• Journal of information and communication convergence engineering
• /
• v.13 no.4
• /
• pp.264-269
• /
• 2015

The chest X-ray image cannot be focused in the same manner that optical lenses are and the resultant image generally tends to be slightly blurred. Therefore, the methods to improve the quality of chest X-ray image have been studied. In this paper, the inherent noises of the input images are suppressed by adding the Laplacian image to the original. First, the chest X-ray image using an Gaussian high pass filter and an optimal high frequency emphasis filter has shown improvements in the edges and contrast of flat areas. Second, using fuzzy logic_histogram equalization, each pixel of the chest X-ray image shows the normal distribution of intensities that are not overexposed. As a result, the proposed method has shown the enhanced edge and contrast of the images with the noise canceling effect.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.287-294
• /
• 2023

This study was conducted to ultimately reduce unnecessary radiation exposure by emphasizing the need and importance of correct positioning by examining the positioning relationship of anatomical structures in the human body and changes in X-ray images according to changes in patient positioning during the left lateral chest X-ray examination. This study investigated and analyzed previously published papers and books on the left lateral chest X-ray examination to find out the importance of positioning in the left lateral chest X-ray examination. To find out the importance of correct positioning in the left lateral chest X-ray, we compared three images of incorrectly positioned right thorax and left thorax rotated forward and the lower median surface of the body leaning against the image receptor. In the left lateral chest examination, a distorted image was obtained in which the shape of the anatomical structure observed in the image was changed according to the presence or absence of rotation of the patient and the inclination of the median visual surface. X-ray images with the most accurate and large amount of information were obtained from X-ray images with the correct positioning performed during left lateral chest X-ray examination. Therefore, It is believed that the left lateral chest X-ray examination will have beneficial effects such as providing accurate medical information, preventing misdiagnosis, reducing social costs, and ultimately reducing radiation exposure.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.2
• /
• pp.371-378
• /
• 2000

In this study, we proposed pathological pattern detection system for X-ray chest image using artificial neural network. In a physical examination, radiologists have checked on the chest image projected the view box by a magnifying glass and found out what the disease is. Here, the detection of X-ray fluoroscopy is tedious and time-consuming for human doing. Lowering of efficiency for chest diagnosis is caused by lots mistakes of radiologist because of detecting the micro pathology from the film of small size. So, we proposed the method for disease detection using artificial neural network and digital image processing on a X-ray chest image. This method composes the function of image sampling, median filter, image equalizer used neural network and pattern recognition used neural network. We confirm this method has improved the problem of a conventional method.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.1059-1062
• /
• 1999

Recently, X-ray chest radiograph is showing a tendency to take an image of digital radiograph so as to diagnose the pathological pattern of chest in a usual. When the radiologist observes the chest image derived from digital radiograph system on the monitor. he feels difficult to find out because of the sensitivity of chest radiograph. It takes amount of time to adjust the proper image for diagnosis. Therefore, we provided the result and the method of the optimal image equalization for image enhancement.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.538-539
• /
• 2015

일반 영상의 화질을 개선하기 위해 다양한 알고리즘이 존재한다. 하지만 X-ray 영상의 경우 일반 영상과 특성이 다르기 때문에 기존의 화질 개선 알고리즘으로는 진단에 적합한 화질을 얻을 수 없다. 디지털 X-ray 기기로부터 처음 획득된 X-ray 영상은 데이터 범위가 일반 영상에 비해 넓고 밝기 레벨이 고르지 못하다. 특히 Chest X-ray 영상의 경우 다양한 이유로 촬영하기 때문에 갈비뼈와 혈관, 척추 뼈 등 특성이 다른 모든 부위들을 자연스럽게 개선할 필요가 있다. 본 논문은 영상의 불필요한 배경 성분을 제거하여 특정 밝기에 밀집되어 있는 데이터들의 히스토그램 범위를 확장시키고 주파수 대역 별 가중치를 조절하여 대비 및 선명도를 향상시킨다. 마지막으로 전역적 대비 개선 기법과 지역적 대비 개선 기법의 장점을 취하여 진단에 적합하도록 개선된 Chest X-ray 영상을 얻는다.

• 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%.

• The Journal of the Korea Contents Association
• /
• v.12 no.7
• /
• pp.255-260
• /
• 2012

This study aims to examine the generation of scatter rays by dividing it into the presence of the subject at the chest X-ray examination, the X-ray tube and detector in the X-ray room, the front of the patient window, the outside of the entrance door of the patient waiting room, opening of the entrance door, the outside of the radiological technologist's entrance door, and the opening of the radiological technologist's entrance door, etc. When there is a subject, as the subject is thicker, more scatter rays occur at each of the spots for measurement. And when the entrance door is closed at the measurement, fewer scatter rays are generated.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.1
• /
• pp.49-55
• /
• 2000

Recently, X-ray chest rediography is showing a tendency to take an image of digital radiography so as to diagnose the pathology of chest in a usual. When the radiologist observes the chest image derived from digital radiography system on the monitor, he feels difficult to find out the pathological pattern because the quality of chest radiography is unequal. It takes amount of time to adjust the proper image for diagnosis. Therefore, we propose the method of the chest image equalization using neural networks and provide the compared result with histogram equalization method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2131-2153
• /
• 2022

To achieve accurate detection of tuberculosis (TB) areas in chest radiographs, we design a chest X-ray TB area detection algorithm. The algorithm consists of two stages: the chest X-ray TB classification network (CXTCNet) and the chest X-ray TB area detection network (CXTDNet). CXTCNet is used to judge the presence or absence of TB areas in chest X-ray images, thereby excluding the influence of other lung diseases on the detection of TB areas. It can reduce false positives in the detection network and improve the accuracy of detection results. In CXTCNet, we propose a channel attention mechanism (CAM) module and combine it with DenseNet. This module enables the network to learn more spatial and channel features information about chest X-ray images, thereby improving network performance. CXTDNet is a design based on a sparse object detection algorithm (Sparse R-CNN). A group of fixed learnable proposal boxes and learnable proposal features are using for classification and location. The predictions of the algorithm are output directly without non-maximal suppression post-processing. Furthermore, we use CLAHE to reduce image noise and improve image quality for data preprocessing. Experiments on dataset TBX11K show that the accuracy of the proposed CXTCNet is up to 99.10%, which is better than most current TB classification algorithms. Finally, our proposed chest X-ray TB detection algorithm could achieve AP of 45.35% and AP50 of 74.20%. We also establish a chest X-ray TB dataset with 304 sheets. And experiments on this dataset showed that the accuracy of the diagnosis was comparable to that of radiologists. We hope that our proposed algorithm and established dataset will advance the field of TB detection.

• Journal of Biomedical Engineering Research
• /
• v.13 no.1
• /
• pp.25-32
• /
• 1992

A new restoration method of chest X -ray image (dual project filter) was proposed to improve SNR(signal to noise ratio) characteristics. In this method, a priori Information of system and anatomical structure and statistics of projected object are used in the design of filter. Dual projection filter varies its parameters, adapting to the local regions of chest(lung region, mediasternum, subdiaphragm) and the structure of chest (bone, tissue, blood vessel, bronchia). The performance of Dual Projection Filter was 0.1-0.2dB better than Dual Sensor Wiener Filter, which was used for initial estimate of Dual Porjection Filter.