Journal of X-Ray Science and Technology - Volume 29, issue 1

Authors: Yang, Yanhong | Lure, Fleming Y.M. | Miao, Hengyuan | Zhang, Ziqi | Jaeger, Stefan | Liu, Jinxin | Guo, Lin

Article Type: Research Article

Abstract: Background: Accurate and rapid diagnosis of coronavirus disease (COVID-19) is crucial for timely quarantine and treatment. Purpose: In this study, a deep learning algorithm-based AI model using ResUNet network was developed to evaluate the performance of radiologists with and without AI assistance in distinguishing COVID-19 infected pneumonia patients from other pulmonary infections on CT scans. Methods: For model development and validation, a total number of 694 cases with 111,066 CT slides were retrospectively collected as training data and independent test data in the study. Among them, 118 are confirmed COVID-19 infected pneumonia cases and 576 are …other pulmonary infection cases (e.g. tuberculosis cases, common pneumonia cases and non-COVID-19 viral pneumonia cases). The cases were divided into training and testing datasets. The independent test was performed by evaluating and comparing the performance of three radiologists with different years of practice experience in distinguishing COVID-19 infected pneumonia cases with and without the AI assistance. Results: Our final model achieved an overall test accuracy of 0.914 with an area of the receiver operating characteristic (ROC) curve (AUC) of 0.903 in which the sensitivity and specificity are 0.918 and 0.909, respectively. The deep learning-based model then achieved a comparable performance by improving the radiologists’ performance in distinguish COVOD-19 from other pulmonary infections, yielding better average accuracy and sensitivity, from 0.941 to 0.951 and from 0.895 to 0.942, respectively, when compared to radiologists without using AI assistance. Conclusion: A deep learning algorithm-based AI model developed in this study successfully improved radiologists’ performance in distinguishing COVID-19 from other pulmonary infections using chest CT images. Show more

Keywords: COVID-19, artificial intelligence (AI), deep learning, computed tomography (CT)

DOI: 10.3233/XST-200735

Citation: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 1-17, 2021

Authors: Polat, Çağín | Karaman, Onur | Karaman, Ceren | Korkmaz, Güney | Balcı, Mehmet Can | Kelek, Sevim Ercan

Article Type: Research Article

Abstract: BACKGROUND: Chest X-ray imaging has been proved as a powerful diagnostic method to detect and diagnose COVID-19 cases due to its easy accessibility, lower cost and rapid imaging time. OBJECTIVE: This study aims to improve efficacy of screening COVID-19 infected patients using chest X-ray images with the help of a developed deep convolutional neural network model (CNN) entitled nCoV-NET . METHODS: …To train and to evaluate the performance of the developed model, three datasets were collected from resources of “ChestX-ray14”, “COVID-19 image data collection”, and “Chest X-ray collection from Indiana University,” respectively. Overall, 299 COVID-19 pneumonia cases and 1,522 non-COVID 19 cases are involved in this study. To overcome the probable bias due to the unbalanced cases in two classes of the datasets, ResNet, DenseNet, and VGG architectures were re-trained in the fine-tuning stage of the process to distinguish COVID-19 classes using a transfer learning method. Lastly, the optimized final nCoV-NET model was applied to the testing dataset to verify the performance of the proposed model. RESULTS: Although the performance parameters of all re-trained architectures were determined close to each other, the final nCOV-NET model optimized by using DenseNet-161 architecture in the transfer learning stage exhibits the highest performance for classification of COVID-19 cases with the accuracy of 97.1 %. The Activation Mapping method was used to create activation maps that highlights the crucial areas of the radiograph to improve causality and intelligibility. CONCLUSION: This study demonstrated that the proposed CNN model called nCoV-NET can be utilized for reliably detecting COVID-19 cases using chest X-ray images to accelerate the triaging and save critical time for disease control as well as assisting the radiologist to validate their initial diagnosis. Show more

Keywords: Coronavirus (COVID-19) infection, deep learning, convolutional neural network (CNN), transfer learning, chest X-ray images

DOI: 10.3233/XST-200757

Citation: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 19-36, 2021

Authors: Wang, Yizhong | Zhang, Wenkun | Cai, Ailong | Wang, Linyuan | Tang, Chao | Feng, Zhiwei | Li, Lei | Liang, Ningning | Yan, Bin

