• Korean Journal of Radiology
• /
• 제24권4호
• /
• pp.294-304
• /
• 2023

Objective: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. Materials and Methods: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. Results: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). Conclusion: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

• The Korean Journal of Nuclear Medicine Technology
• /
• 제28권1호
• /
• pp.35-40
• /
• 2024

Purpose: To improve the image quality in positron emission tomography (PET), the attenuation correction technique based on the computed tomography (CT) data is important process. However, the artifact is caused by metal material during PET/CT scan, and the image quality is degraded. Therefore, the purpose of this study was to evaluate image quality according to with and without iterative metal artifact reduction (iMAR) algorithm using customized 3D printing phantom. Materials and Methods: The Hoffman and Derenzo phantoms were designed. To protect the gamma ray transmission and express the metal portion, lead substance was located to the surface. The SiPM based PET/CT was used for acquisition of PET images according to application with and without iMAR algorithm. The quantitative methods were used by signal to noise ratio (SNR), coefficient of variation (COV), and contrast to noise ratio (CNR). Results and Discussion: The results shows that the image quality applying iMAR algorithm was higher 1.15, 1.19, and 1.11 times than image quality without iMAR algorithm for SNR, COV, and CNR. Conclusion: In conclusion, the iMAR algorithm was useful for improvement of image quality by reducing the metal artifact lesion.

• Journal of Korea Multimedia Society
• /
• 제15권12호
• /
• 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.

• Journal of the Korea Society of Computer and Information
• /
• 제24권3호
• /
• pp.41-47
• /
• 2019

In this paper, we propose a application of conditional generative adversarial network (cGAN) for generation of contrast enhanced computed tomography (CT) image. Two types of CT data which were the enhanced and non-enhanced were used and applied by the histogram equalization for adjusting image intensities. In order to validate the generation of contrast enhanced CT data, the structural similarity index measurement (SSIM) was performed. Prepared generated contrast CT data were analyzed the statistical analysis using paired sample t-test. In order to apply the optimized algorithm for the lymph node cancer, they were calculated by short to long axis ratio (S/L) method. In the case of the model trained with CT data and their histogram equalized SSIM were $0.905{\pm}0.048$ and $0.908{\pm}0.047$. The tumor S/L of generated contrast enhanced CT data were validated similar to the ground truth when they were compared to scanned contrast enhanced CT data. It is expected that advantages of Generated contrast enhanced CT data based on deep learning are a cost-effective and less radiation exposure as well as further anatomical information with non-enhanced CT data.

• Progress in Medical Physics
• /
• 제23권4호
• /
• pp.292-302
• /
• 2012

The patient dose in advanced radiotherapy techniques is an important issue. These methods should be evaluated to reduce the dose in diagnostic imaging for radiotherapy. Especially, the Computed Tomography in radiotherapy has been used widely; hence the CT was evaluated for dose and image in this study. The evaluations for dose and image were done in equal condition due to compare the dose and image simultaneously. Furthermore, the possibility of dose and image evaluations by using the Monte Carlo simulation MCNPX was confirmed. We made the iterative reconstruction for low dose CT image to elevate image quality with Maximum Likelihood Expectation Maximization; MLEM. The system we developed is expected to be used not only to reduce the patient dose in radiotherapy, also to evaluate the overall factors of image modalities in industrial research.

• The Korean Journal of Nuclear Medicine Technology
• /
• 제27권1호
• /
• pp.47-54
• /
• 2023

Purpose PET-CT imaging require an appropriate quality assurance system to achieve high efficiency and reliability. Quality control is essential for improving the quality of care and patient safety. Currently, there are performance evaluation methods of UN2-1994 and UN2-2001 proposed by NEMA and IEC for PET-CT image evaluation. In this study, we compare phantom images with the same experiments before and after PET-CT 3D normalization and well counter correction and evaluate the usefulness of quality control. Materials and methods Discovery 690 (General Electric Healthcare, USA) PET-CT equiptment was used to perform 3D normalization and well counter correction as recommended by GE Healthcare. Based on the recovery coefficients for the six spheres of the NEMA IEC Body Phantom recommended by the EARL. 20kBq/㎖ of ¹⁸F was injected into the sphere of the phantom and 2kBq/㎖ of ¹⁸F was injected into the body of phantom. PET-CT scan was performed with a radioacitivity ratio of 10:1. Images were reconstructed by appliying TOF+PSF+TOF, OSEM+PSF, OSEM and Gaussian filter 4.0, 4.5, 5.0, 5.5, 6.0, 6,5 mm with matrix size 128×128, slice thickness 3.75 mm, iteration 2, subset 16 conditions. The PET image was attenuation corrected using the CT images and analyzed using software program AW 4.7 (General Electric Healthcare, USA). The ROI was set to fit 6 spheres in the CT image, RC (Recovery Coefficient) was measured after fusion of PET and CT. Statistical analysis was performed wilcoxon signed rank test using R. Results Overall, after the quality control items were performed, the recovery coefficient of the phantom image increased and measured. Recovery coefficient according to the image reconstruction increased in the order TOF+PSF, TOF, OSEM+PSF, before and after quality control, RCmax increased by OSEM 0.13, OSEM+PSF 0.16, TOF 0.16, TOF+PSF 0.15 and RCmean increased by OSEM 0.09, OSEM+PSF 0.09, TOF 0.106, TOF+PSF 0.10. Both groups showed a statistically significant difference in Wilcoxon signed rank test results (P value<0.001). Conclusion PET-CT system require quality assurance to achieve high efficiency and reliability. Standardized intervals and procedures should be followed for quality control. We hope that this study will be a good opportunity to think about the importance of quality control in PET-CT

