• Journal of Biomedical Engineering Research
• /
• 제42권3호
• /
• pp.100-106
• /
• 2021

Measuring Intima-media thickness (IMT) with ultrasound images can help early detection of coronary artery disease. As a result, numerous machine learning studies have been conducted to measure IMT. However, most of these studies require several steps of pre-treatment to extract the boundary, and some require manual intervention, so they are not suitable for on-site treatment in urgent situations. in this paper, we propose to use deep learning networks U-Net, Attention U-Net, and Pretrained U-Net to automatically segment the intima-media complex. This study also applied the HE, HS, and CLAHE preprocessing technique to wireless portable ultrasound diagnostic device images. As a result, The average dice coefficient of HE applied Models is 71% and CLAHE applied Models is 70%, while the HS applied Models have improved as 72% dice coefficient. Among them, Pretrained U-Net showed the highest performance with an average of 74%. When comparing this with the mean value of IMT measured by Conventional wired ultrasound equipment, the highest correlation coefficient value was shown in the HS applied pretrained U-Net.

• Journal of the Korean Society of Radiology
• /
• 제16권1호
• /
• pp.67-75
• /
• 2022

The aim of this study is to establish a new QC method that can simultaneously evaluate the resolution of the x/y plane and the z-axis by producing a phantom that can reflect exposure and reconstruction parameter of MDCT system. It was used with Aquilion ONE(Cannon Medical System, Otawara, Japan), and the examination was scanned using of 120 kV, 260 mA, and the D-FOV of 300 mm². It produced new SSP phantom modules in which two aluminum plates inclined at 45° to a vertical axis and a transverse axis to evaluate high contrast resolution of x/y plane and z axis. And it changed factors such as the algorithm, distance from gantry iso-center. All images were reconstructed in five steps from 0.6 mm to 10.0 mm slice thickness to measure resolution of x/y plane and z-axis. The image data measured FWHM and FWTM using Profile tool of Aquarius iNtusion Edition ver. 4.4.13 P6 software(Terarecon, California, USA), and analysed SPQI and signal intensity by ImageJ program(v1.53n, National Institutes of Health, USA). It decreased by 4.09~11.99%, 4.12~35.52%, and 4.70~37.64% in slice thickness of 2.5 mm, 5.0 mm, and 10.0 mm for evaluating the high contrast resolution of x/y plane according to distance from gantry iso-center. Therefore, the high contrast resolution of the x/y plane decreased when the distance from the iso-center increased or the slice thickness increased. Additionally, the slice thicknesses of 2.5 mm, 5.0 mm, and 10.0 mm with a high algorithm increased 74.83, 15.18 and 81.25%. The FWHM was almost constant on the measured SSP graph for evaluating the accuracy of slice thickness which represents the resolution of x/y plane and z-axis, but it was measured to be higher than the nominal slice thickness set by user. The FWHM and FWTM of z-axis with axial scan mode tended to increase significantly as the distance increased from gantry iso-center than the helical mode. Particularly, the thinner slice thickness that increased error range compare with the nominal slice thickness. The SPQI increased with thick slice thickness, and that was closer to 90% in the helical scan than the axial scan. In conclusion, by producing a phantom suitable for MDCT detectors and capable of quantitative resolution evaluation, it can be used as a specific method in the management of research quality and management of outdated equipment. Thus, it is expected to contribute greatly to the discrimination of lesions in the field of CT imaging.

• Journal of radiological science and technology
• /
• 제29권4호
• /
• pp.241-247
• /
• 2006

Recently, interests and utilization on Computed Radiography(CR) and Digital Radiography(DR) tends to increase owing to an introduction of Picture Archiving and Communication System(PACS) and an accuracy control of special medical equipment for a breast imaging examination. This study was intended to compare and analyze a detector's imaging quality by each system to be used for the breast imaging examination by using ACR Phantom used at the accuracy control. As an evaluation method, a significance and reliability of image's value using the ACR Phantom was analyzed by using SPSS program. The results are followed. 1. For the fiber, there was 3.9 score in Screen-Film, 4.2 score in CR($50{\mu}m$), 3.2 score in CR($100{\mu}m$), and 4.2 score in DR. There was the high score in the order of CR($50{\mu}m$), DR, Screen-Film, and CR($100{\mu}m$)(P<0.05). 2. For the calcification, there was 2.7 score in Screen-Film, 2.5 score in CR($50{\mu}m$), 2.0 score in CR($100{\mu}m$), and 2.9 score in DR. There was the high score in the order of DR, Screen-Film, CR($50{\mu}m$), and CR($100{\mu}m$).(0.025(P<0.05). 3. For Mass, there was 3.8 score in Screen-Film, 3.8 score in CR($50{\mu}m$), 3.6 score in CR($100{\mu}m$), and 4.5 score in DR. There was the high score in the order of DR, CR($50{\mu}m$), Screen-Film, and CR($100{\mu}m$) (P<0.1). 4. As the total score, there was 10.4 score in Screen-Film, 10.6 score in CR($50{\mu}m$), 8.7 score in CR($100{\mu}m$), and 11.3 score in DR. There was the high score in the order of DR, $CR(50{\mu}m$), Screen-Film, and $CR(100{\mu}m$). As shown in the above results, it can be known that DR and Screen-Film System has higher image quality than CR. But, DR has unstability caused by element, and Screen-Film has the low image quality caused by artifact as disadvantages. When Dual-Side CR($50{\mu}m$) was used among CR systems which had the problem of low image quality, it was indicated that there was no difference with Screen-Film System. Because the radiation imaging examination tends to become digitalized, each system for the breast imaging examination will need to be developed and supplemented.

