• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.11
• /
• pp.169-172
• /
• 1996

In this paper, we present the evaluation of signal to noise ratio(SNR) and images of Magnetic resonance imaging system which is underdevelopement. For the evaluation of such parameters, we used two different phantoms, one for SNR and image homogeneity, and the other is for the slice thickness measurement. Further, comparison with other leading MR systems may be needed for the better image quality assessment.

• Korean Journal of Radiology
• /
• v.22 no.6
• /
• pp.983-993
• /
• 2021

Objective: To investigate the image quality of ultralow-dose CT (ULDCT) of the chest reconstructed using a cycle-consistent generative adversarial network (CycleGAN)-based deep learning method in the evaluation of pulmonary tuberculosis. Materials and Methods: Between June 2019 and November 2019, 103 patients (mean age, 40.8 ± 13.6 years; 61 men and 42 women) with pulmonary tuberculosis were prospectively enrolled to undergo standard-dose CT (120 kVp with automated exposure control), followed immediately by ULDCT (80 kVp and 10 mAs). The images of the two successive scans were used to train the CycleGAN framework for image-to-image translation. The denoising efficacy of the CycleGAN algorithm was compared with that of hybrid and model-based iterative reconstruction. Repeated-measures analysis of variance and Wilcoxon signed-rank test were performed to compare the objective measurements and the subjective image quality scores, respectively. Results: With the optimized CycleGAN denoising model, using the ULDCT images as input, the peak signal-to-noise ratio and structural similarity index improved by 2.0 dB and 0.21, respectively. The CycleGAN-generated denoised ULDCT images typically provided satisfactory image quality for optimal visibility of anatomic structures and pathological findings, with a lower level of image noise (mean ± standard deviation [SD], 19.5 ± 3.0 Hounsfield unit [HU]) than that of the hybrid (66.3 ± 10.5 HU, p < 0.001) and a similar noise level to model-based iterative reconstruction (19.6 ± 2.6 HU, p > 0.908). The CycleGAN-generated images showed the highest contrast-to-noise ratios for the pulmonary lesions, followed by the model-based and hybrid iterative reconstruction. The mean effective radiation dose of ULDCT was 0.12 mSv with a mean 93.9% reduction compared to standard-dose CT. Conclusion: The optimized CycleGAN technique may allow the synthesis of diagnostically acceptable images from ULDCT of the chest for the evaluation of pulmonary tuberculosis.

• 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.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.746-754
• /
• 1996

Grading and sorting fresh cut flowers are time consuming process. In Korea, cut flowers are sorted mostly by human inspection due to the lack of adequate machinery. In this paper, quality evaluation factors of cut flowers are discussed, and types of sorting machines existing in the market are introduced . Aspects of computer image processing in evaluation the quality of cut flowers are also discussed.

• Journal of the Korean Society of Radiology
• /
• v.16 no.7
• /
• pp.889-896
• /
• 2022

This study attempted to evaluate the usefulness of the air mattress by analyzing the subjective comfort of the patient due to the application of the air mattress to the table of computed tomography through a questionnaire and analyzing the change in image quality through quantitative and qualitative evaluation of the patient's clinical images. The subjects who participated in the study were 221 men and 229 women, and the age range was from 18 to 86. To evaluate the change in image quality, a total of 150 patients, 50 patients per group, were selected for quantitative evaluation, and 20 patients per group, a total of 60 patients were selected for qualitative evaluation. As a result of this study, the subjective comfort of patients increased due to air mattresses, and there was no difference in image quality as a result of quantitative and qualitative evaluation of clinical images. From the above results, it is believed that the air mattress can be usefully applied in a way that can increase the subjective comfort of the patient without any harm to the diagnostic image.

• Journal of radiological science and technology
• /
• v.38 no.3
• /
• pp.187-197
• /
• 2015

This study analysed the effectiveness of aluminium(Al) filter in the added compound filtration for the removal of characteristic radiation by energy spectrum and image evaluation. 0.1, 0.2, 0.3 mm copper with and without 1 mm Al were evaluated. The energy spectrum was measured using the GATE and evaluated separately by each energy. Image quality was evaluated by PSNR, MAE, MSE, CNR, SNR and qualitative analysis was performed by seven items for resolution and contrast from chest x-ray criteria of National Cancer Screening and Cardiovascular evaluation table. In the analysis of the quality of the energy per photon spectrum with the exception of a low energy region, without Al were superior in all area. PSNR MAE, MSE, CNR, SNR and qualitative analysis were the same or slightly better. PSNR was over 30 dB and all significant and the p>0.05 in the T-test of qualitative analysis. The energy spectrum and image quality have little difference between before and after use of Al filter. Therefore, it is effective to use the Al filter for the radiation dose management with the compensation capability of DR system.

