Journal of X-Ray Science and Technology - Volume 30, issue 1

Authors: Hu, Dongcai | Zhou, Zheng | Wang, Jianxin | Xiao, Dexin | Zhou, Kui | Li, Peng | Li, Shigen | Shan, Lijun | Wang, Hanbin | Liu, Yu | Shen, Xuming | Lao, Chenglong | Luo, Xing | He, Tianhui | Zhang, Peng | Yan, Longgang | Liu, Jie | Ding, Yushou | Cai, Zhe | Li, Lei | Zhang, Chengxin | Liu, Qinghua | Li, Jing | Wang, Yuan | Yang, Xingfan | Li, Ming | Wu, Dai | Chen, Menxue | Zhao, Jianheng

Article Type: Research Article

Abstract: High-energy, high-dose, microfocus X-ray computed tomography (HHM CT) is one of the most effective methods for high-resolution X-ray radiography inspection of high-density samples with fine structures. Minimizing the effective focal spot size of the X-ray source can significantly improve the spatial resolution and the quality of the sample images, which is critical and important for the performance of HHM CT. The objective of this study is to present a 9 MeV HHM CT prototype based on a high-average-current photo-injector in which X-rays with about 70μm focal spot size are produced via using tightly focused electron beams with 65/66μm beam size to …hit an optimized tungsten target. In digital radiography (DR) experiment using this HHM CT, clear imaging of a standard 0.1 mm lead DR resolution phantom reveals a resolution of 6 lp/mm (line pairs per mm), while a 5 lp/mm resolution is obtained in CT mode using another resolution phantom made of 10 mm ferrum. Moreover, comparing with the common CT systems, a better turbine blade prototype image was obtained with this HHM CT system, which also indicates the promising application potentials of HHM CT in non-destructive inspection or testing for high-density fine-structure samples. Show more

Keywords: Digital radiography (DR), Microfocus X-ray computed tomography (CT), non-destructive inspection, X-ray source, X-ray focal spot

DOI: 10.3233/XST-210960

Citation: Journal of X-Ray Science and Technology, vol. 30, no. 1, pp. 1-12, 2022

Authors: Olasz, Csaba | Varga, László G. | Nagy, Antal

Article Type: Research Article

Abstract: BACKGROUND: The fusion of computer tomography and deep learning is an effective way of achieving improved image quality and artifact reduction in reconstructed images. OBJECTIVE: In this paper, we present two novel neural network architectures for tomographic reconstruction with reduced effects of beam hardening and electrical noise. METHODS: In the case of the proposed novel architectures, the image reconstruction step is located inside the neural networks, which allows the network to be trained by taking the mathematical model of the projections into account. This strong connection enables us to enhance the projection data and the reconstructed …image together. We tested the two proposed models against three other methods on two datasets. The datasets contain physically correct simulated data, and they show strong signs of beam hardening and electrical noise. We also performed a numerical evaluation of the neural networks on the reconstructed images according to three error measurements and provided a scoring system of the methods derived from the three measures. RESULTS: The results showed the superiority of the novel architecture called TomoNet2 . TomoNet2 improved the quality of the images according to the average Structural Similarity Index from 0.9372 to 0.9977 and 0.9519 to 0.9886 on the two data sets, when compared to the FBP method. This network also yielded the best results for 79.2 and 53.0 percent for the two datasets according to Peak-Signal-to-Noise-Ratio compared to the other improvement techniques. CONCLUSIONS: Our experimental results showed that the reconstruction step used in skip connections in deep neural networks improves the quality of the reconstructions. We are confident that our proposed method can be effectively applied to other datasets for tomographic purposes. Show more

Keywords: Computed Tomography, Deep Learning, U-net, FBP

DOI: 10.3233/XST-210962

Citation: Journal of X-Ray Science and Technology, vol. 30, no. 1, pp. 13-31, 2022

