• 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 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 Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.313-315
• /
• 2021

Timely and accurate diagnosis of lung diseases using Chest X-ray images has been gained much attention from the computer vision and medical imaging communities. Although previous studies have presented the capability of deep convolutional neural networks by achieving competitive binary classification results, their models were seemingly unreliable to effectively distinguish multiple disease groups using a large number of x-ray images. In this paper, we aim to build an advanced approach, so-called Ensemble Knowledge Distillation (EKD), to significantly boost the classification accuracies, compared to traditional KD methods by distilling knowledge from a cumbersome teacher model into an ensemble of lightweight student models with parallel branches trained with ground truth labels. Therefore, learning features at different branches of the student models could enable the network to learn diverse patterns and improve the qualify of final predictions through an ensemble learning solution. Although we observed that experiments on the well-established ChestX-ray14 dataset showed the classification improvements of traditional KD compared to the base transfer learning approach, the EKD performance would be expected to potentially enhance classification accuracy and model generalization, especially in situations of the imbalanced dataset and the interdependency of 14 weakly annotated thorax diseases.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.9 no.1
• /
• pp.61-66
• /
• 2015

Chest X-ray images is the most common and widely used in clinical findings for a wide range of anatomical information about the prognosis of the disease in patients with cardiopulmonary rehabilitation. Many analysis algorithm was developed by a number of studies regarding the region segmentation and image analysis, there are specific differences due to the complexity and diversity of the image. In this paper, a diagnosis support system of the chest X-ray image based on image processing and analysis methods to detect the cardiopulmonary disease. The threshold value and morphological method was applied to segment the pulmonary region in a chest X-ray image. Anatomical measurements and texture analysis was performed on the segmented regions. The effectiveness of the proposed method is shown through experiments and comparison with diagnosis results by clinical experts to show that the proposed method can be used for decision support system.

• Tuberculosis and Respiratory Diseases
• /
• v.40 no.4
• /
• pp.353-356
• /
• 1993

Advent of new imaging modalities such as computed tomography, magnetic resonance imaging and ultrasound contributed greately to the specific imaging diagnosis. However plain chest X-ray is still most prequently used for imaging diagnosis of respiratory disease in clinical pratic and it is important to make a good quality of X-ray film and good interpretation. The optimal chest X-ray should be taken with full inspiration without rotation and motion and the exposure is at the level of barely demonstrable thoracic vertebral disc space. It is recommended that higk KVP technique for detection of lesions which is overlaped by mediastinum, heart and rib cage. It is better to examine chest X-ray film start at some distance(6-8 feet) and closer to the film later on and the reader should not read a film in fatigue condition. The reading room should be quiet and relately dark illumination. It is important, to make a good X-ray film and good interpretation to reduce the observer error.

• Journal of the Korean Society of Radiology
• /
• v.14 no.6
• /
• pp.773-780
• /
• 2020

With the development of the 4th industrial, research is being conducted to prevent diseases and reduce damage in various fields of science and technology such as medicine, health, and bio. As a result, artificial intelligence technology has been introduced and researched for image analysis of radiological examinations. In this paper, we will directly apply a deep learning model for classification and detection of pneumonia using chest X-ray images, and evaluate whether the deep learning model of the Inception series is a useful model for detecting pneumonia. As the experimental material, a chest X-ray image data set provided and shared free of charge by Kaggle was used, and out of the total 3,470 chest X-ray image data, it was classified into 1,870 training data sets, 1,100 validation data sets, and 500 test data sets. I did. As a result of the experiment, the result of metric evaluation of the Inception V3 deep learning model was 94.80% for accuracy, 97.24% for precision, 94.00% for recall, and 95.59 for F1 score. In addition, the accuracy of the final epoch for Inception V3 deep learning modeling was 94.91% for learning modeling and 89.68% for verification modeling for pneumonia detection and classification of chest X-ray images. For the evaluation of the loss function value, the learning modeling was 1.127% and the validation modeling was 4.603%. As a result, it was evaluated that the Inception V3 deep learning model is a very excellent deep learning model in extracting and classifying features of chest image data, and its learning state is also very good. As a result of matrix accuracy evaluation for test modeling, the accuracy of 96% for normal chest X-ray image data and 97% for pneumonia chest X-ray image data was proven. The deep learning model of the Inception series is considered to be a useful deep learning model for classification of chest diseases, and it is expected that it can also play an auxiliary role of human resources, so it is considered that it will be a solution to the problem of insufficient medical personnel. In the future, this study is expected to be presented as basic data for similar studies in the case of similar studies on the diagnosis of pneumonia using deep learning.

• 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.13 no.7
• /
• pp.1062-1075
• /
• 2010

In the medical image application the difference of intensity is widely used for the image segmentation and feature extraction, and a well known method is the threshold technique that determines a threshold value and generates a binary image based on the threshold. A frequently-used threshold technique is the Otsu algorithm that provides efficient processing and effective selection criterion for choosing the threshold value. However, we cannot get good segmentation results by applying the Otsu algorithm to chest X-ray images. It is because there are various organic structures around lung regions such as ribs and blood vessels, causing unclear distribution of intensity levels. To overcome the ambiguity, we propose in this paper an effective algorithm to extract pulmonary regions that utilizes the Otsu algorithm after removing the background of an X-ray image, constructs intensity-level maps, and uses them for segmenting the X-ray image. To verify the effectiveness of our method, we compared it with the existing 1-dimensional and 2-dimensional Otsu algorithms, and also the results by expert's naked eyes. The experimental result showed that our method achieved the more accurate extraction of pulmonary regions compared to the Otsu methods and showed the similar result as the naked eye's one.

• 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.

• 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.