Article Type: Research Article

Abstract: Dual-energy computed tomography (DECT) provides more anatomical and functional information for image diagnosis. Presently, the popular DECT imaging systems need to scan at least full angle (i.e., 360°). In this study, we propose a DECT using complementary limited-angle scan (DECT-CL) technology to reduce the radiation dose and compress the spatial distribution of the imaging system. The dual-energy total scan is 180°, where the low- and high-energy scan range is the first 90° and last 90°, respectively. We describe this dual limited-angle problem as a complementary limited-angle problem, which is challenging to obtain high-quality images using traditional reconstruction algorithms. Furthermore, a …complementary-sinogram-inpainting generative adversarial networks (CSI-GAN) with a sinogram loss is proposed to inpainting sinogram to suppress the singularity of truncated sinogram. The sinogram loss focuses on the data distribution of the generated sinogram while approaching the target sinogram. We use the simultaneous algebraic reconstruction technique namely, a total variable (SART-TV) algorithms for image reconstruction. Then, taking reconstructed CT images of pleural and cranial cavity slices as examples, we evaluate the performance of our method and numerically compare different methods based on root mean square error (RMSE), peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). Compared with traditional algorithms, the proposed network shows advantages in numerical terms. Compared with Patch-GAN, the proposed network can also reduce the RMSE of the reconstruction results by an average of 40% and increase the PSNR by an average of 26%. In conclusion, both qualitative and quantitative comparison and analysis demonstrate that our proposed method achieves a good artifact suppression effect and can suitably solve the complementary limited-angle problem. Show more

Keywords: Dual-energy computed tomography, complementary limited angle problem, generative adversarial networks

DOI: 10.3233/XST-200736

Citation: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 37-61, 2021

Authors: Kageyama, Masashi | Okajima, Kenichi | Maesawa, Minoru | Nonoguchi, Masahiro | Nonoguchi, Manabu | Kuribayashi, Masaru | Hara, Yukihiro | Momose, Atsushi

Article Type: Research Article

Abstract: X-ray phase computed tomography (CT) is used to observe the inside of light materials. In this paper, we report a new study to develop and test a laboratory assembled X-ray phase CT system that comprises an X-ray Lau interferometer, a rotating Mo anode X-ray tube, and a detector with high spatial resolution. The system has a high spatial resolution lower than 10 μm, which is evaluated by differentiating neighbouring carbon fibres in a polymer composite material. The density resolution is approximately 0.035 g/cm3 , which enables to successfully distinguish the high-density polyethylene (HDPE, 0.93 g/cm3 ) from the ultra-low-density polyethylene (ULDPE, 0.88 g/cm3 …) in the sample. Moreover, the system can be switched to operate on another mode based on a Talbot–Lau interferometer that provides a wider field of view with a moderate spatial resolution (approximately 100 μm). By analyzing sample images of the biological, this study demonstrates the feasibility and advantages of using hybrid configuration of this X-ray phase CT system. Show more

Keywords: X-ray phase contrast, Talbot–Lau interferometer, grating, X-ray CT

DOI: 10.3233/XST-200732

Citation: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 63-73, 2021

Authors: Zhang, Ling | Zhuang, Yan | Hua, Zhan | Han, Lin | Li, Cheng | Chen, Ke | Peng, Yulan | Lin, Jiangli

Article Type: Research Article

Abstract: BACKGROUND: Thyroid ultrasonography is widely used to diagnose thyroid nodules in clinics. Automatic localization of nodules can promote the development of intelligent thyroid diagnosis and reduce workload of radiologists. However, besides the ultrasound image has low contrast and high noise, the thyroid nodules are diverse in shape and vary greatly in size. Thus, thyroid nodule detection in ultrasound images is still a challenging task. OBJECTIVE: This study proposes an automatic detection algorithm to locate nodules in B ultrasound images and Doppler ultrasound images. This method can be used to screen thyroid nodules and provide a basis for subsequent …automatic segmentation and intelligent diagnosis. METHODS: We develop and optimize an improved YOLOV3 model for detecting thyroid nodules in ultrasound images with B-mode and Doppler mode. Improvements include (1) using the high-resolution network (HRNet) as the basic network for gradually extracting high-level semantic features to reduce the missed detection and misdetection, (2) optimizing the loss function for single target detection like nodules, and (3) obtaining the anchor boxes by clustering the candidate frames of real nodules in the dataset. RESULTS: The experimental results of applying to 8000 clinical ultrasound images show that the new method developed and tested in this study can effectively detect thyroid nodules. The method achieves 94.53% mean precision and 95.00% mean recall. CONCLUTIONS: The study demonstrates a new automated method that enables to achieve high detection accuracy and effectively locate thyroid nodules in various ultrasound images without any user interaction, which indicates its potential clinical application value for the thyroid nodule screening. Show more