Authors: Yang, Yunfeng | Guan, Chen

Article Type: Research Article

Abstract: The accurately automatic classification of medical pathological images has always been an important problem in the field of deep learning. However, the traditional manual extraction of features and image classification usually requires in-depth knowledge and more professional researchers to extract and calculate high-quality image features. This kind of operation generally takes a lot of time and the classification effect is not ideal. In order to solve these problems, this study proposes and tests an improved network model DenseNet-201-MSD to accomplish the task of classification of medical pathological images of breast cancer. First, the image is preprocessed, and the traditional pooling …layer is replaced by multiple scaling decomposition to prevent overfitting due to the large dimension of the image data set. Second, the BN algorithm is added before the activation function Softmax and Adam is used in the optimizer to optimize performance of the network model and improve image recognition accuracy of the network model. By verifying the performance of the model using the BreakHis dataset, the new deep learning model yields image classification accuracy of 99.4%, 98.8%, 98.2%and 99.4%when applying to four different magnifications of pathological images, respectively. The study results demonstrate that this new classification method and deep learning model can effectively improve accuracy of pathological image classification, which indicates its potential value in future clinical application. Show more

Keywords: Breast cancer pathological image, classification of breast cancer, convolutional neural network, DenseNet-201-MSD, multiple scaling decomposition, BN algorithm

DOI: 10.3233/XST-210982

Citation: Journal of X-Ray Science and Technology, vol. 30, no. 1, pp. 33-44, 2022

Authors: Sahli, Hanene | Ben Slama, Amine | Labidi, Salam

Article Type: Research Article

Abstract: This study proposes a new predictive segmentation method for liver tumors detection using computed tomography (CT) liver images. In the medical imaging field, the exact localization of metastasis lesions after acquisition faces persistent problems both for diagnostic aid and treatment effectiveness. Therefore, the improvement in the diagnostic process is substantially crucial in order to increase the success chance of the management and the therapeutic follow-up. The proposed procedure highlights a computerized approach based on an encoder–decoder structure in order to provide volumetric analysis of pathologic tumors. Specifically, we developed an automatic algorithm for the liver tumors defect segmentation through the …Seg-Net and U-Net architectures from metastasis CT images. In this study, we collected a dataset of 200 pathologically confirmed metastasis cancer cases. A total of 8,297 CT image slices of these cases were used developing and optimizing the proposed segmentation architecture. The model was trained and validated using 170 and 30 cases or 85% and 15% of the CT image data, respectively. Study results demonstrate the strength of the proposed approach that reveals the superlative segmentation performance as evaluated using following indices including F1-score = 0.9573, Recall = 0.9520, IOU = 0.9654, Binary cross entropy = 0.0032 and p -value <0.05, respectively. In comparison to state-of-the-art techniques, the proposed method yields a higher precision rate by specifying metastasis tumor position. Show more

Keywords: Liver tumors, CT images, segmentation, deep transfer learning, encoder-decoder architecture

DOI: 10.3233/XST-210993

Citation: Journal of X-Ray Science and Technology, vol. 30, no. 1, pp. 45-56, 2022

Authors: Widodo, Chomsin S. | Naba, Agus | Mahasin, Muhammad M. | Yueniwati, Yuyun | Putranto, Terawan A. | Patra, Pangeran I.

