• Proceedings of the Korean Magnestics Society Conference
• /
• 2014.05a
• /
• pp.61-62
• /
• 2014

• Journal of Internet Computing and Services
• /
• v.24 no.1
• /
• pp.49-59
• /
• 2023

Recently, attention to the pandemic situation represented by COVID-19 emerged problems caused by unexpected shortage of medical personnel. In this paper, we present a method for diagnosing the presence or absence of lesional sign on PA chest X-ray images as computer vision solution to support diagnosis tasks. Method for visual anomaly detection based on feature modeling can be also applied to X-ray images. With extracting feature vectors from PA chest X-ray images and divide to patch unit, region-specific abnormality can be detected. As preliminary experiment, we created simulation data set containing multiple objects and present results of the comparative experiments in this paper. We present method to improve both efficiency and performance of the process through hard masking of patch features to aligned images. By summing up regional specificity and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to previous studies. By aggregating region-specific and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to our last study.

• Journal of Korea Multimedia Society
• /
• v.16 no.7
• /
• pp.829-840
• /
• 2013

In this paper, we propose a new lung segmentation method for chest x-ray images which can take both global and local properties into account. Firstly, the initial lung segmentation is computed by applying the active shape model (ASM) which keeps the shape of deformable model from the pre-learned model and searches the image boundaries. At the second segmentation stage, we also applied the localizing region-based active contour model (LRACM) for correcting various regional errors in the initial segmentation. Finally, to measure the similarities, we calculated the Dice coefficient of the segmented area using each semiautomatic method with the result of the manually segmented area by a radiologist. The comparison experiments were performed using 5 lung x-ray images. In our experiment, the Dice coefficient with manually segmented area was $95.33%{\pm}0.93%$ for the proposed method. Effective segmentation methods will be essential for the development of computer-aided diagnosis systems for a more accurate early diagnosis and prognosis regarding lung cancer in chest x-ray images.

• Korean Journal of Radiology
• /
• v.21 no.5
• /
• pp.511-525
• /
• 2020

Chest X-ray radiography and computed tomography, the two mainstay modalities in thoracic radiology, are under active investigation with deep learning technology, which has shown promising performance in various tasks, including detection, classification, segmentation, and image synthesis, outperforming conventional methods and suggesting its potential for clinical implementation. However, the implementation of deep learning in daily clinical practice is in its infancy and facing several challenges, such as its limited ability to explain the output results, uncertain benefits regarding patient outcomes, and incomplete integration in daily workflow. In this review article, we will introduce the potential clinical applications of deep learning technology in thoracic radiology and discuss several challenges for its implementation in daily clinical practice.

• The Korean Journal of Nuclear Medicine
• /
• v.33 no.4
• /
• pp.381-387
• /
• 1999

Purpose: The International Labor Organization (ILO) has established an international standard for chest X-ray diagnosis of pneumoconiosis since 1980. However, there is a need for improved diagnosis and staging in occupational disease. We evaluated Ga-67 citrate scintigraphy quantitatively and correlated the scintigraphic findings with pulmonary function tests and chest X-ray results. Materials and Methods: Twenty-five patients underwent whole body scintigraphy with additional chest and abdomen images 48 hrs after intravenous injection of 185 MBq of Ga-67 citrate. Ten normal controls were also studied. Regions of interest (ROI) were drawn on the posterior image to measure counts from the liver and lungs (Lung/Liver Ratio). Results: L/L ratio according to the stages of chest X-ray classification were as follows; stage 0 (normal, n=10): $0.3948{\pm}0.0692$, stage 1 (n=10): $0.5763{\pm}0.1537$, stage 2 (n=11), $0.6849{\pm}0.1459$, stage 3 (n=4) $0.9913{\pm}0.0712$. There was a significant correlation between the scintigraphic L/L ratio and the X-ray stage (r=0.618, p<0.05). However, no significant correlation between L/L ratio and pulmonary function tests were observed (p>0.05). Conclusion: Quantitative Ga-67 scintigraphy can be a useful method for staging of silicosis. However, it is not a method to assess pulmonary functional impairment.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.794-798
• /
• 2009

We introduce an implementation of plug-ins on PLUTO. These plug-ins discriminate inflammatory nodules from other types of nodules in chest X-ray CT images. The PLUTO is a common platform for computer-aided diagnosis systems on Microsoft Windows series and it is easy to add new functions as plug-ins. We coded two plug-ins. One of the them calculates features based on medical knowledge. The other plug-in calculates parameters to classify the type of nodules, and it also classifies nodules into inflammatory nodules and others using SVM. These plug-ins are coded using MIST library which is produced at Nagoya University, Japan. In our previous study, the MIST library was parallelized, so that we can utilize a number of CPUs to calculate features and SVM learning/classifying depending on the amount of computation. Using these plug-ins, it became easy to extract features to discriminate inflammatory nodules from other types of nodules and to change parameters for feature extraction and SVM learning/classifying with GUI interface. The accuracy of the classifying result is 100% with 78 solid nodules which contains 43 inflammatory nodules and 35 other type of nodules.

