• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.2_2
• /
• pp.437-443
• /
• 2024

The purpose of radiological Dispersal Device(RDD) is to kill people by explosives and to cause radiation exposure by dispersing radioactive materials. And It is a form of explosive that combines radioactive materials such as Co-60 and Ir-192 with improvised explosives. In this study, we tested and evaluated whether it was possible to read the internal structure of an explosive using X-rays in a radioactive explosive situation. The improvised explosive device was manufactured using 2 lb of model TNT explosives, one practice detonator, one 9V battery, and a timer switch in a leather briefcase measuring 41×35×10 cm³. The radioactive material used was the Co-60 source used in the low-level gamma ray irradiation device operated at the Advanced Radiation Research Institute of the Korea Atomic Energy Research Institute. The radiation dose used was gamma ray energy of 1.17 MeV and 1.33 MeV from a Co-60 source of 2208 Ci. The dose rates are divided into 0.5, 1, 2, and 4 Gy/h, and the exposure time was divided into 1, 3, 5, and 10 minutes. Co-60 source was mixed with the manufactured explosive and X-ray image reading was performed. As a result of the experiment, the X-ray image appeared black in all conditions divided by dose rate and time, and it was impossible to confirm the internal structure of the explosive. This is because γ-rays emitted from radioactive explosives have higher energy and stronger penetrating power than X-rays, so it is believed that imaging using X-rays is limited By blackening the film. The results of this study are expected to be used as basic data for research and development of X-ray imaging that can read the internal structure of explosives in radioactive explosive situations.

• Korean Journal of Digital Imaging in Medicine
• /
• v.12 no.2
• /
• pp.89-95
• /
• 2010

High contrast and high resolution are the most important factors for examining mammography images. Despite of the inconveniences of screen-film, most clinics still prefer them to computed radiography(CR) and direct radiography(DR). The reading of screen-film mammography images is influenced by the brightness from the X-ray illuminator, the exam room and incoming light from outside sources. Therefore, a comparative analysis on the results of mammo phantom images would be variated by the changes in the reading environment. There was no influence on reading results from the examiners close distance eyesight(p > 0.05); however, reading of micro lesions improved with greater darkness in the X-ray film reading room and the brightness of the X-ray illuminator(p < 0.05). Also, observation of fiber and mass images were maximized at a distance of 50 cm from the reader. Now, it is possible to observe these small classification groups using a magnifying glass without being physically close to the image. For the image of mammography, obtaining high quality images is important but in order to get an accurate clinical lesions of the reading also needs to be considered the optimal environmental factors.

• Electronics and Telecommunications Trends
• /
• v.35 no.6
• /
• pp.37-47
• /
• 2020

Today, the volume of international trade by airplanes and ships is rapidly increasing, and the volume of trade over land is expected to increase as inter-Korean relations change. In customs processes, humans inspect using the naked eye; therefore, computer vision technology can be used to assist customs inspectors responsible for X-ray security screening. In particular, because of recent advances in deep learning technology, algorithms for image understanding and object detection performance are improving, and studies on their application to X-ray screening have been published. This manuscript describes trends in artificial intelligence X-ray image-reading technology to detect prohibited items. X-ray inspection AI technology is similar to the Sphinx, which was the guardian of the pyramids in ancient Egyptian mythology.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.789-795
• /
• 2020

Many deaths have been reported due to the worldwide pandemic of COVID-19. In order to prevent the further spread of COVID-19, it is necessary to quickly and accurately read images of suspected patients and take appropriate measures. To this end, this paper introduces a deep learning-based COVID-19 chest X-ray reading technique that can assist in image reading by providing medical staff whether a patient is infected. First of all, in order to learn the reading model, a sufficient dataset must be secured, but the currently provided COVID-19 open dataset does not have enough image data to ensure the accuracy of learning. Therefore, we solved the image data number imbalance problem that degrades AI learning performance by using a Stacked Generative Adversarial Network(StackGAN++). Next, the DenseNet-based classification model was trained using the augmented data set to develop the reading model. This classification model is a model for binary classification of normal chest X-ray and COVID-19 chest X-ray, and the performance of the model was evaluated using part of the actual image data as test data. Finally, the reliability of the model was secured by presenting the basis for judging the presence or absence of disease in the input image using Grad-CAM, one of the explainable artificial intelligence called XAI.

