Journal of X-Ray Science and Technology - Volume 31, issue 6

Authors: Liu, Yi | Yan, Rongbiao | Liu, Yuhang | Zhang, Pengcheng | Chen, Yang | Gui, Zhiguo

Article Type: Research Article

Abstract: BACKGROUND: Recently, one promising approach to suppress noise/artifacts in low-dose CT (LDCT) images is the CNN-based approach, which learns the mapping function from LDCT to normal-dose CT (NDCT). However, most CNN-based methods are purely data-driven, thus lacking sufficient interpretability and often losing details. OBJECTIVE: To solve this problem, we propose a deep convolutional dictionary learning method for LDCT denoising, in which a novel convolutional dictionary learning model with adaptive window (CDL-AW) is designed, and a corresponding enhancement-based convolutional dictionary learning network (called ECDAW-Net) is constructed to unfold the CDL-AW model iteratively using the proximal gradient descent technique. …METHODS: In detail, the adaptive window-constrained convolutional dictionary atom is proposed to alleviate spectrum leakage caused by data truncation during convolution. Furthermore, in the ECDAW-Net, a multi-scale edge extraction module that consists of LoG and Sobel convolution layers is proposed in the unfolding iteration, to supplement lost textures and details. Additionally, to further improve the detail retention ability, the ECDAW-Net is trained by the compound loss function of the pixel-level MSE loss and the proposed patch-level loss, which can assist to retain richer structural information. RESULTS: Applying ECDAW-Net to the Mayo dataset, we obtained the highest peak signal-to-noise ratio (33.94) and sub-optimal structural similarity (0.92). CONCLUSIONS: Compared with some state-of-art methods, the interpretable ECDAW-Net performs well in suppressing noise/artifacts and preserving textures of tissue. Show more

Keywords: Low-dose CT, deep convolutional dictionary learning, adaptive window, multi-scale edge extraction, patch-level loss

DOI: 10.3233/XST-230094

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 6, pp. 1165-1187, 2023

Authors: Yan, Huimin | Fang, Chenyun | Liu, Peng | Qiao, Zhiwei

Article Type: Research Article

Abstract: BACKGROUND: An effective method for achieving low-dose CT is to keep the number of projection angles constant while reducing radiation dose at each angle. However, this leads to high-intensity noise in the reconstructed image, adversely affecting subsequent image processing, analysis, and diagnosis. OBJECTIVE: This paper proposes a novel Channel Graph Perception based U-shaped Transformer (CGP-Uformer) network, aiming to achieve high-performance denoising of low-dose CT images. METHODS: The network consists of convolutional feed-forward Transformer (ConvF-Transformer) blocks, a channel graph perception block (CGPB), and spatial cross-attention (SC-Attention) blocks. The ConvF-Transformer blocks enhance the ability of feature representation and …information transmission through the CNN-based feed-forward network. The CGPB introduces Graph Convolutional Network (GCN) for Channel-to-Channel feature extraction, promoting the propagation of information across distinct channels and enabling inter-channel information interchange. The SC-Attention blocks reduce the semantic difference in feature fusion between the encoder and decoder by computing spatial cross-attention. RESULTS: By applying CGP-Uformer to process the 2016 NIH AAPM-Mayo LDCT challenge dataset, experiments show that the peak signal-to-noise ratio value is 35.56 and the structural similarity value is 0.9221. CONCLUSIONS: Compared to the other four representative denoising networks currently, this new network demonstrates superior denoising performance and better preservation of image details. Show more

Keywords: Low-dose CT, deep learning, transformer, graph convolutional network, convolutional neural network