Article Type: Research Article

Abstract: BACKGROUND: Analysis of chest X-ray images is one of the primary standards in diagnosing patients with COVID-19 and pneumonia, which is faster than using PCR Swab method. However, accuracy of using X-ray images needs to be improved. OBJECTIVE: To develop a new deep learning system of chest X-ray images and evaluate whether it can quickly and accurately detect pneumonia and COVID-19 patients. METHODS: The developed deep learning system (UBNet v3) uses three architectural hierarchies, namely first, to build an architecture containing 7 convolution layers and 3 ANN layers (UBNet v1) to classify between …normal images and pneumonia images. Second, using 4 layers of convolution and 3 layers of ANN (UBNet v2) to classify between bacterial and viral pneumonia images. Third, using UBNet v1 to classify between pneumonia virus images and COVID-19 virus infected images. An open-source database with 9,250 chest X-ray images including 3,592 COVID-19 images were used in this study to train and test the developed deep learning models. RESULTS: CNN architecture with a hierarchical scheme developed in UBNet v3 using a simple architecture yielded following performance indices to detect chest X-ray images of COVID-19 patients namely, 99.6%accuracy, 99.7%precision, 99.7%sensitivity, 99.1%specificity, and F1 score of 99.74%. A desktop GUI-based monitoring and classification system supported by a simple CNN architecture can process each chest X-ray image to detect and classify COVID-19 image with an average time of 1.21 seconds. CONCLUSION: Using three hierarchical architectures in UBNet v3 improves system performance in classifying chest X-ray images of pneumonia and COVID-19 patients. A simple architecture also speeds up image processing time. Show more

Keywords: Deep learning, detection of COVID-19, classification of pneumonia, chest X-ray images, convolution neural network (CNN)

DOI: 10.3233/XST-211005

Citation: Journal of X-Ray Science and Technology, vol. 30, no. 1, pp. 57-71, 2022

Authors: Taspinar, Yavuz Selim | Cinar, Ilkay | Koklu, Murat

Article Type: Research Article

Abstract: Affecting millions of people all over the world, the COVID-19 pandemic has caused the death of hundreds of thousands of people since its beginning. Examinations also found that even if the COVID-19 patients initially survived the coronavirus, pneumonia left behind by the virus may still cause severe diseases resulting in organ failure and therefore death in the future. The aim of this study is to classify COVID-19, normal and viral pneumonia using the chest X-ray images with machine learning methods. A total of 3486 chest X-ray images from three classes were first classified by three single machine learning models including …the support vector machine (SVM), logistics regression (LR), artificial neural network (ANN) models, and then by a stacking model that was created by combining these 3 single models. Several performance evaluation indices including recall, precision, F-1 score, and accuracy were computed to evaluate and compare classification performance of 3 single four models and the final stacking model used in the study. As a result of the evaluations, the models namely, SVM, ANN, LR, and stacking, achieved 90.2%, 96.2%, 96.7%, and 96.9%classification accuracy, respectively. The study results indicate that the proposed stacking model is a fast and inexpensive method for assisting COVID-19 diagnosis, which can have potential to assist physicians and nurses to better and more efficiently diagnose COVID-19 infection cases in the busy clinical environment. Show more

Keywords: COVID-19, Stacking model, Convolutional neural network, X-ray chest images

DOI: 10.3233/XST-211031

Citation: Journal of X-Ray Science and Technology, vol. 30, no. 1, pp. 73-88, 2022

Authors: Naseer, Asma | Tamoor, Maria | Azhar, Arifah

Article Type: Research Article

Abstract: Background: Coronavirus Disease 2019 (COVID-19) is contagious, producing respiratory tract infection, caused by a newly discovered coronavirus. Its death toll is too high, and early diagnosis is the main problem nowadays. Infected people show a variety of symptoms such as fatigue, fever, tastelessness, dry cough, etc. Some other symptoms may also be manifested by radiographic visual identification. Therefore, Chest X-Rays (CXR) play a key role in the diagnosis of COVID-19. Methods: In this study, we use Chest X-Rays images to develop a computer-aided diagnosis (CAD) of the disease. These images are used to train two deep networks, the …Convolution Neural Network (CNN), and the Long Short-Term Memory Network (LSTM) which is an artificial Recurrent Neural Network (RNN). The proposed study involves three phases. First, the CNN model is trained on raw CXR images. Next, it is trained on pre-processed CXR images and finally enhanced CXR images are used for deep network CNN training. Geometric transformations, color transformations, image enhancement, and noise injection techniques are used for augmentation. From augmentation, we get 3,220 augmented CXRs as training datasets. In the final phase, CNN is used to extract the features of CXR imagery that are fed to the LSTM model. The performance of the four trained models is evaluated by the evaluation techniques of different models, including accuracy, specificity, sensitivity, false-positive rate, and receiver operating characteristic (ROC) curve. Results: We compare our results with other benchmark CNN models. Our proposed CNN-LSTM model gives superior accuracy (99.02%) than the other state-of-the-art models. Our method to get improved input, helped the CNN model to produce a very high true positive rate (TPR 1) and no false-negative result whereas false negative was a major problem while using Raw CXR images. Conclusions: We conclude after performing different experiments that some image pre-processing and augmentation, remarkably improves the results of CNN-based models. It will help a better early detection of the disease that will eventually reduce the mortality rate of COVID. Show more