Keywords: Automatic localization, thyroid nodules, deep learning, ultrasound images

DOI: 10.3233/XST-200775

Citation: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 75-90, 2021

Authors: Feng, Zhiwei | Cai, Ailong | Wang, Yizhong | Li, Lei | Tong, Li | Yan, Bin

Article Type: Research Article

Abstract: The excessive radiation doses in the application of computed tomography (CT) technology pose a threat to the health of patients. However, applying a low radiation dose in CT can result in severe artifacts and noise in the captured images, thus affecting the diagnosis. Therefore, in this study, we investigate a dual residual convolution neural network (DRCNN) for low-dose CT (LDCT) imaging, whereby the CT images are reconstructed directly from the sinogram by integrating analytical domain transformations, thus reducing the loss of projection information. With this new framework, feature extraction is performed simultaneously on both the sinogram-domain sub-net and the image-domain …sub-net, which utilize the residual shortcut networks and play a complementary role in suppressing the projection noise and reducing image error. This new DRCNN approach helps not only decrease the sinogram noise but also preserve significant structural information. The experimental results of simulated and real projection data demonstrate that our DRCNN achieve superior performance over other state-of-art methods in terms of visual inspection and quantitative metrics. For example, comparing with RED-CNN and DP-ResNet, the value of PSNR using our DRCNN is improved by nearly 3 dB and 1 dB, respectively. Show more

Keywords: Low-dose CT, image denoising, deep learning, residual network

DOI: 10.3233/XST-200777

Citation: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 91-109, 2021

Authors: Yu, Hengyong | Wang, Ge

Article Type: Research Article

Abstract: Thyroid cancer is the most common type of endocrine-related cancer and the most common cancer in young women. Currently, single photon emission computed tomography (SPECT) and computed tomography (CT) are used with radioiodine scintigraphy to evaluate patients with thyroid cancer. The gamma camera for SPECT contains a mechanical collimator that greatly compromises dose efficiency and limits diagnostic sensitivity. Fortunately, the Compton camera is emerging as an ideal approach for mapping the distribution of radiopharmaceuticals inside the thyroid. In this preliminary study, based on the state-of-the-art readout chip Timepix3, we investigate the feasibility of using Compton camera for radiotracer SPECT imaging …in thyroid cancer. A thyroid phantom is designed to mimic human neck, the mechanism of Compton camera-based event detection is simulated to generate realistic list-mode data, and a weighted back-projection method is developed to reconstruct the original distribution of the emission source. Study results show that the Compton camera can improve the detection efficiency for two or higher orders of magnitude comparing with the conventional gamma cameras. The thyroid gland regions can be reconstructed from the Compton camera measurements in terms of radiotracer distribution. This makes the Compton-camera-based SPECT imaging a promising modality for future clinical applications with significant benefits for dose reduction, scattering artifact reduction, temporal resolution enhancement, scan throughput increment, and others. Show more

Keywords: Compton scattering, compton camera, SPECT imaging, thyroid cancer

DOI: 10.3233/XST-200769

Citation: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 111-124, 2021

Authors: Zhao, Yongxia | Li, Dongxue | Liu, Zhichao | Geng, Xue | Zhang, Tianle | Xu, Yize

