• Journal of the Korean Society of Radiology
• /
• v.15 no.5
• /
• pp.613-620
• /
• 2021

The purpose of this study is to propose a convolutional neural network model that can classify normal and abnormal(cardiomegaly) in chest X-ray images. The training data and test data used in this paper were used by acquiring chest X-ray images of patients diagnosed with normal and abnormal(cardiomegaly). Using the proposed deep learning model, we classified normal and abnormal(cardiomegaly) images and verified the classification performance. When using the proposed model, the classification accuracy of normal and abnormal(cardiomegaly) was 99.88%. Validation of classification performance using normal images as test data showed 95%, 100%, 90%, and 96% in accuracy, precision, recall, and F1 score. Validation of classification performance using abnormal(cardiomegaly) images as test data showed 95%, 92%, 100%, and 96% in accuracy, precision, recall, and F1 score. Our classification results show that the proposed convolutional neural network model shows very good performance in feature extraction and classification of chest X-ray images. The convolutional neural network model proposed in this paper is expected to show useful results for disease classification of chest X-ray images, and further study of CNN models are needed focusing on the features of medical images.

• Nuclear Engineering and Technology
• /
• v.53 no.5
• /
• pp.1626-1633
• /
• 2021

In an industrial field, non-destructive testing (NDT) is commonly used to inspect industrial products. Among NDT methods using radiation sources, X-ray laminography has several advantages, such as high depth resolution and low computational costs. Moreover, an X-ray laminography system with stationary source array and compact detector is able to reduce mechanical motion artifacts and improve inspection efficiency. However, this system, called stationary inverse-geometry X-ray laminography (s-IGXL), causes truncation artifacts in reconstructed images due to limited fields-of-view (FOVs). In this study, we proposed a projection data correction (PDC) method to reduce the truncation artifacts arisen in s-IGXL images, and the performance of the proposed method was evaluated with the different number of focal spots in terms of quantitative accuracy. Comparing with conventional techniques, the PDC method showed superior performance in reducing truncation artifacts and improved the quantitative accuracy of s-IGXL images for all the number of focal spots. In conclusion, the PDC method can improve the accuracy of s-IGXL images and allow precise NDT measurements.

• Nuclear Engineering and Technology
• /
• v.54 no.9
• /
• pp.3380-3389
• /
• 2022

We evaluated the performance of an improved hybrid median filter (IHMF) applied to X-ray computed tomography (CT) images obtained using a high-resolution photon-counting cadmium zinc telluride (CZT) detector. To study how the proposed approach improves the image quality, we measured the noise levels and the overall CT-image quality. We established a CZT imaging system with a detector length of 5.12 cm and thickness of 0.3 cm and acquired phantom images. To evaluate the efficacy of the proposed filter, we first modeled two conventional median filters. Subsequently, we were able to achieve a normalized noise power spectrum result of ~10^-8 mm², and furthermore, the proposed method improved the contrast-to-noise ratio by a factor of ~1.51 and the coefficient of variation by 1.55 relative to the counterpart values of the no-filter image. In addition, the IHMF exhibited the best performance among the three filters considered as regards the peak signal-to-noise ratio and no-reference-based image-quality evaluation parameters. Thus, our results demonstrate that the IHMF approach provides a superior image performance over conventional median filtering methods when applied to actual CZT X-ray CT images.

• Journal of information and communication convergence engineering
• /
• v.20 no.3
• /
• pp.219-225
• /
• 2022

In this study, we propose training a support vector machine (SVM) model on top of deep networks for detecting Covid-19 from chest X-ray images. We started by gathering a real chest X-ray image dataset, including positive Covid-19, normal cases, and other lung diseases not caused by Covid-19. Instead of training deep networks from scratch, we fine-tuned recent pre-trained deep network models, such as DenseNet121, MobileNet v2, Inception v3, Xception, ResNet50, VGG16, and VGG19, to classify chest X-ray images into one of three classes (Covid-19, normal, and other lung). We propose training an SVM model on top of deep networks to perform a nonlinear combination of deep network outputs, improving classification over any single deep network. The empirical test results on the real chest X-ray image dataset show that deep network models, with an exception of ResNet50 with 82.44%, provide an accuracy of at least 92% on the test set. The proposed SVM on top of the deep network achieved the highest accuracy of 96.16%.

• 한국가시화정보학회:학술대회논문집
• /
• 2007.11a
• /
• pp.155-158
• /
• 2007

Water management for Polymer Electrolyte Fuel Cell (PEFC) has been receiving large attention as an important issue in practical applications. Proper water management is vital to achieve high performance and durability of PEFC. In this study, an X-ray imaging technique was employed to visualize the water distribution in a PEFC quantitatively. X-ray images of the PEFC components with and without water are distinguished clearly. From the visualized X-ray images, we could confirm the water distribution in the region between separator and gas diffusion layer (GDL). In addition, the contact angle of water in the micro-channels was also clearly visualized..