DOI: 10.3233/XST-230158

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 6, pp. 1189-1205, 2023

Authors: Lina, Jia | Xu, He | Aimin, Huang | Beibei, Jia | Zhiguo, Gui

Article Type: Research Article

Abstract: BACKGROUND: Low dose computed tomography (LDCT) uses lower radiation dose, but the reconstructed images contain higher noise that can have negative impact in disease diagnosis. Although deep learning with the edge extraction operators reserves edge information well, only applying the edge extraction operators to input LDCT images does not yield overall satisfactory results. OBJECTIVE: To improve LDCT images quality, this study proposes and tests a dual edge extraction multi-scale attention mechanism convolution neural network (DEMACNN) based on a compound loss. METHODS: The network uses edge extraction operators to extract edge information from both the input images …and the feature maps in the network, improving the utilization of the edge operators and retaining the images edge information. The feature enhancement block is constructed by fusing the attention mechanism and multi-scale module, enhancing effective information, while suppressing useless information. The residual learning method is used to learn the network, improving the performance of the network, and solving the problem of gradient disappearance. Except for the network structure, a compound loss function, which consists of the MSE loss, the proposed joint total variation loss, and the edge loss, is proposed to enhance the denoising ability of the network and reserve the edge of images. RESULTS: Compared with other advanced methods (REDCNN, CT-former and EDCNN), the proposed new network achieves the best PSNR and SSIM values in LDCT images of the abdomen, which are 33.3486 and 0.9104, respectively. In addition, the new network also performs well on head and chest image data. CONCLUSION: The experimental results demonstrate that the proposed new network structure and denoising algorithm not only effectively removes the noise in LDCT images, but also protects the edges and details of the images well. Show more

Keywords: Low dose CT(LDCT), image denoising, edge operator, attention mechanism, residual learning, convolution neural network (CNN)

DOI: 10.3233/XST-230132

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 6, pp. 1207-1226, 2023

Authors: Ma, Yue | Liu, Dexiang | Hua, Jianfei | Lu, Wei

Article Type: Research Article

Abstract: BACKGROUND: Inverse Compton scattering (ICS) source can produce quasi-monoenergetic micro-focus X-rays ranging from keV to MeV level, with potential applications in the field of high-resolution computed tomography (CT) imaging. ICS source has an energy-angle correlated feature that lower photon energy is obtained at larger emission angle, thus different photon energies are inherently contained in each ICS pulse, which is especially advantageous for dual- or multi-energy CT imaging. OBJECTIVE: This study proposes a dual-energy micro-focus CT scheme based on the energy-angle correlation of ICS source and tests its function using numerical simulations. METHODS: In this scheme, high- …and low-energy regions are chosen over the angular direction of each ICS pulse, and dual-energy projections of the object are obtained by an angularly-splicing scanning method. The field-of-view (FOV) of ICS source is extended simultaneously through this scanning method, thus the scale of the imaging system can be efficiently reduced. A dedicated dual-energy CT algorithm is developed to reconstruct the monoenergetic attenuation coefficients, electron density, and effective atomic number distributions of the object. RESULTS: A test object composed of different materials (carbon, aluminium, titanium, iron and copper) and line pairs with different widths (15/24/39/60 μm) is imaged by the proposed dual-energy CT scheme using numerical simulations, and high-fidelity monoenergetic attenuation coefficient, electron density, and effective atomic number distributions are obtained. All the line pairs are well identified, and the contrast ratio of the 15 μm lines is 22%, showing good accordance with the theoretical predictions. CONCLUSIONS: The proposed dual-energy CT scheme can reconstruct fine inner structures and material compositions of the object simultaneously, opening a new possibility for the application of ICS source in the field of non-destructive testing. Show more

Keywords: Inverse compton scattering X-ray source, dual-energy computed tomography, laser plasma accelerator

DOI: 10.3233/XST-230093

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 6, pp. 1227-1243, 2023

Authors: Wang, Zhisheng | Liu, Yue | Wang, Shunli | Bian, Xingyuan | Li, Zongfeng | Cui, Junning

Article Type: Research Article

Abstract: This paper is to investigate the high-quality analytical reconstructions of multiple source-translation computed tomography (mSTCT) under an extended field of view (FOV). Under the larger FOVs, the previously proposed backprojection filtration (BPF) algorithms for mSTCT, including D-BPF and S-BPF (their differences are different derivate directions along the detector and source, respectively), make some errors and artifacts in the reconstructed images due to a backprojection weighting factor and the half-scan mode, which deviates from the intention of mSTCT imaging. In this paper, to achieve reconstruction with as little error as possible under the extremely extended FOV, we combine the full-scan mSTCT …(F-mSTCT) geometry with the previous BPF algorithms to study the performance and derive a suitable redundancy-weighted function for F-mSTCT. The experimental results indicate FS-BPF can get high-quality, stable images under the extremely extended FOV of imaging a large object, though it requires more projections than FD-BPF. Finally, for different practical requirements in extending FOV imaging, we give suggestions on algorithm selection. Show more

Keywords: Multiple source-translation computed tomography, extended field-of-view, backprojection weighting factor, full-scan, backprojection filtration

