• Journal of Biomedical Engineering Research
• /
• v.20 no.5
• /
• pp.581-586
• /
• 1999

척추의 생체역학적 해석을 위한 유한요소기법을 이용한 컴퓨터 시뮬레이션은 척추의 손상에 대한 발생원인과 기전을 이해하고 치료의 효과를 예측하는 유용한 수단으로 기대되고 있다. 본 논문에서는 요추의 2차원 CT 영상을 이용하여 유한요소해석을 위한 척추의 3차원 모델링에 소비되는 많은 시간을 줄일 수 있도록 3차원 형상모델을 CT 형상 데이터와 형상변수를 이용, 각각 구현하는 과정을 자동화하여 이를 비교하였다.

• Journal of the Korean Society of Radiology
• /
• v.14 no.7
• /
• pp.991-1001
• /
• 2020

Supervised deep learning technologies for improving the image quality of computed tomography (CT) need a lot of training data. When input images have different characteristics with training images, the technologies cause structural distortion in output images. In this study, an imaging model based on the deep reinforcement learning (DRL) was developed for overcoming the drawbacks of the supervised deep learning technologies and reducing noise in CT images. The DRL model was consisted of shared, value and policy networks, and the networks included convolutional layers, rectified linear unit (ReLU), dilation factors and gate rotation unit (GRU) in order to extract noise features from CT images and improve the performance of the DRL model. Also, the quality of the CT images obtained by using the DRL model was compared to that obtained by using the supervised deep learning model. The results showed that the image accuracy for the DRL model was higher than that for the supervised deep learning model, and the image noise for the DRL model was smaller than that for the supervised deep learning model. Also, the DRL model reduced the noise of the CT images, which had different characteristics with training images. Therefore, the DRL model is able to reduce image noise as well as maintain the structural information of CT images.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.119-126
• /
• 2023

Sarcopenia is not well known enough to be classified as a disease in 2021 in Korea, but it is recognized as a social problem in developed countries that have entered an aging society. The diagnosis of sarcopenia follows the international standard guidelines presented by the European Working Group for Sarcopenia in Older People (EWGSOP) and the d Asian Working Group for Sarcopenia (AWGS). Recently, it is recommended to evaluate muscle function by using physical performance evaluation, walking speed measurement, and standing test in addition to absolute muscle mass as a diagnostic method. As a representative method for measuring muscle mass, the body composition analysis method using DEXA has been formally implemented in clinical practice. In addition, various studies for measuring muscle mass using abdominal images of MRI or CT are being actively conducted. In this paper, we develop an AI image segmentation model based on abdominal images of CT with a relatively short imaging time for the diagnosis of sarcopenia and describe the multicenter validation. We developed an artificial intelligence model using U-Net that can automatically segment muscle, subcutaneous fat, and visceral fat by selecting the L3 region from the CT image. Also, to evaluate the performance of the model, internal verification was performed by calculating the intersection over union (IOU) of the partitioned area, and the results of external verification using data from other hospitals are shown. Based on the verification results, we tried to review and supplement the problems and solutions.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.11
• /
• pp.305-310
• /
• 2021

Artificial intelligence technology in the medical field initially focused on analysis and algorithm development, but it is gradually changing to web application development for service as a product. This paper describes a Urinary Stone segmentation model in abdominal CT images and an artificial intelligence web application based on it. To implement this, a model was developed using U-Net, a fully-convolutional network-based model of the end-to-end method proposed for the purpose of image segmentation in the medical imaging field. And for web service development, it was developed based on AWS cloud using a Python-based micro web framework called Flask. Finally, the result predicted by the urolithiasis segmentation model by model serving is shown as the result of performing the AI web application service. We expect that our proposed AI web application service will be utilized for screening test.

• Journal of Korea Multimedia Society
• /
• v.9 no.8
• /
• pp.1086-1094
• /
• 2006

The CT is all relation knowledge and technology which are applied to make the culture contents. Recently demand regarding the CT is increasing rapidly with a great growth and high technology of culture contents industry. In this paper we suggest a CT technology valuation model for promoting R & D results and technical diffusion of the CT. Also, It is shown how to derive a value of the CT using simulation. For it, we study a classification and distinctive characteristics of the CT. And this paper reviews the methods of technology valuation that have been developed by valuation specialists.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.5
• /
• pp.331-337
• /
• 2023

In this paper, we propose a deep learning model to detect lumbar 3 (L3) CT images to determine the occurrence and degree of sarcopenia. In addition, we would like to propose an optimization technique that uses oversampling ratio and class weight as design parameters to address the problem of performance degradation due to data imbalance between L3 level and non-L3 level portions of CT data. In order to train and test the model, a total of 150 whole-body CT images of 104 prostate cancer patients and 46 bladder cancer patients who visited Gangneung Asan Medical Center were used. The deep learning model used ResNet50, and the design parameters of the optimization technique were selected as six types of model hyperparameters, data augmentation ratio, and class weight. It was confirmed that the proposed optimization-based L3 level extraction model reduced the median L3 error by about 1.0 slices compared to the control model (a model that optimized only 5 types of hyperparameters). Through the results of this study, accurate L3 slice detection was possible, and additionally, we were able to present the possibility of effectively solving the data imbalance problem through oversampling through data augmentation and class weight adjustment.