Keywords: Chest X-Rays (CXRs), classification, computer-aided diagnosis (CAD), convolution neural network (CNN), COVID-19, long short-term memory network (LSTM), medical imaging

DOI: 10.3233/XST-211047

Citation: Journal of X-Ray Science and Technology, vol. 30, no. 1, pp. 89-109, 2022

Authors: Zhao, Lei | Liu, Lijuan | Zhao, Haiyan | Bao, Jiaqi | Dou, Yana | Yang, Zhenxing | Lin, Yang | Sun, Zhenting | Meng, Lingxin | Yan, Li | Liu, Aishi

Article Type: Research Article

Abstract: OBJECTIVE: To investigate feasibility of the quantitative parameters of dual-energy computed tomography (DECT) to assess therapy response in advanced non-small cell lung cancer (NSCLC) compared with the traditional enhanced CT parameters based on the Response Evaluation Criteria in Solid Tumors (RECIST) guidelines. METHODS: Forty-five patients with unresectable locally advanced NSCLC who underwent DECT before and after chemotherapy or concurrent chemoradiotherapy (cCRT) were prospectively enrolled. By comparing baseline studies with follow-up, patients were divided into two groups according to RECIST guidelines as follows: disease control (DC, including partial response and stable disease) and progressive disease (PD). The diameter (D), …attenuation, iodine concentration and normalized iodine concentration of arterial and venous phases (ICA, ICv, NICA, NICv ) and the percentage of these changes pre- and post-therapy were measured and calculated. The Pearson correlation was used to analyze correlation between various quantitative parameters. The receiver operating characteristic (ROC) curves were used to evaluate accuracy of therapy response prediction. RESULTS: The change percentages of Attenuation (Δ -Attenuation-A and Δ -Attenuation-V ), IC (Δ ICA and Δ ICV ) and NIC (Δ NICA and Δ NICV ) pre- and post-therapy correlate with the change percentage of D (Δ D). Among these, Δ ICA strongly correlates with Δ D (r  = 0.793, P  < 0.001). The areas under ROC curves generated using Δ -Attenuation-A , Δ ICA , and Δ NICA are 0.796, 0.900, and 0.880 with the corresponding cutoff value of 9.096, −15.692, and −4.7569, respectively, which are significantly different (P  < 0.001). CONCLUSIONS: The quantitative parameters of DECT iodine map, especially iodine concentration, in arterial phase provides a new quantitative image marker to predict therapy response of patients diagnosed with advanced NSCLC. Show more

Keywords: Dual-energy CT, therapeutic response, non-small cell lung cancer (NSCLC), quantitative image marker

DOI: 10.3233/XST-210989

Citation: Journal of X-Ray Science and Technology, vol. 30, no. 1, pp. 111-122, 2022

Authors: Tao, Wei | Ming, Xu | Zang, Yachen | Zhu, Jin | Zhang, Yuanyuan | Sun, Chuanyang | Xue, Boxin

