs) with deep learning features (DFs) for classifying brain tumors-specifically Glioma, Meningioma, and Pituitary Tumor-using MRI scans and advanced ensemble learning techniques.</p><p><strong>Methods: </strong>A total of 3064 T1-weighted contrast-enhanced brain MRI scans were analyzed. RFs were extracted using Pyradiomics, while DFs were obtained from a 3D convolutional neural network (CNN). These features were used both individually and together to train a range of machine learning models, including Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF), AdaBoost, Bagging, k-Nearest Neighbors (KNN), and Multi-Layer Perceptrons (MLP). To enhance the accuracy of these models, ensemble approaches such as Stacking, Voting, and Boosting were employed. LASSO feature selection and five-fold cross-validation were utilized to ensure the models' robustness.</p><p><strong>Results: </strong>The results demonstrated that combining RFs and DFs significantly improved the model's performance compared to using either feature set alone. The best performance was achieved using the combined RF + DF approach with ensemble methods, particularly Boosting, which resulted in an accuracy of 95.0%, an AUC of 0.92, a sensitivity of 88%, and a specificity of 90%. Conversely, models utilizing only RFs or DFs showed lower performance, with RFs reaching an AUC of 0.82 and DFs achieving an AUC of 0.85.</p><p><strong>Conclusion: </strong>The integration of RFs and DFs, along with advanced ensemble methods, significantly improves the accuracy and reliability of brain tumor classification using MRI. This approach shows strong clinical potential, with opportunities for further enhancing generalizability and precision through additional MRI sequences and advanced machine learning techniques.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"47-57"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460307","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":"Quantitative analysis of deep learning reconstruction in CT angiography: Enhancing CNR and reducing dose.","authors":"Chang-Lae Lee","doi":"10.1177/08953996241301696","DOIUrl":"10.1177/08953996241301696","url":null,"abstract":"<p><strong>Background: </strong>Computed tomography angiography (CTA) provides significant information on image quality in vascular imaging, thus offering high-resolution images despite having the disadvantages of increased radiation doses and contrast agent-related side effects. The deep-learning image reconstruction strategies were used to quantitatively evaluate the enhanced contrast-to-noise ratio (CNR) and the dose reduction effect of subtracted images.</p><p><strong>Objective: </strong>This study aimed to elucidate a comprehensive understanding of the quantitative image quality features of the conventional filtered back projection (FBP) and the advanced intelligent clear-IQ engine (AiCE), a deep learning reconstruction technique. The comparison was made in subtracted images with variable concentrations of contrast agents at variable tube currents and voltages, enhancing our knowledge of these two techniques.</p><p><strong>Methods: </strong>Data were obtained using a state-of-the-art 320-detector CT scanner. Image reconstruction was performed using FBP and AiCE with various intensities. The image quality evaluation was based on eight iodine concentrations in the phantom setup. The efficiency of AiCE relative to FBP was assessed by computing parameters including the root mean square error (RMSE), dose-dependent CNR, and potential dose reduction.</p><p><strong>Results: </strong>The results showed that elevated concentrations of iodine and increased tube currents improved AiCE performance regarding CNR enhancement compared to FBP. AiCE also demonstrated a potential dose reduction ranging from 13.7 to 81.9% compared to FBP, suggesting a significant reduction in radiation exposure while maintaining image quality.</p><p><strong>Conclusions: </strong>The employment of deep learning image reconstruction with AiCE presented a significant improvement in CNR and potential dose reduction in CT angiography. This study highlights the potential of AiCE to improve vascular image quality and decrease radiation exposure risk, thereby improving diagnostic precision and patient care in vascular imaging practices.