• Korean Journal of Digital Imaging in Medicine
• /
• 제9권1호
• /
• pp.21-30
• /
• 2007

Our objective was to evaluate the CT attenuation coefficient and noise of spatial domain filtering as an alternative to additional image reconstruction using different kernels in abdominal CT. Derived from thin collimated source images was generated using abdomen B10 (very smooth), B20 (smooth), B30 (medium smooth), B40 (medium), B50 (medium sharp), B60 (sharp), B70 (very sharp) and B80 (ultra sharp) kernels. Quantitative CT coefficient and noise measurements provided comparable HU (hounsfield) units in this respect. CT attenuation coefficient (mean HU) values in the abdominal were 60.4$\sim$62.2 HU and noise (7.6$\sim$63.8 HU) in the liver parenchyma. In the stomach a mean (CT attenuation coefficient) of -2.2$\sim$0.8 HU and noise (10.1$\sim$82.4 HU) was measured. Image reconstructed with a convolution kernel led to an increase in noise, whereas the results for CT attenuation coefficient were comparable. Image medications of image sharpness and noise eliminate the need for reconstruction using different kernels in the future. CT images increase the diagnostic accuracy may be controlled by adjusting CT various kernels, which should be adjusted to take into account the kernels of the CT undergoing the examination.

• Journal of the Korean Society of Radiology
• /
• 제10권1호
• /
• pp.45-51
• /
• 2016

The purpose of this study was tried to remove the noise and improve the spatial resolution in the computed tomography (CT) by using anisotropic 2-dimensional (2D) diffusion based filter. We used 4-channel multi-detector CT and american association of physicists in medicine (AAPM) phantom was used for CT performance evaluation to evaluate the image quality. X-ray irradiation conditions for image acquisition was fixed at 120 kVp, 100 mAs and scanned 10 mm axis with ultra-high resolution. The improvement of anisotropic 2D diffusion filtering that we suggested firstly, increase the contrast of the image by using histogram stretching to the original image for 0.4%, and multiplying the individual pixels by 1.2 weight value, and applying the anisotropic diffusion filtering. As a result, we could distinguished five holes until 0.75 mm in the original image but, five holes until 0.40 mm in the image with improved anisotropic diffusion filter. The noise of the original image was 46.0, the noise of the image with improved anisotropic 2D diffusion filter was decreased to 33.5(27.2%). In conclusion improved anisotropic 2D diffusion filter that we proposed could remove the noise of the CT image and improve the spatial resolution.

• The Journal of the Korea institute of electronic communication sciences
• /
• 제10권6호
• /
• pp.713-720
• /
• 2015

As the hand-held mobile devices are widely used, they are recently coming into convergence with medical diagnostic systems. Furthermore, the wireless mobile Internet and the various kinds of communication devices are rapidly coming into wide use converging with medical technology. The mobile communication environments can make people get more health care services beyond space and time. In this paper, we implement and evaluate the mobile client and the medical diagnostic information server for transmitting, searching and updating the medical diagnostic information. The DICOM CT image and the compressed JPEG 2000 CT image are statistically evaluated by t-test performance whether those images are clinically appropriate. In the case of the DICOM CT image, we realize that the average value is relatively more appropriate to the clinical diagnosis than the JPEG 2000 CT image.

• Journal of radiological science and technology
• /
• 제41권6호
• /
• pp.595-602
• /
• 2018

Quality control (QC) of Computed Tomography (CT) devices is based on image quality measurement on AAPM CT phantom which is a standard phantom. Although it is possible to control the accuracy of the CT apparatus, it is expensive and has a disadvantage of low penetration rate. Therefore, in this study, we make image quality measurement phantom at low cost using FFF (Fused Filament Fabrication) type three-dimensional printer and try to analyze the usefulness, compare it with existing standard phantom. To print a phantom, We used three-dimensional printer of the FFF system and PLA (Poly Lactic Acid, density: $1.24g/cm^3$) filament, and the CT device of 64 MDCT (Aquilion CX, Toshiba, Japan). In addition, we printed a phantom using three-dimensional printer after design using various tool based on existing standard phantom. For image quality evaluation, AAPM CT phantom and self-generated phantom were measured 10 times for each block. The measured data were analyzed for significance using the Mannwhiteney U-test of SPSS (Version 22.0, SPSS, Chicago, IL, USA). As a result of the analysis, phantom fabricated with three-dimensional printer and standard phantom showed no significant difference (p>0.05). Furthermore, we confirmed that image quality measurement performance of a phantom using three-dimensional printer is similar to the existing standard phantom. In conclusion, we confirmed the possibility of low cost phantom fabrication using three dimensional printer.