Article Type: Research Article

Abstract: PURPOSE: To evaluate efficacy and safety of flexible ureteroscopy and laser lithotripsy (FURSL) for treatment of the upper urinary tract calculi. METHODS: We retrospectively analyzed 784 patients who underwent FURSL between January 2015 and October 2020 in our unit. All patients were preoperatively evaluated with urine analysis, serum biochemistry, urinary ultrasonography, non-contrast computed tomography and intravenous urography. The procedure was considered as successful in patients with complete stone disappearance or fragments < 4 mm on B ultrasound or computed tomography. The operative parameters, postoperative outcomes and complications were recorded and analyzed respectively. RESULTS: The average operative time and …postoperative hospital stay were 46.9±15.8 min and 1.2±1.1 days, respectively, among 784 patients. In addition, 746 patients were followed up and 38 patients were lost. In these patients, 700 (93.8%) cases met the stone removal criteria and 46 cases (6.2%) did not meet the stone removal criteria who need further treatment. The stone free rate (SFR) is 92.5%after 1–3 months and SFR of middle and upper calyceal calculi was higher than that of lower calyceal calculi significantly. The most common complications were fever (58/784, 7.4%), gross hematuria (540/784, 68.9%) and lpsilateral low back pain (47/784, 6.0%). The incidence rate of serious complication was 1.28%(10/784), including 5 cases of septic shock and 5 cases of subcapsular hematoma, which were cured after active treatment. CONCLUSION: FURSL is a reliable treatment for small and medium calculi patients of upper urinary tract. The curative effect of stone removal is clear. The complications are few and the safety is high. However, there are certain limitations to the efficacy in treating larger stone and lower calyceal calculi. Show more

Keywords: Upper urinary tractcalculi, flexible ureteroscopy, laser lithotripsy, stone free rate (SFR)

DOI: 10.3233/XST-210992

Citation: Journal of X-Ray Science and Technology, vol. 30, no. 1, pp. 123-133, 2022

Authors: Kim, Gyeong Rip | Kim, Sungho | Sung, Soon Ki | Kim, Chang Hyeun | Lee, Sang Bong | Yoo, Jang Seon | Kwak, Jong Hyeok

Article Type: Research Article

Abstract: OBJECTIVE: To invastgate feasibility of low-dose contrast agent in cerebral computed tomography angiography (CTA) to alleviate side effects. METHOD: Siemens’ Somatom Definition AS+CT scanner, Heine’s blood pressure monitor G7-M237 (BP cuff) and Ultravist contrast agent (370 mg Iodine/ml) are used. CTA is acquired using following scan parameters including slice thickness of 1mm, image acquisition parameters of 128×0.6 mm, pitch size of 0.8 mm, 175 effective mAs, 120 kVp tube voltage, scan delay time of 3 seconds, and the scan time of 4 seconds. This study is conducted by securing the IV route in the left antecubital vein before injection of contrast agent, …wrapping BP cuff around the branchial artery of the opposite right arm after setting the pressure to 200 mmHg. Then, the injection rate of the contrast agent is fixed at 4.5 cc/sec and contrast agent was injected in three different amounts (70, 80, and 100 cc). Bp cuff is released from this moment when HU value reachs 100. RESULT: In this study, the mean HU values measured from common carotid artery are 412.45±5.89 when injecting 80cc contrast agent and using BP cuff and 399.64±5.51 when injecting 100 cc contrast agenet and not using BP cuff, respectively. In middle cerebral artery M1, the mean HU values are 325.23±38.29 when injecting 80cc contrast agent and using BP cuff and 325.00±30.63 when injecting 100cc contrast agent blood and not using pressure cuff, respectively. Difference of mean HU values is not statistically significant (p  > 0.05) with and without using BP cuff. CONCLUSION: This study demonstrates that reducing amount of contrast agent is possible when the right brachial artery is compressed using BP cuff. Study results indicate that reducing 20% injection of contrast agent in CT cerebrovascular angiography can still yield comparable imaging results with conventional contrast angent usage, which implies that less side effects are expected with a contrast agent injection. Thus, this study can serve as a reference for potential reducing side effect during CT cerebrovascular angiography. Show more

Keywords: Contrast agent, right brachial artery, blood pressure cuff, computed tomography cerebrovascular angiography

DOI: 10.3233/XST-211022

Citation: Journal of X-Ray Science and Technology, vol. 30, no. 1, pp. 135-144, 2022