• Journal of radiological science and technology
• /
• v.43 no.2
• /
• pp.65-70
• /
• 2020

PA(postero-anterior) and AP(antero-posterior) chest projections are the most sought-after types of all kinds of projections. But if a radiological technologist puts wrong information about the position in the computer, the orientation of left and right side of an image would be reversed. In order to solve this problem, we utilized CNN(convolutional neural network) which has recently utilized a lot for studies of medical imaging technology and rule-based system. 70% of 111,622 chest images were used for training, 20% of them were used for testing and 10% of them were used for validation set in the CNN experiment. The same amount of images which were used for testing in the CNN experiment were used in rule-based system. Python 3.7 version and Tensorflow r1.14 were utilized for data environment. As a result, rule-based system had 66% accuracy on evaluating whether the orientation reversal on chest x-ray image. But the CNN had 97.9% accuracy on that. Being overcome limitations by CNN which had been shown on rule-based system and shown the high accuracy can be considered as a meaningful result. If some problems which can occur for tasks of the radiological technologist can be separated by utilizing CNN, It can contribute a lot to optimize workflow.

• 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.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.293-294
• /
• 2007

The purpose of this study is prove the effectiveness of an energy subtraction image for the detection of pulmonary nodules and the effectiveness of multi-resolutional filter on an energy subtraction image to detect pulmonary nodules. Also we study influential factors to the accuracy of detection of pulmonary nodules from viewpoints of types of images, types of digital filters and types of evaluation methods. As one type of images, we select an energy subtraction image, which removes bones such as ribs from the conventional X-ray image by utilizing the difference of X-ray absorption ratios at different energy between bones and soft tissue. Here we select two evaluation methods and make clear the effectiveness of multi-resolutional filter on an energy subtraction image.

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.35-45
• /
• 2022

Even in recent years, treatment of first-aid patients is still often delayed due to a shortage of medical resources in marginalized areas. Research on automating the analysis of medical data to solve the problems of inaccessibility for medical services and shortage of medical personnel is ongoing. Computer vision-based medical inspection automation requires a lot of cost in data collection and labeling for training purposes. These problems stand out in the works of classifying lesion that are rare, or pathological features and pathogenesis that are difficult to clearly define visually. Anomaly detection is attracting as a method that can significantly reduce the cost of data collection by adopting an unsupervised learning strategy. In this paper, we propose methods for detecting abnormal images on chest X-RAY images as follows based on existing anomaly detection techniques. (1) Normalize the brightness range of medical images resampled as optimal resolution. (2) Some feature vectors with high representative power are selected in set of patch features extracted as intermediate-level from lesion-free images. (3) Measure the difference from the feature vectors of lesion-free data selected based on the nearest neighbor search algorithm. The proposed system can simultaneously perform anomaly classification and localization for each image. In this paper, the anomaly detection performance of the proposed system for chest X-RAY images of PA projection is measured and presented by detailed conditions. We demonstrate effect of anomaly detection for medical images by showing 0.705 classification AUROC for random subset extracted from the PadChest dataset. The proposed system can be usefully used to improve the clinical diagnosis workflow of medical institutions, and can effectively support early diagnosis in medically poor area.

• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.455-461
• /
• 2021

Cardiomegaly is one of the most common diseases seen on chest X-rays, but if it is not detected early, it can cause serious complications. In view of this, in recent years, many researches on image analysis in which deep learning algorithms using artificial intelligence are applied to medical care have been conducted with the development of various science and technology fields. In this paper, we would like to evaluate whether the Inception V3 deep learning model is a useful model for the classification of Cardiomegaly using chest X-ray images. For the images used, a total of 1026 chest X-ray images of patients diagnosed with normal heart and those diagnosed with Cardiomegaly in Kyungpook National University Hospital were used. As a result of the experiment, the classification accuracy and loss of the Inception V3 deep learning model according to the presence or absence of Cardiomegaly were 96.0% and 0.22%, respectively. From the research results, it was found that the Inception V3 deep learning model is an excellent deep learning model for feature extraction and classification of chest image data. The Inception V3 deep learning model is considered to be a useful deep learning model for classification of chest diseases, and if such excellent research results are obtained by conducting research using a little more variety of medical image data, I think it will be great help for doctor's diagnosis in future.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.4
• /
• pp.195-201
• /
• 2020

This study studied scoliosis, one of the most common modern diseases caused by lifestyle patterns of office workers sitting in front of computers all day and modern people who use smart phones frequently. Scoliosis is a typical complication that takes more than 80% of the nation's total population at least once. X-ray are used to test for these complications. X-ray, a non-destructive testing method that allows scoliosis to be easily performed and filmed in various areas such as the chest, abdomen and bone without contrast agents or other instruments. We uses NI DAQ to miniaturize digital X-ray imaging devices and image intensifier in self-shielding housing with Vision Assistant for drawing lines to the top and the bottom of the spine to acquire angles, i.e. curvature in real-time. In this way, the research was conducted to see scoliosis patients and their condition easily and to help rapid treatment for solving the problem of posture correction in modern people.