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"86-95"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460253","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 study on CT detection image generation based on decompound synthesize method.","authors":"Jintao Fu, Renjie Liu, Tianchen Zeng, Peng Cong, Ximing Liu, Yuewen Sun","doi":"10.1177/08953996241296249","DOIUrl":"10.1177/08953996241296249","url":null,"abstract":"<p><strong>Background: </strong>Nuclear graphite and carbon components are vital structural elements in the cores of high-temperature gas-cooled reactors(HTGR), serving crucial roles in neutron reflection, moderation, and insulation. The structural integrity and stable operation of these reactors heavily depend on the quality of these components. Helical Computed Tomography (CT) technology provides a method for detecting and intelligently identifying defects within these structures. However, the scarcity of defect datasets limits the performance of deep learning-based detection algorithms due to small sample sizes and class imbalance.</p><p><strong>Objective: </strong>Given the limited number of actual CT reconstruction images of components and the sparse distribution of defects, this study aims to address the challenges of small sample sizes and class imbalance in defect detection model training by generating approximate CT reconstruction images to augment the defect detection training dataset.</p><p><strong>Methods: </strong>We propose a novel CT detection image generation algorithm called the Decompound Synthesize Method (DSM), which decomposes the image generation process into three steps: model conversion, background generation, and defect synthesis. First, STL files of various industrial components are converted into voxel data, which undergo forward projection and image reconstruction to obtain corresponding CT images. Next, the Contour-CycleGAN model is employed to generate synthetic images that closely resemble actual CT images. Finally, defects are randomly sampled from an existing defect library and added to the images using the Copy-Adjust-Paste (CAP) method. These steps significantly expand the training dataset with images that closely mimic actual CT reconstructions.</p><p><strong>Results: </strong>Experimental results validate the effectiveness of the proposed image generation method in defect detection tasks. Datasets generated using DSM exhibit greater similarity to actual CT images, and when combined with original data for training, these datasets enhance defect detection accuracy compared to using only the original images.</p><p><strong>Conclusion: </strong>The DSM shows promise in addressing the challenges of small sample sizes and class imbalance. Future research can focus on further optimizing the generation algorithm and refining the model structure to enhance the performance and accuracy of defect detection models.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"72-85"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460269","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":"PCB CT image element segmentation model based on boundary-attention-guided finetuning.","authors":"Chen Chen, Kai Qiao, Jie Yang, Jian Chen, Bin Yan","doi":"10.1177/08953996241303366","DOIUrl":"10.1177/08953996241303366","url":null,"abstract":"<p><strong>Background: </strong>Computed Tomography (CT) technology is commonly used to realize non-destructive testing of Printed Circuit Board (PCB), and element segmentation is the key link in the process. Although the pretraining and finetuning paradigm alleviates the problem of labeling, PCB CT images are easily affected by uneven grayscale and layer penetration. This leads to difficult segmentation of boundaries and affect semantic understanding, resulting in jagged boundaries and even missing elements.</p><p><strong>Objective: </strong>This paper aims to solve the problem of poor boundary segmentation in PCB CT image element segmentation.</p><p><strong>Methods: </strong>To this end, we propose PCB CT image element segmentation model based on boundary-attention-guided finetuning. An improved boundary detection algorithm is proposed to enhance boundary sensing ability. In order to achieve non-fixed weight feature fusion, the Attention Feature Fusion module is designed to help boundary features better assist segmentation through attention mechanism.</p><p><strong>Results: </strong>Experiments show that BAG-FTseg can achieve 89.5% mIoU on our PCB CT dataset, exceeding the baseline model by 0.9%, and the boundary-mIoU reaches 69.5%, 5.3% higher than the baseline model.</p><p><strong>Conclusion: </strong>This method improves the accuracy of boundary segmentation of PCB elements and the efficiency of feature fusion through attention mechanism, which has practical significance.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"134-144"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460313","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}
Yang Liu, Jian Chen, Jinjin Hai, Kai Qiao, Xin Qi, Yongli Li, Bin Yan