DOI: 10.3233/XST-230138

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 6, pp. 1245-1262, 2023

Authors: Ren, Yongzhen | Lu, Siyuan | Zhang, Dongmei | Wang, Xian | Agyekum, Enock Adjei | Zhang, Jin | Zhang, Qing | Xu, Feiju | Zhang, Guoliang | Chen, Yu | Shen, Xiangjun | Zhang, Xuelin | Wu, Ting | Hu, Hui | Shan, Xiuhong | Wang, Jun | Qian, Xiaoqin

Article Type: Research Article

Abstract: BACKGROUND: Preoperative prediction of cervical lymph node metastasis (CLNM) in patients with papillary thyroid carcinoma (PTC) is significant for surgical decision-making. OBJECTIVE: This study aims to develop a dual-modal radiomics (DMR) model based on grayscale ultrasound (GSUS) and dual-energy computed tomography (DECT) for non-invasive CLNM in PTC. METHODS: In this study, 348 patients with pathologically confirmed PTC at Jiangsu University Affiliated People’s Hospital who completed preoperative ultrasound (US) and DECT examinations were enrolled and randomly assigned to training (n  = 261) and test (n  = 87) cohorts. The enrolled patients were divided into two groups based on pathology …findings namely, CLNM (n  = 179) and CLNM-Free (n  = 169). Radiomics features were extracted from GSUS images (464 features) and DECT images (960 features), respectively. Pearson correlation coefficient (PCC) and the least absolute shrinkage and selection operator (LASSO) regression with 10-fold cross-validation were then used to select CLNM-related features. Based on the selected features, GSUS, DECT, and GSUS combined DECT radiomics models were constructed by using a Support Vector Machine (SVM) classifier. RESULTS: Three predictive models based on GSUS, DECT, and a combination of GSUS and DECT, yielded performance of areas under the curve (AUC) = 0.700 [95% confidence interval (CI), 0.662–0.706], 0.721 [95% CI, 0.683–0.727], and 0.760 [95% CI, 0.728–0.762] in the training dataset, and AUC = 0.643 [95% CI, 0.582–0.734], 0.680 [95% CI, 0.623–0.772], and 0.744 [95% CI, 0.686–0.784] in the test dataset, respectively. It shows that the predictive model combined GSUS and DECT outperforms both models using GSUS and DECT only. CONCLUSIONS: The newly developed combined radiomics model could more accurately predict CLNM in PTC patients and aid in better surgical planning. Show more

Keywords: Grayscale ultrasound, dual-energy computed tomography, radiomics, papillary thyroid carcinoma, cervical lymph node metastasis

DOI: 10.3233/XST-230091

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 6, pp. 1263-1280, 2023

Authors: Kong, Yan | Xu, Muchen | Wei, Xianding | Qian, Danqi | Yin, Yuan | Huang, Zhaohui | Gu, Wenchao | Zhou, Leyuan

Article Type: Research Article

Abstract: OBJECTIVE: To investigate the use of non-contrast-enhanced (NCE) and contrast-enhanced (CE) CT radiomics signatures (Rad-scores) as prognostic factors to help improve the prediction of the overall survival (OS) of postoperative colorectal cancer (CRC) patients. METHODS: A retrospective analysis was performed on 65 CRC patients who underwent surgical resection in our hospital as the training set, and 19 patient images retrieved from The Cancer Imaging Archive (TCIA) as the external validation set. In training, radiomics features were extracted from the preoperative NCE/CE-CT, then selected through 5-fold cross validation LASSO Cox method and used to construct Rad-scores. Models derived from …Rad-scores and clinical factors were constructed and compared. Kaplan-Meier analyses were also used to compare the survival probability between the high- and low-risk Rad-score groups. Finally, a nomogram was developed to predict the OS. RESULTS: In training, a clinical model achieved a C-index of 0.796 (95% CI: 0.722–0.870), while clinical and two Rad-scores combined model performed the best, achieving a C-index of 0.821 (95% CI: 0.743–0.899). Furthermore, the models with the CE-CT Rad-score yielded slightly better performance than that of NCE-CT in training. For the combined model with CE-CT Rad-scores, a C-index of 0.818 (95% CI: 0.742–0.894) and 0.774 (95% CI: 0.556–0.992) were achieved in both the training and validation sets. Kaplan-Meier analysis demonstrated a significant difference in survival probability between the high- and low-risk groups. Finally, the areas under the receiver operating characteristics (ROC) curves for the model were 0.904, 0.777, and 0.843 for 1, 3, and 5-year survival, respectively. CONCLUSION: NCE-CT or CE-CT radiomics and clinical combined models can predict the OS for CRC patients, and both Rad-scores are recommended to be included when available. Show more