Article Type: Research Article

Abstract: OBJECTIVE: To determine the optimal pre-adaptive and post-adaptive level statistical iterative reconstruction V (ASiR-V) for improving image quality and reducing radiation dose in coronary computed tomography angiography (CCTA). METHODS: The study was divided into two parts. In part I, 150 patients for CCTA were prospectively enrolled and randomly divided into 5 groups (A, B, C, D, and E) with progressive scanning from 40% to 80% pre-ASiR-V with 10% intervals and reconstructing with 70% post-ASiR-V. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated. Subjective image quality was assessed using a 5-point scale. The CT dose index volume …(CTDIvol ) and dose-length product (DLP) of each patient were recorded and the effective radiation dose (ED) was calculated after statistical analysis by optimizing for the best pre-ASiR-V value with the lowest radiation dose while maintaining overall image quality. In part II, the images were reconstructed with the recommended optimal pre-ASiR-V values in part I (D group) and 40%–90% of post-ASiR-V. The reconstruction group (D group) was divided into 6 subgroups (interval 10%, D0:40% post-ASiR-V, D1:50% post - ASiR-V, D2:60% post-ASiR-V, D3:70% post-ASiR-V, D4:80% post-ASiR-V, and D5:90% post-ASiR-V).The SNR and CNR of D0-D5 subgroups were calculated and analyzed using one-way analysis of variance, and the consistency of the subjective scores used the k test. RESULTS: There was no significant difference in the SNRs, CNRs, and image quality scores among A, B, C, and D groups (P  > 0.05). The SNR, CNR, and image quality scores of the E group were lower than those of the A, B, C, and D groups (P  < 0.05). The mean EDs in the B, C, and D groups were reduced by 7.01%, 13.37%, and 18.87%, respectively, when compared with that of the A group. The SNR and CNR of the D4–D5 subgroups were higher than the D0-D3 subgroups, and the image quality scores of the D4 subgroups were higher than the other subgroups (P  < 0.05). CONCLUSION: The wide-detector combined with 70% pre-ASiR-V and 80% post-ASiR-V significantly reduces the radiation dose of CCTA while maintaining overall image quality as compared with the manufacture’s recommendation of 40% pre-ASiR-V. Show more

Keywords: Pre-ASiR-V, Post-ASiR-V, CCTA, radiation dose, image quality

DOI: 10.3233/XST-200754

Citation: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 125-134, 2021

Authors: Zheng, Xuan | Qu, Gangrong | Zhou, Jiajia

Article Type: Research Article

Abstract: BACKGROUND: A statistical method called maximum likelihood expectation maximization (MLEM) is quite attractive, especially in PET/SPECT. However, the convergence rate of the iterative scheme of MLEM is quite slow. OBJECTIVE: This study aims to develop and test a new method to speed up the convergence rate of the MLEM algorithm. METHODS: We introduce a relaxation parameter in the conventional MLEM iterative formula and propose the relaxation strategy on the condition that the spectral radius of the derived iterative matrix from the iterative scheme with the accelerated parameter reaches a minimum value. RESULTS: Experiments with …Shepp-Logan phantom and an annual tree image demonstrate that the new computational strategy effectively accelerates computation time while maintains reasonable image quality. CONCLUSIONS: The proposed new computational method involving the relaxation strategy has a faster convergence speed than the original method. Show more

Keywords: MLEM algorithm, convergence rate, relaxation strategy, image reconstruction

DOI: 10.3233/XST-200749

Citation: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 135-149, 2021

Authors: Deng, Lan | Wang, Yuanjun

Article Type: Research Article

Abstract: BACKGROUND: Effective detection of Alzheimer’s disease (AD) is still difficult in clinical practice. Therefore, establishment of AD detection model by means of machine learning is of great significance to assist AD diagnosis. OBJECTIVE: To investigate and test a new detection model aiming to help doctors diagnose AD more accurately. METHODS: Diffusion tensor images and the corresponding T1w images acquired from subjects (AD = 98, normal control (NC) = 100) are used to construct brain networks. Then, 9 types features (198×90×9 in total) are extracted from the 3D brain networks by a graph theory method. Features with low correction in both …groups are selected through the Pearson correlation analysis. Finally, the selected features (198×33, 198×26, 198×30, 198×42, 198×36, 198×23, 198×29, 198×14, 198×25) are separately used into train 3 machine learning classifier based detection models in which 60% of study subjects are used for training, 20% for validation and 20% for testing. RESULTS: The best detection accuracy levels of 3 models are 90%, 98% and 90% with the corresponding sensitivity of 92%, 96%, and 72% and specificity of 88%, 100% and 94% when using a random forest classifier trained with the Shortest Path Length (SPL) features (198×14), a support vector machine trained with the Degree Centrality features (198×33), and a convolution neural network trained with SPL features, respectively. CONCLUSIONS: This study demonstrates that the new method and models not only improve the accuracy of detecting AD, but also avoid bias caused by the method of direct dimensionality reduction from high dimensional data. Show more

Keywords: Alzheimer’s disease, support vector machine, structural brain network, feature recognition

DOI: 10.3233/XST-200771

Citation: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 151-169, 2021