• Journal of Biomedical Engineering Research
• /
• v.43 no.4
• /
• pp.290-297
• /
• 2022

During surgery, Surgical instruments are often left behind due to accidents. Most of these are surgical gauze, so radioactive non-permeable gauze (X-ray gauze) is used for preventing of accidents which gauze is left in the body. This gauze is divided into wire and pad type. If it is confirmed that the gauze remains in the body, gauze must be detected by radiologist's reading by imaging using a mobile X-ray device. But most of operating rooms are not equipped with a mobile X-ray device, but equipped C-Arm equipment, which is of poorer quality than mobile X-ray equipment and furthermore it takes time to read them. In this study, Use C-Arm equipment to acquire gauze image for detection and Build dataset using artificial intelligence and select a detection model to Assist with the relatively low image quality and the reading of radiology specialists. mAP@50 and detection time are used as indicators for performance evaluation. The result is that two-class gauze detection dataset is more accurate and YOLOv5 model mAP@50 is 93.4% and detection time is 11.7 ms.

• Journal of the Korean Society of Radiology
• /
• v.15 no.3
• /
• pp.329-336
• /
• 2021

The Study studied the Inspection Method of Images to obtain a sharp image of the Costume among the bones Composed of Thoracic Using the Thoracic Cage Rando Phantom. At 80 cm of the phantom Distance at the X-ray tube focus, the position of the Phantom was Examined by Changing the Rt and Lt Posterior Oblique(LAO) and Rt and Lt Posterior Postero Oblique positions by 20°, 25° and 30°. The acquired images were Subjectively Evaluated by the Radiographer, and the Evaluation data were analyzed as SPSS ver. 3.0. The signal-to-noise ratio (SNR) was Calculated using the ImageJ Program. As a result, the Cronbach Alpha value was Significantly higher at 0.789. The results of the Signal-to-Noise Ratio (SNR) were high at 20° to 6.038 in the right posterior Transcription Direction at the time of Examination and 7.860, in the Supine Position, for images of Sternum bones. In conclusion, it is Believed that the patient position can be obtained from the Right Anterior Oblique(RAO) Position 20° if the X-ray technique is used to obtain the Sternum's advanced image, and the Left Anterior Oblique(LAO) Position 25° when filming in the Rght lying position.

• Journal of Biomedical Engineering Research
• /
• v.39 no.1
• /
• pp.48-54
• /
• 2018

In this study, We developed a Ancillary device for child radiography for X-ray of children under 5 years old and verified its effectiveness. Chest X-rays of children younger than 5 years of age were performed by Supine method at the position of Table detector, Short - Source to Image Receptor Distance(SID). Existing Supine and Short -SID imaging methods cause many problems, such as errors in image reading and excessive radiation exposure dose to patients, but the use of an Ancillary device for child radiography(ADCR) solves these problems. A total of 160 children were divided into the Upright group using ADCR and Supine group without ADCR. The chest X-ray image was visually evaluated by two radiologists with reference to the European Commission's List of Quality Criteria for Diagnostic Radiographic Images in Pediatrics. The total score of the qualitative evaluation was 5.15% higher in the chest upright method using ADCR than in the chest supine method without ADCR, and the chest upright method score was higher than that of the chest supine method in items 1 to 7. whether infants have deep inspiration or not, 4.87% higher for item 1, whether infants rotate or not and the degree of tilting, 0% higher for the item 2, the reproduction of image from just above apices of lungs to T12/L1, 0% for the item 3, reproduction of the vascular pattern in central 2/3 of the lungs, 6.92% higher for the item 4, reproduction of the trachea and the proximal bronchi, 12.9% higher for the item 5, visually sharp reproduction of the diaphragm and costo-phrenic angles, 10% higher for the item 6, reproduction of the spine and paraspinal structures and visualisation of the retrocardiac lung and the mediastinum, and 3.65% higher for the item 7. Items 2 and 3 showed no statistically significant differences(P > 0.05), and items 1, 4, 5, 6, and 7 showed statistically significant differences(P < 0.05). In conclusion, Upright method using ADCR in pediatric chest X-ray is considered as a good alternative to existing Supine method.