{"title":"Three-dimensional semi-supervised lumbar vertebrae region of interest segmentation based on MAE pre-training.","authors":"Yang Liu, Jian Chen, Jinjin Hai, Kai Qiao, Xin Qi, Yongli Li, Bin Yan","doi":"10.1177/08953996241301685","DOIUrl":"10.1177/08953996241301685","url":null,"abstract":"<p><strong>Background:: </strong>The annotation of the regions of interest (ROI) of lumbar vertebrae by radiologists for bone density assessment is a tedious and time-intensive task. However, deep learning (DL) methods for image segmentation has the potential to substitute manual annotations which can significantly improve the efficiency of clinical diagnostics.</p><p><strong>Objective:: </strong>The paper proposes a semi-supervised three-dimensional (3D) segmentation method for the ROI of lumbar vertebrae by integrating the tube masking masked autoencoder (MAE) pre-training.</p><p><strong>Methods:: </strong>The paper proposes a method that modifies the masking strategy of the original MAE pre-training network. And the pre-training network is only trained by images without segmentation labels, when the training is finished, the weights will be saved for segmentation tasks. In downstream tasks, a semi-supervised approach utilizing pseudo-label generation is employed for training. This method leverages a small amount of labeled data to achieve the segmentation of ROI of the lumbar vertebrae.</p><p><strong>Results:: </strong>The experimental results demonstrate that under the condition of limited annotated data, the proposed network improves the dice coefficient by 5-7% and reduces the hausdorff distance by 0.2∼0.6 mm compared to using the UNetr network alone for segmentation. When compared to the conventional MAE, the tube masking MAE presented in this paper assists effectively in segmentation, resulting in a 2% increase in the dice coefficient and a 0.24 mm reduction in the hausdorff distance.</p><p><strong>Conclusion:: </strong>Automatic segmentation of the ROI of the lumbar vertebrae helps to shorten the time for doctors to annotate vertebrae during clinical bone density examinations. The paper employs the tube masking MAE pre-trained model to effectively extract contextual information of the 3D lumbar vertebrae, combining it with a semi-supervised network leveraging pseudo-label generation for fine-tuning, which leads to effective 3D segmentation of the lumbar vertebrae.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"270-282"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460242","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":"MAFA-Uformer: Multi-attention and dual-branch feature aggregation U-shaped transformer for sparse-view CT reconstruction.","authors":"Xuan Zhang, Chenyun Fang, Zhiwei Qiao","doi":"10.1177/08953996241300016","DOIUrl":"10.1177/08953996241300016","url":null,"abstract":"<p><strong>Background: </strong>Although computed tomography (CT) is widely employed in disease detection, X-ray radiation may pose a risk to the health of patients. Reducing the projection views is a common method, however, the reconstructed images often suffer from streak artifacts.</p><p><strong>Purpose: </strong>In previous related works, it can be found that the convolutional neural network (CNN) is proficient in extracting local features, while the Transformer is adept at capturing global information. To suppress streak artifacts for sparse-view CT, this study aims to develop a method that combines the advantages of CNN and Transformer.</p><p><strong>Methods: </strong>In this paper, we propose a Multi-Attention and Dual-Branch Feature Aggregation U-shaped Transformer network (MAFA-Uformer), which consists of two branches: CNN and Transformer. Firstly, with a coordinate attention mechanism, the Transformer branch can capture the overall structure and orientation information to provide a global context understanding of the image under reconstruction. Secondly, the CNN branch focuses on extracting crucial local features of images through channel spatial attention, thus enhancing detail recognition capabilities. Finally, through a feature fusion module, the global information from the Transformer and the local features from the CNN are integrated effectively.</p><p><strong>Results: </strong>Experimental results demonstrate that our method achieves outstanding performance in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and root mean square error (RMSE). Compared with Restormer, our model achieves significant improvements: PSNR increases by 0.76 dB, SSIM improves by 0.44%, and RMSE decreases by 8.55%.</p><p><strong>Conclusion: </strong>Our method not only effectively suppresses artifacts but also better preserves details and features, thereby providing robust support for accurate diagnosis of CT images.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"157-166"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460445","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}
