• Journal of the Korean Society of Radiology
• /
• v.16 no.4
• /
• pp.453-462
• /
• 2022

In this paper, the artificial intelligence (AI) technology used in the medical image analysis field was analyzed through a literature review. Literature searches were conducted on PubMed, ResearchGate, Google and Cochrane Review using the key word. Through literature search, 114 abstracts were searched, and 98 abstracts were reviewed, excluding 16 duplicates. In the reviewed literature, AI is applied in classification, localization, disease detection, disease segmentation, and fit degree of registration images. In machine learning (ML), prior feature extraction and inputting the extracted feature values into the neural network have disappeared. Instead, it appears that the neural network is changing to a deep learning (DL) method with multiple hidden layers. The reason is thought to be that feature extraction is processed in the DL process due to the increase in the amount of memory of the computer, the improvement of the calculation speed, and the construction of big data. In order to apply the analysis of medical images using AI to medical care, the role of physicians is important. Physicians must be able to interpret and analyze the predictions of AI algorithms. Additional medical education and professional development for existing physicians is needed to understand AI. Also, it seems that a revised curriculum for learners in medical school is needed.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.3
• /
• pp.132-137
• /
• 2019

The amount of data generated from medical images is increasingly exceeding the limits of professional visual analysis, and the need for automated medical image analysis is increasing. For this reason, this study evaluated the classification and accuracy according to the presence or absence of tumor using Inception V3 deep learning model, using MRI medical images showing normal and tumor findings. As a result, the accuracy of the deep learning model was 90% for the training data set and 86% for the validation data set. The loss rate was 0.56 for the training data set and 1.28 for the validation data set. In future studies, it is necessary to secure the data of publicly available medical images to improve the performance of the deep learning model and to ensure the reliability of the evaluation, and to implement modeling by improving the accuracy of labeling through labeling classification.

• Journal of Magnetics
• /
• v.18 no.2
• /
• pp.142-149
• /
• 2013

We aim to monitor vascularization of early bone perfusion following rabbit lumbar intertransverse bone graft fusion surgery using magnetic resonance imaging assessment. Correlation with graft survival status was evaluated by histological method. Experimental animals were randomly divided into three groups and the model was established by operating bilateral lumbar intertransverse bone graft with different types of bone graft substitute material. The lumbar intertransverse area of three groups of rabbits was scanned via MRI. In addition, histological examinations were performed at the $6^{th}$ week after surgery and the quantitative analysis of the osteogenesis in different grafted area was carried out by an image analysis system. The MRI technique can be used for early postoperative evaluation of vascularized bone graft perfusion after transplantation of different bone materials, whereas histological examination allows direct visualization of the osteogenesis process.

• Journal of radiological science and technology
• /
• v.27 no.2
• /
• pp.7-12
• /
• 2004

MDCT is a useful, non-invasive, diagnostic tool in the evaluation of coronary artery disease. However, the image quality is affected by an irregular heart rhythm of the patients. Especially, premature ventricular contraction induced stair-step artifacts in the reconstruction of 2-D or 3-D images of the heart including coronary arteries. In recent, we experienced some improving of the image quality after correcting the PVC. Accordingly, the purpose of our study was to evaluate the effectiveness of the arrhythmia correction method, which was commercially available software, in improving the quality of the reconstruction images of the heart. Image analysis was performed, in consensus, by two radiologists. The scores for image quality were ranked as follows; excellent is 4 (image quality is markedly improved and is helpful in the image evaluation), good is 3 (image quality is mildly improved, but is somewhat helpful in the image evaluation), fair is 2 (image quality is improved and is not helpful in the image evaluation), and poor is 1 (image quality is not improved). We used ANOVA method to evaluate the statistical significant differences in the image qualities among the correction methods of the arrhythmia with below 0.05 of p-value. The method of moving the R-R interval showed statistically significant differences in improving of the image quality in patients with arrhythmia. We concluded that the regulation of R-R interval in patients with arrhythmia was an effective method to improve the image quality in the reconstructions of the MDCT coronary angiograms.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.1-8
• /
• 2010

Some methods employing the Active Contour Model have been widely used to extract face contour. Their performance, however, depends on the initial position of the model and the coefficients of the energy function which should be reconsidered whenever illumination and environmental condition of an input image is changed. Additionally, the number of points in the contour model should increase drastically in order to extract a fine contour. In this paper, we thus propose a novel approach which extracts face contour by segmenting the face region with threshold values obtained by a histogram analysis technique in the separated region of input image. The proposed method shows good performance under various illumination and environmental condition since it extracts face contour by considering the characteristics of the input image.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.11-19
• /
• 2022

Recently, various researches on medical image generation have been suggested, and it becomes crucial to accurately evaluate the quality and diversity of the generated medical images. For this purpose, the expert's visual turing test, feature distribution visualization, and quantitative evaluation through IS and FID are evaluated. However, there are few methods for quantitatively evaluating medical images in terms of fidelity and diversity. In this paper, images are generated by learning a chest CT dataset of non-small cell lung cancer patients through DCGAN and PGGAN generative models, and the performance of the two generative models are evaluated in terms of fidelity and diversity. The performance is quantitatively evaluated through IS and FID, which are one-dimensional score-based evaluation methods, and Precision and Recall, Improved Precision and Recall, which are two-dimensional score-based evaluation methods, and the characteristics and limitations of each evaluation method are also analyzed in medical imaging.