• Journal of Biomedical Engineering Research
• /
• v.44 no.2
• /
• pp.118-124
• /
• 2023

Many recent studies have reported that the quality of input learning data was vital to the detection of regions of interest. However, due to a lack of research on the quality of learning data on lesion detetcting using gastroscopy, we aimed to quantify the impact of quality difference in endoscopic images to lesion detection models using Image Quality Assessment (IQA) algorithms. Through IQA methods such as BRISQUE (Blind/Referenceless Image Spatial Quality Evaluation), Laplacian Score, and PSNR (Peak Signal-To-Noise) algorithm on 430 sheets of high quality data (HQD) and 430 sheets of low quality data (PQD), we showed that there were significant differences between high and low quality images in lesion detecting through BRISQUE and Laplacian scores (p<0.05). The PSNR value showed 10.62±1.76 dB on average, illustrating the lower lesion detection performance of PQD than HQD. In addition, F1-Score of HQD showed higher detection performance at 77.42±3.36% while F1-Score of PQD showed 66.82±9.07%. Through this study, we hope to contribute to future gastroscopy lesion detection assistance systems that involve IQA algorithms by emphasizing the importance of using high quality data over lower quality data.

• Journal of radiological science and technology
• /
• v.33 no.4
• /
• pp.341-348
• /
• 2010

By accessing the current status of FPD system use in the hospitals located in Seoul and Gyeonggi Province as well as the entrance skin dose and the image quality evaluation realized by C-D Phantom, and the image assessment by the medical professionals regarding the radiography for the extremity, the following results were derived. 1. According to the evaluation made in the actual use of FPD system (12 machines), the grid ratio varied from 8:1 to 13:1, and 6 machines used the grid ratio with 12:1, realizing the largest number. Among the machines, there were 8 machines that allowed a removable grid while 3 machines did use a removable grid (25.0%). 2. When it came to the equipments used for the experiment, it showed that the amount of the entrance skin dose increased from 4.13 times up to 4.79 times with the grid use. 3. The difference in the entrance skin dose depending on the changes in the exposure condition(0.5times or 2.0times) was not significantly different regardless of the patients' thickness. 4. In terms of the image quality depending on C-D Phantom, the grid use was distinguished well. However, the images were well distinguishable as the exposure condition got increased. 5. In the clinical assessment, the grid use was less effective for the Hand PA, which was considered to shoot a thin body part. It was evaluated that the grid use was preferred for the Knee AP, which was shooting for a relatively thick body part. Nonetheless, 3 out of 5 people said that they would not use the grid if the entrance skin dose to reduced.

• Journal of radiological science and technology
• /
• v.43 no.5
• /
• pp.343-351
• /
• 2020

This study analyzed dose reduction and quality of images through dose reduction tools and shielding board to protect sensitive eye lens in radiation during orbit CT examinations for clinical data use. During CT scans of the phantom, surface dose (CT scanner dosimetry phantom, ion chamber-3 times) and quality of image (radiosurgery head phantom, visual assessment-2 times, HU standard deviation) were evaluated using X-care which is dose reduction tools and bismuth shielding board. The results of experiments of eight conditions showed a relatively reduced dose in all other conditions compared to when no conditions were set. In particular, the area corresponding to the ophthalmic part reduced the surface dose by up to 45.7 %. The visual evaluation of images by specialists and the quality evaluation of images analyzed by HU standard deviation were clinically closest to the use of X-care and shielding board (1 cm in height). Therefore, it is believed that the use of shielding board in a suitable location with dose reduction tools while investigating the optimal radiation dose will reduce the exposure dose of sensitive lens at radiation while maintaining the quality of the images with high diagnostic value.

• Imaging Science in Dentistry
• /
• v.40 no.1
• /
• pp.15-23
• /
• 2010

Purpose : This study was designed to compare the effective doses from low-dose and standard-dose multi-detector CT (MDCT) scanning protocols and evaluate the image quality and the spatial resolution of the low-dose MDCT protocols for clinical use. Materials and Methods : 6-channel MDCT scanner (Siemens Medical System, Forschheim, Germany), was used for this study. Protocol of the standard-dose MDCT for the orthodontic analysis was 130 kV, 35 mAs, 1.25 mm slice width, 0.8 pitch. Those of the low-dose MDCT for orthodontic analysis and orthodontic surgery were 110 kV, 30 mAs, 1.25 mm slice width, 0.85 pitch and 110 kV, 45 mAs, 2.5 mm slice width, 0.85 pitch. Thermoluminescent dosimeters (TLDs) were placed at 31 sites throughout the levels of adult female ART head and neck phantom. Effective doses were calculated according to ICRP 1990 and 2007 recommendations. A formalin-fixed cadaver and AAPM CT performance phantom were scanned for the evaluation of subjective image quality and spatial resolution. Results : Effective doses in ${\mu}Sv$ ($E_{2007}$) were 699.1, 429.4 and 603.1 for standard-dose CT of orthodontic treatment, low-dose CT of orthodontic analysis, and low-dose CT of orthodontic surgery, respectively. The image quality from the low-dose protocol were not worse than those from the standard-dose protocol. The spatial resolutions of both standard-dose and low-dose CT images were acceptable. Conclusion : From the above results, it can be concluded that the low-dose MDCT protocol is preferable in obtaining CT images for orthodontic analysis and orthodontic surgery.