Jun Lv, Liuli Chen, Zhiqiang Zhu, Pengcheng Long, Liqin Hu
{"title":"Optimization of dynamic multi-leaf collimator based on multi-objective particle swarm optimization algorithm.","authors":"Jun Lv, Liuli Chen, Zhiqiang Zhu, Pengcheng Long, Liqin Hu","doi":"10.1177/08953996241304986","DOIUrl":"10.1177/08953996241304986","url":null,"abstract":"<p><strong>Background: </strong>The dynamic multi-leaf collimator (DMLC) plays a crucial role in shaping X-rays, significantly enhancing the precision, efficiency, and quality of tumor radiotherapy.</p><p><strong>Objective: </strong>To improve the shaping effect of X-rays by optimizing the end structure of the DMLC leaf, which significantly impacts the collimator's performance.</p><p><strong>Methods: </strong>This study introduces the innovative application of the multi-objective particle swarm optimization (MOPSO) algorithm to optimize DMLC parameters, including leaf end radius, source-to-leaf distance, leaf height, and tangent angle between the leaf end and the central axis. The main optimization objectives are to minimize the width and variance of the penumbra, defined as the distance between the 80% and 20% dose of X-rays on the isocenter plane, which directly impacts treatment accuracy.</p><p><strong>Results: </strong>Structural optimization across various scenarios showed significant improvements in the size and uniformity of the penumbra, ensuring a more precise radiation dose. Based on the optimized structure, a three-dimensional model of the MLC was designed and an experimental prototype was fabricated for performance testing. The results indicate that the optimized MLC exhibits a smaller penumbra.</p><p><strong>Conclusion: </strong>The proposed optimization method significantly enhances the precision of radiotherapy while minimizing radiation exposure to healthy tissue, representing a notable advancement in radiotherapy technology.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"145-156"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460312","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":"Mask R-CNN assisted diagnosis of spinal tuberculosis.","authors":"Wenjun Li, Yanfan Li, Huan Peng, Wenjun Liang","doi":"10.1177/08953996241290326","DOIUrl":"10.1177/08953996241290326","url":null,"abstract":"<p><p>The prevalence of spinal tuberculosis (ST) is particularly high in underdeveloped regions with inadequate medical conditions. This not only leads to misdiagnosis and delays in treatment progress but also contributes to the continued transmission of tuberculosis bacteria, posing a risk to other individuals. Currently, CT imaging is extensively utilized in computer-aided diagnosis (CAD). The main features of ST on CT images include bone destruction, osteosclerosis, sequestration formation, and intervertebral disc damage. However, manual diagnosis by doctors may result in subjective judgments and misdiagnosis. Therefore, an accurate and objective method is needed for diagnosing of spinal tuberculosis. In this paper, we put forward an assistive diagnostic approach for spinal tuberculosis that is based on deep learning. The approach uses the Mask R-CNN model. Moreover, we modify the original model network by incorporating the ResPath and cbam* to improve the performance metrics, namely <math><mi>m</mi><mi>A</mi><msub><mi>P</mi><mrow><mrow><mi>small</mi></mrow></mrow></msub></math> and <i>F1-score</i>. Meanwhile, other deep learning models such as Faster-RCNN and SSD were also compared. Experimental results demonstrate that the enhanced model can effectively identify spinal tuberculosis lesions, with an <math><mi>m</mi><mi>A</mi><msub><mi>P</mi><mrow><mrow><mi>small</mi></mrow></mrow></msub></math> of 0.9175, surpassing the original model's 0.8340, and an <i>F1-score</i> of 0.9335, outperforming the original model's 0.8657.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"120-133"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460308","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 class of Landweber-type iterative methods based on the Radon transform for incomplete view tomography.","authors":"Duo Liu, Gangrong Qu","doi":"10.1177/08953996241301697","DOIUrl":"10.1177/08953996241301697","url":null,"abstract":"<p><strong>Background: </strong>We study the reconstruction problem for incomplete view tomography, including sparse view tomography and limited angle tomography, by the Landweber iteration and its accelerated version. Traditional implementations of these Landweber-type iterative methods necessitate multiple large-scale matrix-vector multiplications, which in turn require substantial time and storage resources.