• Journal of radiological science and technology
• /
• v.37 no.3
• /
• pp.203-209
• /
• 2014

Usefulness and clinical availability for surgery efficiency were evaluated by conducting pre-operative planning with a model manufactured by desktop 3D printer by using clavicle CT image. The patient-customized clavicle fracture model was manufactured by desktop 3D printer of FDM wire laminated processing method by converting the CT image into STL file in Open Source DICOM Viewer Osirix. Also, the model of the original shape before damaged was restored and manufactured by Mirror technique based on STL file of not fractured clavicle of the other side by using the symmetry feature of the human body. For the model, the position and size, degree of the fracture was equally printed out. Using the clavicle model directly manufactured with low cost and less time in Department of Radiology is considered to be useful because it can reduce secondary damage during surgery and increase surgery efficiency with Minimal invasive percutaneous plate osteosynthesis(MIPO).

• Journal of the Korean Society of Radiology
• /
• v.13 no.2
• /
• pp.305-311
• /
• 2019

In this study, present the most useful delay scan time by statistical analysis of SUVm data for 30 suspected pancreatic cancer patients. Two statistical analysis and a mathematical model was applied to the theoretical formula by glucose and insulin mechanics, and a mathematical model was created. Statistical analysis was performed via Metlab p/g. Optimal delay scan time was suggested by Metlab p/g for the change of SUV value over time.In this study, for diagnosis pancreatic cancer by dual time point PET/CT, propose optimal delay scan time 131.5 minuts. The proposed delay scan time showed statistical reliability applicable to the diagnosis of pancreatic cancer (p<0.05). Delayed scanning with the suggested delay scan time of 131.5 minutes is considered to be useful for the diagnosis of pancreatic cancer compared to general PET / CT scan.hen the delayed test is performed with the proposed delay scan time 131.5 minuts, Compared with general PET/CT scans.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.51-61
• /
• 2004

In the dental field, the 3D tooth model in which each tooth can be manipulated individually is an essential component for the simulation of orthodontic surgery and treatment. To reconstruct such a tooth model from CT slices, we need to define the accurate boundary of each tooth from CT slices. However, the global threshold method, which is commonly used in most existing 3D reconstruction systems, is not effective for the tooth segmentation in the CT image. In tooth CT slices, some teeth touch with other teeth and some are located inside of alveolar bone whose intensity is similar to that of teeth. In this paper, we propose an image segmentation algorithm based on B-spline curve fitting to produce smooth tooth regions from such CT slices. The proposed algorithm prevents the malfitting problem of the B-spline algorithm by providing accurate initial tooth boundary for the fitting process. This paper proposes an optimal threshold scheme using the intensity and shape information passed by previous slice for the initial boundary generation and an efficient B-spline fitting method based on genetic algorithm. The test result shows that the proposed method detects contour of the individual tooth successfully and can produce a smooth and accurate 3D tooth model for the simulation of orthodontic surgery and treatment.

• The Journal of the Korea Contents Association
• /
• v.12 no.9
• /
• pp.270-279
• /
• 2012

This paper explores CT findings of a rabbit brain infection model injected with Escherichia coli and investigates the changes in Hounsfield unit (HU) of arterial blood over time. The brain infection model was produced by injecting E. coli $1{\times}10^7$ CFU/ml, 0.1 ml through the burr hole in the calvarium; 2~3 mm in depth from the dura mater, and contrast-enhanced CT, dynamic CT and arterial blood CT images were gained. It was found that various brain infections such as brain abscess, ventriculitis and meningitis. The CT image of brain abscess showed a typical pattern which the peripheral area was strongly contrast-enhanced while the center was weakly contrast-enhanced. The CT image of ventriculitis showed a strong contrast-enhancement along the lateral ventricle wall, and the CT image of meningitis showed a strong contrast-enhancement in the area between the telencephalon and the diencephalon. In dynamic CT images, the HU value of the infection core before injecting contrast medium was $31.01{\pm}3.55$. By 10 minutes after the injection, the value increased gradually to $40.36{\pm}3.76$. The HU value in the areas of the marginal rim where was hyper-enhanced showed $47.23{\pm}3.12$ before contrast injection, and it increased to $63.59{\pm}3.31$ about 45 seconds after the injection. In addition, the HU value of the normal brain tissue opposite to the E. coli. injected brain was $39.01{\pm}3.24$ before the injection, but after the contrast injection, the value increased to $49.01{\pm}4.29$ in about 30 seconds, and then it showed a gradual decline. In the arterial blood CT, the HU value before the contrast injection was $87.78{\pm}6.88$, and it increased dramatically between 10 to 30 seconds until it reached a maximum value of $749.13{\pm}98.48$. Then it fell sharply to $467.85{\pm}62.98$ between 30 seconds to 45 seconds and reached a plateau by 60 seconds. Later, the value showed a steady decrease and indicated $188.28{\pm}25.03$ at 20 minutes. Through this experiment, it was demonstrated that the brain infection model can be produced by injecting E. coli., and the characteristic of the infection model can be well observed with contrast-enhanced CT scan. The dynamic CT scan showed that the center of the infection was gradually contrast-enhanced, whereases the peripheral area was rapidly contrast-enhanced and then slowly decreased. As for arterial blood, it increased significantly between 10 seconds to 30 seconds after the contrast medium injection and decreased gradually after reaching a plateau.