• Journal of the Korean Society of Radiology
• /
• v.17 no.6
• /
• pp.873-879
• /
• 2023

This study explored the use of artificial intelligence(AI) to detect foreign bodies in chest X-ray images. Medical imaging, especially chest X-rays, plays a crucial role in diagnosing diseases such as pneumonia and lung cancer. With the increase in imaging tests, AI has become an important tool for efficient and fast diagnosis. However, images can contain foreign objects, including everyday jewelry like buttons and bra wires, which can interfere with accurate readings. In this study, we developed an AI algorithm that accurately identifies these foreign objects and processed the National Institutes of Health chest X-ray dataset based on the YOLOv8 model. The results showed high detection performance with accuracy, precision, recall, and F1-score all close to 0.91. Despite the excellent performance of AI, the study solved the problem that foreign objects in the image can distort the reading results, emphasizing the innovative role of AI in radiology and its reliability based on accuracy, which is essential for clinical implementation.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.18 no.3
• /
• pp.283-292
• /
• 2015

This paper presents the development of the automatic safety inspection technique for the ammunition fuzes using radiography images. The technique inspects 49-ammunition fuze by detecting the X-ray or neutron radiographic images to check whether the fuze is unintendedly armed or/and some major assembled parts are at right place. To execute the program, we loads the image(s) for under test. After reading images, the program conducts a series of pre-image processing, and then starts inspecting input images by using the detection algorithms which are designed distinctively for each fuze. After completing the detection process, the program displays the final result of the fuze status: "safety or danger." Through this program, we can cut off the fuzes which have any doubt about safety, and can only provide absolutely safe fuzes, compared with the current naked eye inspection method.

• Journal of the Korean Society of Radiology
• /
• v.12 no.1
• /
• pp.39-46
• /
• 2018

The purpose of this study was to determine suitable angle of Tibia-foot and the X-ray tube for scaphoid in foot X-ray examination. A total of twenty patients(mean age $32.12{\pm}years)$ are participated in this study. In the positions of Foot AP, internal and external oblique, tibia-foot angle was defined as $90^{\circ}$ and $135^{\circ}$, and x-ray tube angle was defined as $0^{\circ}$, $5^{\circ}$, $10^{\circ}$, $15^{\circ}$ and $20^{\circ}$ respectively. The image quality was evaluated with blind test yielding scores ranging from 0 to 5 by the evaluation team consisted of 2 radiogical technologists, 2 radiologists, and 2 orthopedic surgeons. In case of Foot AP position, the degree of overlap between cuneiform and navicular was 3% and the blind test result was 4.89 at tibia-foot angle of $90^{\circ}$ and $15^{\circ}$ X-ray tube angle. When the tibia-foot angle is $135^{\circ}$, the degree of overlap was 5%, also the blind test result was 4.30 at $15^{\circ}$ X-ray tube angle. The degree of overlap and blind test result were 30% and 3.75 respectively at $0^{\circ}$ X-ray tube angle. In case of internal oblique position, at tibia-foot angle of $90^{\circ}$ and $0^{\circ}$ X-ray tube angle, the degree of overlap was 4% and the blind test result was 4.70. The 5% overlapping and highest score as 4.55 were obtained on tibia-foot angle of $135^{\circ}$ and $0^{\circ}$ X-ray tube angle. In case of external oblique position, at tibia-foot angle of $90^{\circ}$ and $15^{\circ}$ X-ray tube angle, the degree of overlap was 4% and the blind test score was 4.85. The 5% overlapping and highest score as 4.75 were obtained on tibia-foot angle of $135^{\circ}$ and $15^{\circ}$ X-ray tube angle. In conclusion, we confirmed suitable angle of tibia-foot and X-ray tube for scaph46oid in foot X-ray examination in this study. These findings will be helpful for us to reading for navicular fracture.