Keywords: Colorectal cancer, overall survival, radiomics, nomogram

DOI: 10.3233/XST-230090

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 6, pp. 1281-1294, 2023

Authors: Sun, Peng | Yang, Sijing | Guan, Haolin | Mo, Taiping | Yu, Bonan | Chen, Zhencheng

Article Type: Research Article

Abstract: BACKGROUND: Medical image segmentation is crucial in disease diagnosis and treatment planning. Deep learning (DL) techniques have shown promise. However, optimizing DL models requires setting numerous parameters, and demands substantial labeled datasets, which are labor-intensive to create. OBJECTIVE: This study proposes a semi-supervised model that can utilize labeled and unlabeled data to accurately segment kidneys, tumors, and cysts on CT images, even with limited labeled samples. METHODS: An end-to-end semi-supervised learning model named MTAN (Mean Teacher Attention N-Net) is designed to segment kidneys, tumors, and cysts on CT images. The MTAN model is built on the …foundation of the AN-Net architecture, functioning dually as teachers and students. In its student role, AN-Net learns conventionally. In its teacher role, it generates objects and instructs the student model on their utilization to enhance learning quality. The semi-supervised nature of MTAN allows it to effectively utilize unlabeled data for training, thus improving performance and reducing overfitting. RESULTS: We evaluate the proposed model using two CT image datasets (KiTS19 and KiTS21). In the KiTS19 dataset, MTAN achieved segmentation results with an average Dice score of 0.975 for kidneys and 0.869 for tumors, respectively. Moreover, on the KiTS21 dataset, MTAN demonstrates its robustness, yielding average Dice scores of 0.977 for kidneys, 0.886 for masses, 0.861 for tumors, and 0.759 for cysts, respectively. CONCLUSION: The proposed MTAN model presents a compelling solution for accurate medical image segmentation, particularly in scenarios where the labeled data is scarce. By effectively utilizing the unlabeled data through a semi-supervised learning approach, MTAN mitigates overfitting concerns and achieves high-quality segmentation results. The consistent performance across two distinct datasets, KiTS19 and KiTS21, underscores model’s reliability and potential for clinical reference. Show more

Keywords: Medical image segmentation, kidney tumor segmentation, KiTS, AN-Net, MTAN, semi-supervised learning

DOI: 10.3233/XST-230133

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 6, pp. 1295-1313, 2023

Authors: Su, Hsin-Yueh | Hsieh, Shang-Ting | Tsai, Kun-Zhe | Wang, Yu-Li | Wang, Chi-Yuan | Hsu, Shih-Yen | Liu, Kuo-Ying | Huang, Yung-Hui | Wei, Ya-Wen | Lu, Nan-Han | Chen, Tai-Been

Article Type: Research Article

Abstract: BACKGROUND: Dental panoramic imaging plays a pivotal role in dentistry for diagnosis and treatment planning. However, correctly positioning patients can be challenging for technicians due to the complexity of the imaging equipment and variations in patient anatomy, leading to positioning errors. These errors can compromise image quality and potentially result in misdiagnoses. OBJECTIVE: This research aims to develop and validate a deep learning model capable of accurately and efficiently identifying multiple positioning errors in dental panoramic imaging. METHODS AND MATERIALS: This retrospective study used 552 panoramic images selected from a hospital Picture Archiving and Communication System …(PACS). We defined six types of errors (E1-E6) namely, (1) slumped position, (2) chin tipped low, (3) open lip, (4) head turned to one side, (5) head tilted to one side, and (6) tongue against the palate. First, six Convolutional Neural Network (CNN) models were employed to extract image features, which were then fused using transfer learning. Next, a Support Vector Machine (SVM) was applied to create a classifier for multiple positioning errors, using the fused image features. Finally, the classifier performance was evaluated using 3 indices of precision, recall rate, and accuracy. RESULTS: Experimental results show that the fusion of image features with six binary SVM classifiers yielded high accuracy, recall rates, and precision. Specifically, the classifier achieved an accuracy of 0.832 for identifying multiple positioning errors. CONCLUSIONS: This study demonstrates that six SVM classifiers effectively identify multiple positioning errors in dental panoramic imaging. The fusion of extracted image features and the employment of SVM classifiers improve diagnostic precision, suggesting potential enhancements in dental imaging efficiency and diagnostic accuracy. Future research should consider larger datasets and explore real-time clinical application. Show more

