• Journal of Korea Multimedia Society
• /
• v.15 no.12
• /
• pp.1442-1448
• /
• 2012

The problem of Metal Area Segmentation (MAS) in X-ray CT images is a very hard task because of metal artifacts. This research features a practical yet effective method for MAS in X-ray CT images that exploits both projection image and reconstructed image spaces. We employ the Relevant Neighbor Area (RNA) idea [1] originally developed for projection image inpainting in order to create a novel feature in the projection image space that distinctively represents metal and near-metal pixels with opposite signs. In the reconstructed result of the feature image, application of a simple thresholding technique provides accurate segmentation of metal areas due to nice separation of near-metal areas from metal areas in its histogram.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.28.2-28
• /
• 2001

Three dimensional shape measurement techniques are widely needed in industries for product quality monitoring and control. X-ray imaging method is a promising technology to achieve three-dimensional Information, both the surface and inner structure of an object, since it can overcome the limitations of conventional visual or optical methods such as an occlusion problem or surface reflection properties. In this paper, we propose three dimensional volume reconstruction method based on x-ray stereo imaging technology. Here, the stereo images of an object from two different views are taken by changing the object pose rather than moving imaging plane as in conventional stereo vision method. We propose a series of image processing techniques to extract the features efficiently from x-ray images, where the occluded features in case of normal camera vision could be found ...

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.51-58
• /
• 2023

In this paper, we propose an organ segmentation technique for the automatic extraction of medical diagnostic indicators from X-ray images. In order to calculate diagnostic indicators of heart disease and spinal disease such as VHS(vertebral heart scale) and Cobb angle, it is necessary to accurately segment the thoracic spine, carina, and heart in a chest X-ray image. A deep neural network model in which the high-resolution representation of the image for each layer and the structure converted into a low-resolution feature map are connected in parallel was adopted. This structure enables the relative position information in the image to be effectively reflected in the segmentation process. It is shown that learning performance can be improved by combining the OCR module, in which pixel information and object information are mutually interacted in a multi-step process, and the channel attention module, which allows each channel of the network to be reflected as different weight values. In addition, a method of augmenting learning data is presented in order to provide robust performance against changes in the position, shape, and size of the subject in the X-ray image. The effectiveness of the proposed theory was evaluated through an experiment using 145 human chest X-ray images and 118 animal X-ray images.

• 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.

• 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 Biomedical Engineering Research
• /
• v.26 no.5
• /
• pp.295-300
• /
• 2005

We introduce an x-ray micro tomography system capable of high resolution imaging of a local region inside a small animal. By combining two kinds of projection data, one from a full field-of-view (FOV) scan of the whole body and the other from a limited FOV scan of the region of interest, we have obtained zoomed-in images of the region of interest without any contrast a nomalies. We have integrated a micro tomography system using a micro-focus x-ray source, a $1248\times1248$ flat-panel x-ray detector, and a precision scan mechanism. Using the cross-sectional images taken with the zoom-in micro tomography system, we measured trabecular thicknesses of femur bones in postmortem rats. To compensate the limited spatial resolution in the zoom-in micro tomography images, we used the fuzzy distance transform for the calculation of the trabecular thickness. To validate the trabecular thickness measurement with the zoom-in micro tomography images, we compared the measurement results with the ones obtained from the conventional micro tomography images of the extracted bone samples.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1134-1139
• /
• 2019

One of the most important applications of computer vision algorithms is the detection of threat objects in x-ray security images. However, in the practical setting, this task is complicated by two properties inherent to the dataset, namely, the problem of class imbalance and visual complexity. In our previous work, we resolved the class imbalance problem by using a GAN-based anomaly detection to balance out the bias induced by training a classification model on a non-practical dataset. In this paper, we propose a new method to alleviate the visual complexity problem by using a KNN-based automatic cropping algorithm to remove distracting and irrelevant information from the x-ray images. We use the cropped images as inputs to our current model. Empirical results show substantial improvement to our model, e.g. about 3% in the practical dataset, thus further outperforming previous approaches, which is very critical for security-based applications.

• Journal of Biomedical Engineering Research
• /
• v.10 no.3
• /
• pp.243-252
• /
• 1989

In this study, medical images, which are X-ray image and CT image, are compressed by the adam live coding technique. The medical images may be treated as special ones, because they are different from general images in many respects. The statistical characteristics that medical images only have in transform domain are analyzed, and then the improved quantization method is proposed for medical images. For chest X-ray image and CT head image, the better results are obtained by the improved adaptive coding technique.

• Journal of the Korean Society of Visualization
• /
• v.5 no.2
• /
• pp.33-38
• /
• 2007

Water management in polymer electrolyte fuel cell (PEFC) has been receiving large attention as an important issue in practical applications. Proper water management is vital to achieve high performance and durability of PEFC. In this study, an X-ray imaging technique was employed to visualize the water distribution in a PEFC quantitatively. X-ray images of the PEFC components with and without water were distinguished clearly. From the visualized X-ray images, we could evaluate the water distribution in the region between separator and gas diffusion layer (GDL) quantitatively. In addition, the contact angle of water in the micro-channels was also clearly visualized.

• Journal of the Korean Society of Radiology
• /
• v.15 no.2
• /
• pp.153-158
• /
• 2021

X-ray image analysis is a very important field to improve the early diagnosis rate and prediction accuracy of periodontal disease. Research on the development and application of artificial intelligence-based algorithms to improve the quality of such dental X-ray images is being widely conducted worldwide. Thus, the aim of this study was to design a super-resolution algorithm for predicting periodontal disease and to evaluate its applicability in dental X-ray images. The super-resolution algorithm was constructed based on the convolution layer and ReLU, and an image obtained by up-sampling a low-resolution image by 2 times was used as an input data. Also, 1,500 dental X-ray data used for deep learning training were used. Quantitative evaluation of images used root mean square error and structural similarity, which are factors that can measure similarity through comparison of two images. In addition, the recently developed no-reference based natural image quality evaluator and blind/referenceless image spatial quality evaluator were additionally analyzed. According to the results, we confirmed that the average similarity and no-reference-based evaluation values were improved by 1.86 and 2.14 times, respectively, compared to the existing bicubic-based upsampling method when the proposed method was used. In conclusion, the super-resolution algorithm for predicting periodontal disease proved useful in dental X-ray images, and it is expected to be highly applicable in various fields in the future.