• Journal of the Korean Society of Radiology
• /
• 제2권4호
• /
• pp.11-25
• /
• 2008

As breast cancer shows the highest incidence among women's cancers, the use of mammography is also increasing as a screening test. Mammography should produce high-quality images for accurate diagnosis. For this, it is necessary to manage the performance and image quality of mammography. Thus, in order to investigate quality control, the present study conducted a questionnaire survey of 37 hospitals registered as breast cancer medical examination centers in Gwang-Ju, concerning their quality control of mammography. In the results of surveying the characteristics of apparatus use for mammography, many respondents did not know about the equipment that they were using. Of the hospitals, 19 (49%) were using film, 19 (49%) CR, and 1 DR. In the results of asking how to do quality control, only 38% answered that they inspected according to the manual. In addition, all the surveyed hospitals had specialized agencies do quality control for them. As to the reason for using agencies, 65% mentioned limitations in personnel, time, distance, etc, and 44% mentioned the absence of machines and materials. These results suggest that quality control is being performed perfunctorily, as well as passively and indifferently as it relies on specialized agencies. Accordingly, it is necessary to provide regular education for enhancing people's perception of quality control and to perform quality control adequately in the presence of Radiologist.

• Journal of the Korean Society of Radiology
• /
• 제11권7호
• /
• pp.619-625
• /
• 2017

The sudy was intended to evaluate the optimal equipment selection by quantitatively assessing the SNR(signal to noise ratio) and CNR(contrast to noise ratio) on the abdominal organ. This study performed on 1.5 T and 3.0 T MRI units focusing on HASTE, HASTE(f/s) and FFE(in of phase), FFE(out of phase) without using the contrast medium(Gadolinium). The data analysis was performed by randomly selecting on 1.5 T and 3.0 T abdominal MRI images. As a results, SNR and CNR values of 3.0 T is higher than 1.5 T at liver, kidney and spleen(p<0.05). Stomach, abdominal fat and pancreas was obtained a higher value at 1.5 T(p<0.05). On conclusion, the organs of outer part in the body showed generally a high value at 3.0 T, and the organs of inner part in the body including the gas showed a high value at 3.0 T because of a large difference on magnetic susceptibility.

• Journal of the Korean Society of Radiology
• /
• 제10권4호
• /
• pp.285-290
• /
• 2016

The purpose of our study was to retrospectively evaluate the cause of a decreased calcium score of follow-up studies on coronary artery calcium scores (CACs) computed tomography (CT). The subjects were healthy 100 people(85 males $60.6{\pm}6.9$ years, 15 females $67.2{\pm}7.3$ years). The subjects decreased CACs were divided into 4 subgroups depending on Agatston classification, minimal (1-10), mild (11-100), moderate (101-400), severe (400<). As a result of decreased CACs were scan location disagreement 51%, motion artifact 26%, equipment changes 14%, operator mistakes 5%, input miss 2%, image loss 1%, arrhythmia 1%. In the mild group, the most common decreased CACs were 49 people. In the minimal group, the most significant variation reduction has occurred to 6 people. Scan location disagreement was considered a partial volume effects due to the scan starting position. It showed less than 100 CACs a high variation (19.7%) in more than 100 CACs, a lower variation (2.2%), these could be seen that the variation range is different that can be tolerated according to the calcification score. Motion artifact factor was found in 26%, which is so closely related to the preceding tests that affect the higher heart rate like this pulmonary function test, exercise stress test.

• Journal of the Korea Society of Computer and Information
• /
• 제27권12호
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.

• The Journal of Korean Society for Radiation Therapy
• /
• 제29권2호
• /
• pp.101-108
• /
• 2017