Keywords: Dental panoramic imaging, multiple positioning error, fused image features

DOI: 10.3233/XST-230171

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 6, pp. 1315-1332, 2023

Authors: Ma, Ze-Peng | Li, Xiao-Lei | Gao, Kai | Zhang, Tian-Le | Wang, Heng-Di | Zhao, Yong-Xia

Article Type: Research Article

Abstract: OBJECTIVE: To explore the value of applying computed tomography (CT) radiomics based on different CT-enhanced phases to determine the immunotherapeutic efficacy of non-small cell lung cancer (NSCLC). METHODS: 106 patients with NSCLC who underwent immunotherapy are randomly divided into training (74) and validation (32) groups. CT-enhanced arterial and venous phase images of patients before treatment are collected. Region-of-interest (ROI) is segmented on the CT-enhanced images, and the radiomic features are extracted. One-way analysis of variance and least absolute shrinkage and selection operator (LASSO) are used to screen the optimal radiomics features and analyze the association between radiomics features …and immunotherapy efficacy. The area under receiver-operated characteristic curves (AUC) along with the sensitivity and specificity are computed to evaluate diagnostic effectiveness. RESULTS: LASSO regression analysis screens and selects 6 and 8 optimal features in the arterial and venous phases images, respectively. Applying to the training group, AUCs based on CT-enhanced arterial and venous phase images are 0.867 (95% CI:0.82–0.94) and 0.880 (95% CI:0.86–0.91) with the sensitivities of 73.91% and 76.19%, and specificities of 66.67% and 72.19%, respectively, while in validation group, AUCs of the arterial and venous phase images are 0.732 (95% CI:0.71–0.78) and 0.832 (95% CI:0.78–0.91) with sensitivities of 75.00% and 76.00%, and specificities of 73.07% and 75.00%, respectively. There are no significant differences between AUC values computed from arterial phases and venous phases images in both training and validation groups (P  < 0.05). CONCLUSION: The optimally selected radiomics features computed from CT-enhanced different-phase images can provide new imaging marks to evaluate efficacy of the targeted therapy in NSCLC with a high diagnostic value. Show more

Keywords: Radiomics, non-small cell lung cancer, computed tomography-enhanced, immunotherapy, curative effect evaluation

DOI: 10.3233/XST-230189

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 6, pp. 1333-1340, 2023

Authors: Tian, Zonghan | Tao, Siwei | Bai, Ling | Xu, Yueshu | Liu, Xu | Kuang, Cuifang

Article Type: Research Article

Abstract: BACKGROUNDS: X-ray phase contrast imaging (XPCI) can separate the attenuation, refraction, and scattering signals of the object. The application of image fusion enables the concentration of distinctive information into a single image. Some methods have been applied in XPCI field, but wavelet-based decomposition approaches often result in loss of original data. OBJECTIVE: To explore the application value of a novel image fusion method for XPCI system and computed tomography (CT) system. METHODS: The means of fast adaptive bidimensional empirical mode decomposition (FABEMD) is considered for image decomposition to avoid unnecessary information loss. A parameter δ …is proposed to guide the fusion of bidimensional intrinsic mode functions which contain high-frequency information, using a pulse coupled neural network with morphological gradients (MGPCNN). The residual images are fused by the energy attribute fusion strategy. Image preprocessing and enhancement are performed on the result to ensure its quality. The effectiveness of other image fusion methods has been compared, such as discrete wavelet transforms and anisotropic diffusion fusion. RESULTS: The δ -guided FABEMD-MGPCNN method achieved either the first or second position in objective evaluation metrics with biological samples, as compared to other image fusion methods. Moreover, comparisons are made with other fusion methods used for XPCI. Finally, the proposed method applied in CT show expected results to retain the feature information. CONCLUSIONS: The proposed δ -guided FABEMD-MGPCNN method shows potential feasibility and superiority over traditional and recent image fusion methods for X-ray differential phase contrast imaging and computed tomography systems. Show more

Keywords: X-ray phase contrast imaging, X-ray grating interferometry, fast adaptive bidimensional empirical mode decomposition, pulse coupled neural network, image fusion

DOI: 10.3233/XST-230180

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 6, pp. 1341-1362, 2023