• Journal of Radiopharmaceuticals and Molecular Probes
• /
• v.9 no.1
• /
• pp.3-8
• /
• 2023

Parkinson's disease is a neurodegenerative disease caused by damage to brain neurons related to dopamine. Non-clinical animal models mainly used in Parkinson's disease research include drug-induced models of 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine and 6-hydroxydopamine, and genetically modified transgenic animal models. Parkinson's diagnosis can be made using brain imaging of the substantia nigra-striatal dopamine system and using a radiotracer that specifically binds to the dopamine transporter. In this study, ¹⁸F-N-(3-fluoropropyl)-2β-carboxymethoxy-3β-(4-iodophenyl) nortropane was used to confirm the image evaluation cutoff between normal and parkinson's disease models, and to confirm model persistence over time. In addition, the efficacy of single or combined administration of clinically used therapeutic drugs in parkinson's animal models was evaluated. Image analysis was performed using the PMOD software. Converted to standardized uptake value, and analyzed by standardized uptake value ratio by dividing the average value of left striatum by the average value of right striatum obtained by applying positron emission tomography images to the atlas magnetic resonance template. The image cutoff of the normal and the parkinson's disease model was calculated as SUVR=0.829, and it was confirmed that it was maintained during the test period. In the three-drug combination administration group, the right and left striatum showed a high symmetry of more than 0.942 on average and recovered significantly. Images using ¹⁸F-N-(3-fluoropropyl)-2β-carboxymethoxy-3β-(4-iodophenyl) nortropane are thought to be able to diagnose and evaluate treatment efficacy of non-clinical Parkinson's disease.

• Journal of the Korean Society of Radiology
• /
• v.11 no.7
• /
• pp.663-669
• /
• 2017

In diagnostic medical imaging, it is essential to reduce the scattered radiation for the high medical image quality and low patient dose. Therefore, in this study, the influence of the scattered radiation on medical images was analyzed as the tube voltage increases. For this purpose, ANSI chest phantom was used to measure the scattering ratio, and the scattering effect on the image quality was investigated by RMS evaluation, RSD and NPS analysis. It was found that the scattering ratio with increasing x-ray tube voltage gradually increased to 48.8% at 73 kV tube voltage and to 80.1% at 93 kV tube voltage. As a result of RMS analysis for evaluating the image quality, RMS value according to increase of tube voltage was increased, resulting in low image quality. Also, the NPS value at 2.5 lp/mm spatial frequency was increased by 20% when the tube voltage was increased by 93 kV compared to the tube voltage of 73 kV. From this study, it can be seen that the scattering radiation have a significant effect on the image quality according to the increase of x-ray tube voltage. The results of this study can be used as basic data for the improvement of medical imaging quality.

• Journal of radiological science and technology
• /
• v.43 no.3
• /
• pp.195-208
• /
• 2020

Artificial intelligence(AI) is a field of computer science that is defined as allowing computers to imitate human intellectual behavior, even though AI's performance is to imitate humans. It is grafted across software-based fields with the advantages of high accuracy and speed of processing that surpasses humans. Indeed, the AI based technology has become a key technology in the medical field that will lead the development of medical image analysis. Therefore, this article introduces and discusses the concept of deep learning-based medical imaging analysis using the principle of algorithms for convolutional neural network(CNN) and back propagation. The research cases application of the AI based medical imaging analysis is used to classify the various disease(such as chest disease, coronary artery disease, and cerebrovascular disease), and the performance estimation comparing between AI based medical imaging classifier and human experts.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.2
• /
• pp.35-41
• /
• 2017

In This Paper, We Propose the Development of a Medical Questionnaire Recognition System using Vision Technology. The Proposed System is Able to Accurately Recognize and Effectively Process a Large Number of Questionnaires used in Community Health Surveys in the Medical and Health Fields. The System Consists of Questionnaire Scanning, Answer Recognition and Error Data Processing, Result Data Verification, Image Storage and DB Construction, and Analysis of Questionnaire Results. Unlike Existing Systems, This System is Free from the Form of Questionnaires used, and Enables Accurate Recognition by Processing Various Markings and Erroneous Markings. Experimental Results Show that the Proposed System has 98.9% Recognition rate.