</p><p><strong>Objective: </strong>This paper aims to develop and test a novel and efficient discretization approach for a class of Landweber-type methods that minimizes storage requirements by incorporating the specific structure of the incomplete view Radon transform.</p><p><strong>Methods: </strong>We prove that the normal operator of incomplete view Radon transform in these methods is a compact convolution operator, and derive the explicit representation of its convolution kernel. Discretized by the pixel basis, these Landweber-type iterative methods can be implemented quickly and accurately by introducing a discretized convolution operation between two small-scale matrices with minimal storage requirements.</p><p><strong>Results: </strong>For the simulated complete and limited angle data, the reconstruction results using various Landweber-type methods with our proposed discretization scheme achieve a 1-5dB improvement in PSNR and require one-third of computation time compared to the traditional approach. For the simulated sparse view data, our discretization scheme yields a valid image with the highest PSNR.</p><p><strong>Conclusions: </strong>The Landweber-type iterative methods, when combined with our proposed discretization approach based on the Radon transform, are effective for addressing the incomplete view tomography problem.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"187-203"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460283","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}
Junli Yu, Yan Ding, Li Wang, Shunxin Hu, Ning Dong, Jiangnan Sheng, Yingna Ren, Ziyue Wang
{"title":"Radiomics and deep learning features of pericoronary adipose tissue on non-contrast computerized tomography for predicting non-calcified plaques.","authors":"Junli Yu, Yan Ding, Li Wang, Shunxin Hu, Ning Dong, Jiangnan Sheng, Yingna Ren, Ziyue Wang","doi":"10.1177/08953996241292476","DOIUrl":"10.1177/08953996241292476","url":null,"abstract":"<p><strong>Background: </strong>Inflammation of coronary arterial plaque is considered a key factor in the development of coronary heart disease. Early the plaque detection and timely treatment of the atherosclerosis could effectively reduce the risk of cardiovascular events. However, there is no study combining radiomics with deep learning techniques to predict non-calcified plaques (NCP) in coronary artery at present.</p><p><strong>Objective: </strong>To investigate the value of combination of radiomics and deep learning features based on non-contrast computerized tomography (CT) scans of pericoronary adipose tissue (PCAT), integrating with clinical risk factors of patients, in identifying coronary inflammation and predicting the presence of NCP.</p><p><strong>Methods: </strong>The clinical and imaging data of 353 patients were analyzed. The region of interest (ROI) of PCAT was manually outlined on non-contrast CT scan images, like coronary CT calcium score sequential images, then the radiomics and deep learning features in ROIs were extracted respectively. In training set (Center 1), after performing feature selection, radiomics and deep learning feature models were established, meanwhile, clinical models were built. Finally, combined models were developed out via integrating clinical, radiomics, and deep learning features. The predictive performance of the four feature model groups (clinical, radiomics, deep learning, and three combination) was assessed by seven different machine learning models through generation of receiver operating characteristic curves (ROC) and the calculation of area under the curve (AUC), sensitivity, specificity, and accuracy. Furthermore, the predictive performance of each model was validated in an external validation set (Center 2).</p><p><strong>Results: </strong>For the single model comparation, eXtreme Gradient Boosting (XGBoost) showed the best performance among the clinical model group in the validation set. And Random Forest (RF) exhibited the best indicative performance not only among the radiomics feature group but also in the deep learning feature model group. What's more, among the combined model group, RF still displayed the best predictive performance, with the value of AUC, sensitivity, specificity, and accuracy in the validation set are 0.963, 0.857, 0.929, and 0.905.</p><p><strong>Conclusion: </strong>The RF model in the combined model group based on non-contrast CT scan PCAT can predict the presence of NCP more accurately and has the potential for preliminary screening of the NCP.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"96-108"},"PeriodicalIF":1.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460277","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}