• Journal of radiological science and technology
• /
• v.28 no.4
• /
• pp.273-277
• /
• 2005

The rapid development in digital acquisition technology in radiography has not been accompanied by information regarding optimum radiolographic technique for use with an amorphus silicon flat panel detector. The purpose of our study was to compared image quality and radiation dose of an amorphus silicon flat panel detectors for digital chest radiography. All examinations were performed by using an amorphus silicon flat panel detector. Chest radiographs of an chest phantom were obtained with peak kilovoltage values of $60{\sim}150kVp$. Published data on the effect of x-ray beam energy on image quality and patient dose when using an amorphus silicon flat panel detector. It is important that radiographers are aware of optimum kVp selection for an amorphus silicon flat panel detector system, particularly for the commonly performed chest examination.

• Journal of radiological science and technology
• /
• v.16 no.2
• /
• pp.27-38
• /
• 1993

To investigate relationships between image guality and exposure dose, Chest X-ray films were evaluated for the following points:how much scattered radiation can affect reduction in image quality and can be permissible diagnostically? For this purpose using a test charts and Burger's phantoms. The visual evaluation of their X-ray films and the measurements of scattered radiation were carried out. The dose of scattered radiation ranging from 20 to 25% was found to be for nothing in any diagnostic obstacle. In this range, surface doses were low of 17, 21, and $25{\mu}Gy$ for The thickness of the chest of 15, 20 and 25 cm respectively. Comparison of these high voltage X-ray films with low voltage ones showed a surface dose rate of 1:11.7. Therefore, X-ray quality, photosensitive materials(film and screen) and grid should be selected very carefully for the purpose of reduction in exposure dose.

• Journal of radiological science and technology
• /
• v.23 no.1
• /
• pp.13-19
• /
• 2000

We have presented with the "A study on overexposure rate according to over-density in chest X-ray radiography(I)" last year. In this report, We could calculate the entrance skin dose from chest X-ray film density the formula $I_0=Ix/e^{-{\mu}x}{\times}mG$, (mG is Bucky factor) was used to deliver the skin dose. At that time, There was two problems that the Bucky factor from maker was not equal to field experience and the field size influenced on the Attenuation Rate. The experiment of Bucky factor was done from film method and retried the Attenuation Rate of Acryle phantom according to Good & Poor geometry. As the results, The Bucky factor from maker higher than in this experiments $30{\sim}40%$. The Attenuation Rate in good geometric condition brings about a little alteration compare with poor geometric condition. In the field experiment, we could get the chest image with very low entrance skin radiation dose $29.3{\mu}Sv$, especially with air gap methode, the entrance skin dose was detected $10{\mu}Sv$.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.277-285
• /
• 2023

In this study, pneumonia identification networks with the small number of layers were constructed by using chest X-ray images. The networks had similar trainable-parameters, and the performance of the trained models was quantitatively evaluated with the modification of the network architectures. A total of 6 networks were constructed: convolutional neural network (CNN), VGGNet, GoogleNet, residual network with identity blocks, ResNet with bottleneck blocks and ResNet with identity and bottleneck blocks. Trainable parameters for the 6 networks were set in a range of 273,921-294,817 by adjusting the output channels of convolution layers. The network training was implemented with binary cross entropy (BCE) loss function, sigmoid activation function, adaptive moment estimation (Adam) optimizer and 100 epochs. The performance of the trained models was evaluated in terms of training time, accuracy, precision, recall, specificity and F1-score. The results showed that the trained models with the small number of layers precisely detect pneumonia from chest X-ray images. In particular, the overall quantitative performance of the trained models based on the ResNets was above 0.9, and the performance levels were similar or superior to those based on the CNN, VGGNet and GoogleNet. Also, the residual blocks affected the performance of the trained models based on the ResNets. Therefore, in this study, we demonstrated that the object detection networks with the small number of layers are suitable for detecting pneumonia using chest X-ray images. And, the trained models based on the ResNets can be optimized by applying appropriate residual-blocks.