• Journal of the Korean Society of Radiology
• /
• v.15 no.2
• /
• pp.139-145
• /
• 2021

This study is to confirm the range of tube voltage for Chest X-ray in DR system by comparing with dose area product (DAP) and effective dose in efficient detector exposure index (DEI) range. GE definium 8000 was used to for the phantom study. The range of tube voltage is 60~130 kVp and of mAs is 2.5~40 mAs. The acquired images were classified into efficient DEI groups, then calculated effective dose with DAP by using a PC-Based Monte Carlo Program 2.0. The signal to noise ratio (SNR) was measured at 4 regions, including the thoracic spine, the lung area with the ribs, the lung area without the ribs, and the liver by using Picture Archiving and Communication System. The significance of the group for each tube voltage was verified by performing the kruskal-wallis test and the mann-whitney test as a post-test. When set to 4 groups dependned on the tube voltage, DAP showed significant differences; 60 kVp and 80 kVp, and 60 kVp and 90 kVp (p= 0.034, 0.021). Effective dose exhibited no statistically significant differences from the all of the group (p>0.05). SNR exhibited statistically significant differences from the all of the group in the liver except compared to 80 kVp and 90 kVp (p<0.05). Therefore, high tube voltages of 100 kVp or more need to be reconsidered in terms of patient dose and imaging in order to represent an appropriate chest X-ray image in a digital system.

• Journal of radiological science and technology
• /
• v.40 no.3
• /
• pp.371-376
• /
• 2017

Since in case of children, they are sensitive to the radiation compared to the adult and the potential exposure damage lasts longer, the exposure dose should be managed better than for the adult. Therefore, this study was conducted to observe the change in the chest x-ray image by the use of grid, which eliminates the scattering rays but increases the exposure dose during the child chest x-ray examination. As a research method, SNR, CNR and V. Vuichi were measured at 100 cm and 180 cm with the grid varying the kVp to 70, 90 and 110. In addition, SNR, CNR and V. Vuichi were measured fixing 100 cm and 180cm without grid and varying the dose to 6, 8 and 10 mAs. In the results of measuring them by fixing kVp, SNR, VNR and V. Vuichi were represented high when FID is 100cm. And in the results of meaduring them varying mAs, SNR, VNR and V. Vuichi were represented high when FID is 100cm. Currently in our country, the chest x-ray examination is performed at 180 cm. However, as the image is measured high when FID is 100 cm, in case of child, FID is deemed to be 100 cm.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.133-134
• /
• 2015

흉부 X-ray 영상에서 몸체 및 관심영역 분할 기법은 의료 X-ray 영상의 화질 개선 알고리즘을 더 효과적으로 적용하기 위해 전처리 단계로 영상의 물체와 배경을 분할하거나 관심영역만을 분할하는 방법이다. 보통 화질 개선 알고리즘을 적용할 때 영상의 밝기 정보나 주파수 정보를 이용하여 영상 디테일과 대비를 개선하는 방법을 사용한다. 영상 전체에 이러한 알고리즘을 적용하는 경우 불필요한 배경 정보가 포함되기 때문에 디테일과 대비가 떨어질 수 있다. 본 논문은 사용자가 보고자 하는 부분의 정보만을 사용하도록 물체를 분할하는 알고리즘을 제안한다. 1 단계로 몸체 분할 알고리즘을 이용하여 배경 성분의 정보를 제외하고 2 단계에서는 몸체의 중심인 폐와 폐사이의 장기 정보만을 볼 때의 관심영역 분할 알고리즘으로 팔이나 목, 복부의 불필요한 정보를 제외하는 방법을 제안한다.

• Journal of Biomedical Engineering Research
• /
• v.8 no.2
• /
• pp.171-176
• /
• 1987

Wiener filtering method was applied to the dual energy imaging procedure in digital radiography(D.R.). A linear scanning photodiode arrays with 1024 elements(0.6mm H 1.3mm pixel size) were used to obtain chest images in 0.7 sec. For high energy image acquisition, X-ray tube was set at 140KVp, 100mA with a rare-earth phosphor screen. Low energy image was obtained with X-ray tube setting at 70KVp, 150mA. These measured dual energy images are represented in the vector matrix notation as a linear discrete model including the additive random noise. Then, the object images are restored in the minimum mean square error sense using Wiener filtering method in the transformed domain. These restored high and low energy images are used for computation of the basis image decomposition. Then the basis images are linearly combined to produce bone or tissue selective images. Using this process, we could improve the signal to noise ratio characteristics in the material selective images.