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.2
• /
• pp.155-160
• /
• 2004

In this paper, we describe the results of a study on the edge enhancement of X-ray images by using their fuzzy system representation. A set of gray scale X-ray images was generated using the EGS4 computer code. An aluminum plate or a lead plate with three parallel strips taken out has been used as the object with the thickness and the width of the plate, and the gap between the two strips varied. We started with a comparative study on a set of the fuzzy sets for their applicability as the input fuzzy sets for the fuzzy system representation of the gray scale images. Then we describe how the fuzzy system is used to sharpen the edges. Our algorithm is based on adding the magnitude of the gradient not to the pixel value of concern but rather to the nearest neighboring pixel in the direction of the gradient. We show that this algorithm is better in maintaining the spatial resolution of the original image after the edge enhancement.

• Journal of radiological science and technology
• /
• v.45 no.2
• /
• pp.117-125
• /
• 2022

Although stationary inverse-geometry digital tomosynthesis (s-IGDT) is able to reduce motion artifacts, image acquisition time and radiation dose, the image quality of the s-IGDT is degraded due to the truncations arisen in projections. Therefore, the effects of geometric and image acquisition conditions in the s-IGDT should be analyzed for improving the image quality and clinical applicability of the s-IGDT system. In this study, the s-IGDT images were obtained with the various X-ray source arrangement types and the various number of projections. The resolution and noise characteristics of the obtained s-IGDT images were evaluated, and the characteristics were compared with those of the conventional DT images. The s-IGDT system using linear X-ray source arrangement and 40 projections maximized the image characteristics of resolution and noise, and the corresponding system was superior to the conventional DT system in terms of image resolution. In conclusion, we expect that the s-IGDT system can be used for providing medical images in diagnosis.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.27 no.11
• /
• pp.1612-1617
• /
• 2003

Synchrotron X-ray micro imaging technique was employed to non-invasively monitor the water flow inside xylem vessels in a bamboo leaf. The phase contrast X-ray images clearly visualized plant anatomy and the rise of a water front inside the vessels. Consecutive X-ray images taken for 60 seconds revealed water rise kinetics against gravity in the xylem of a cut dry leaf taken from a bamboo tree. For the first time, traces of water rise, variation of contact angle between water and xylem wall as well as the internal structure of xylem were obtained. In xylem vessels, a repeating flow pattern has a typical flow velocity of 30.7$\mu\textrm{m}$/s and faster flow is established intermittently. It is concluded that the transmission type of X-ray micro imaging can be used as a powerful tool to investigate the ascent of sap in the xylem vessels at a resolution higher than that of MRI.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.17 no.3
• /
• pp.13-27
• /
• 2015

The purpose of this study is to understand the general process from textile design till fashion design and to understand the relation between the body structure by using the x-ray technique. The research method was to see background of the anatomic feature and human skeletal X-ray projection through historical aspect of publications, the Internet, and paper. In terms of production, in order to present a design that takes into account the unique silhouette of the human body without distorting the shape of the human skeleton, X-ray images that were reconstituted using a computer graphic tool (Photoshop CS) were reproduced into the fabric as intense images through the digital Textile Printing technique that is capable of expressing fine and delicate details, and applied into the design. An original design was developed that emphasized the impression of the human body being projected and the shape of the human skeleton realistically expressed in terms of silhouette and detail. The results are as follows: First, Body has a anatomic formative characteristic and its formativeness becomes as a great motive for the artistic expression and thereby it becomes more unique and available for new design expression. Second, Using the 'body frame' as the motive of the research, there's mainly tried to make an unique expression. Third, according to reconstructing human skeletal X-ray projection by using Adobe Photoshop CS2, it can be expressed strong and unique design. Forth, DTP which is being used as an essential technique, expresses the body frame realistically and being used the special type of functional product and silk. Likewise by discovering the diverse formativeness of our body frame and reflecting the sense of humanity into the pieces there's been able to make and develop an unique fashion design. I sincerely hope there is a hug progress in this research in this area.

• Journal of Korea Multimedia Society
• /
• v.15 no.12
• /
• pp.1442-1448
• /
• 2012

The problem of Metal Area Segmentation (MAS) in X-ray CT images is a very hard task because of metal artifacts. This research features a practical yet effective method for MAS in X-ray CT images that exploits both projection image and reconstructed image spaces. We employ the Relevant Neighbor Area (RNA) idea [1] originally developed for projection image inpainting in order to create a novel feature in the projection image space that distinctively represents metal and near-metal pixels with opposite signs. In the reconstructed result of the feature image, application of a simple thresholding technique provides accurate segmentation of metal areas due to nice separation of near-metal areas from metal areas in its histogram.