Purpose: The proton used in proton therapy has a characteristic of giving a small dose to the normal tissue in front of the tumor site while forming a Bragg peak at the cancer tissue site and giving up the maximum dose and disappearing immediately. It is very important to verify the proton arrival position. In this study, we used the off-line PET CT method to measure the distribution of positron emitted from nucleons such as 11C (half-life = 20 min), 150 (half-life = 2 min) and 13N The range and distal falloff point of the proton were verified by measurement. Materials and Methods: In the IEC 2001 Body Phantom, 37 mm, 28 mm, and 22 mm spheres were inserted. The phantom was filled with water to obtain a CT image for each sphere size. To verify the proton range and distal falloff points, As a treatment planning system, SOBP were set at 46 mm on 37 mm sphere, 37 mm on 28 mm, and 33 mm on 22 mm sphere for each sphere size. The proton was scanned in the same center with a single beam of Gantry 0 degree by the scanning method. The phantom was scanned using PET-CT equipment. In the PET-CT image acquisition method, 50 images were acquired per minute, four ROIs including the spheres in the phantom were set, and 10 images were reconstructed. The activity profile according to the depth was compared to the dose profile according to the sphere size established in the treatment plan Results: The PET-CT activity profile decreased rapidly at the distal falloff position in the 37 mm, 28 mm, and 22 mm spheres as well as the dose profile. However, in the SOBP section, which is a range for evaluating the range, the results in the proximal part of the activity profile are different from those of the dose profile, and the distal falloff position is compared with the proton therapy plan and PET-CT As a result, the maximum difference of 1.4 mm at the 50 % point of the Max dose, 1.1 mm at the 45 % point at the 28 mm sphere, and the difference at the 22 mm sphere at the maximum point of 1.2 mm were all less than 1.5 mm in the 37 mm sphere. Conclusion: To maximize the advantages of proton therapy, it is very important to verify the range of the proton beam. In this study, the proton range was confirmed by the SOBP and the distal falloff position of the proton beam using PET-CT. As a result, the difference of the distally falloff position between the activity distribution measured by PET-CT and the proton therapy plan was 1.4 mm, respectively. This may be used as a reference for the dose margin applied in the proton therapy plan.

• Journal of the Korea Computer Graphics Society
• /
• 제30권3호
• /
• pp.189-198
• /
• 2024

Research combining deep learning-based models and physical simulations is making important advances in the medical field. This extracts the necessary information from medical image data and enables fast and accurate prediction of deformation of the skeleton and soft tissue based on physical laws. This study proposes a system that integrates Neural Radiance Fields (NeRF), Position-Based Dynamics (PBD), and Parallel Resampling to generate 3D volume data, and deform and visualize them in real-time. NeRF uses 2D images and camera coordinates to produce high-resolution 3D volume data, while PBD enables real-time deformation and interaction through physics-based simulation. Parallel Resampling improves rendering efficiency by dividing the volume into tetrahedral meshes and utilizing GPU parallel processing. This system renders the deformed volume data using ray casting, leveraging GPU parallel processing for fast real-time visualization. Experimental results show that this system can generate and deform 3D data without expensive equipment, demonstrating potential applications in engineering, education, and medicine.

• The Journal of Korean Society for Radiation Therapy
• /
• 제27권1호
• /
• pp.73-78
• /
• 2015

Purpose : Under the assumption of change to the amplitude based sorting, the study will use four dimensional computed tomography imaging (4DCT) arrayed using the phase based sorting to analyze the respiratory phase difference. Materials and Methods : The study analyzed the 4DCT (4-dimensional computed tomography) images of 10 liver cancer patients that were treated with respiratory gated radiotherapy from 2015 February to March. Using RPM respiratory gating (RPM 1.7.5, Varian, USA) equipment, imaging according to respiratory cycle of phase based sorting was acquired and using a treatment planning system (Pinnacle 9.2, Philips, USA) the acquired imaging according to respiratory cycle was used to measure the abdominal movement value by respiratory cycle. The measuring point was the point where the center point of the Marker Block and the body surface met in the 50% phase image and here the coordinate values Lateral, Vertical, Longitudinal (X, Y, Z) were set as reference points, and on the X, Z plane identical to the reference point, using the identical method the Y axis coordinate value of each 0%, 30%, 40%, 50%, 60%, 80% phase images were acquired to quantitatively measure the variation of distance to the Y axis. The abdominal movement value according to respiration was applied to the theoretical model that the value decreases linearly from maximum inhalation to maximum exhalation to divide the variation of my value to predict as amplitude value by respiratory cycle and conversely the variation in amplitude was recalculated with the phase variation deviation value to analyze. Results : The deviation value between expected value and actual location was the largest in the 30% phase with 0.24 cm, and standard deviation was also the largest in 30% phase with 0.13 cm. The effective value of the deviation value derived from the average of the deviation squared value of each patient appeared as minimum 0.7 cm, maximum 0.18 cm, average 0.12 cm, and standard deviation 0.4 cm. Also by dividing the actual movement distance value with the peak expiration value then converting it into %Phase, the deviation value with actual phase 16.5% in 30% phase, 10.0% and 40% phase, 10.0% and 60% phase, 15.4% and 80% phase, and overall average about 13%, and arraying based on amplitude, phase shift occurred and further it was from peak expiration the chance of deviation occurrence was increasingly measured. Conclusion : Based on the results of the study there were differences between value acquired based on theoretical model and actual value. Therefore in respiratory gated radiotherapy using external surrogates, there needs to be establishment of respiration gated radiation system that avoids the combination of two Sorting methods considering that there will be occurrence of treatment and corresponding clinical differences due to the phase difference that occur due to the Amplitude based Phase Sorting.