• The Korean Journal of Nuclear Medicine Technology
• /
• v.24 no.1
• /
• pp.15-19
• /
• 2020

Purpose Generative Adversarial Network(GAN) is one of deep learning technologies. This is a way to create a real fake image after learning the real image. In this study, after acquiring artificial intelligence images through GAN, We were compared and evaluated with real scan time images. We want to see if these technologies are potentially useful. Materials and Methods 30 patients who underwent ¹⁸F-FDG Brain PET/CT scanning at Severance Hospital, were acquired in 15-minute List mode and reconstructed into 1,2,3,4,5 and 15minute images, respectively. 25 out of 30 patients were used as learning images for learning of GAN and 5 patients used as verification images for confirming the learning model. The program was implemented using the Python and Tensorflow frameworks. After learning using the Pix2Pix model of GAN technology, this learning model generated artificial intelligence images. The artificial intelligence image generated in this way were evaluated as Mean Square Error(MSE), Peak Signal to Noise Ratio(PSNR), and Structural Similarity Index(SSIM) with real scan time image. Results The trained model was evaluated with the verification image. As a result, The 15-minute image created by the 5-minute image rather than 1-minute after the start of the scan showed a smaller MSE, and the PSNR and SSIM increased. Conclusion Through this study, it was confirmed that AI imaging technology is applicable. In the future, if these artificial intelligence imaging technologies are applied to nuclear medicine imaging, it will be possible to acquire images even with a short scan time, which can be expected to reduce artifacts caused by patient movement and increase the efficiency of the scanning room.

• Nuclear Medicine and Molecular Imaging
• /
• v.41 no.3
• /
• pp.252-254
• /
• 2007

Image fusion is fast catching attention as Wagner pointed out in his 2006 version of the recent progress and development presented at the annual meeting of Society of Nuclear Medicine. Prototypical fusion of bone scan and radiograph was already attempted at in 1961 when Fleming et al. published an article on strontium-85 bone scan. They simply superimposed dot scan on radiograph enabling simultaneous assessment of altered bone metabolism and local bone anatomy. Indeed the parallel reading of images of bone scan and radiography, CT, MRI or ultrasonography has been practiced in nuclear medicine long since. It is fortunate that recent development of computer science and technology along with the availability of refined CT and SPECT machines has permitted us to open a new avenue to digitally produce precise fusion image so that they can readily be read, exchanged and disseminated using internet. Ten years ago fusion was performed using Bresstrahlung SPECT/CT and it is now achievable by PET/CT and SPECT/CT software and SPECT/CT hardware. The merit of image fusion is its feasibility of reliable assessment of morphological and metabolic change. It is now applicable not only to stationary organs such as brain and skeleton but also to moving organs such as the heart, lung and stomach. Recently, we could create useful fusion image of cardiac SPECT and 64-channel CT angiograph. The former provided myocardial metabolic profile and the latter vascular narrowing in two patients with coronary artery stenosis and myocardial ischemia. Arterial stenosis was severe in Case 1 and mild in Case 2.

• Journal of the Korean Society of Radiology
• /
• v.13 no.5
• /
• pp.699-704
• /
• 2019

It is important to minimize the exposure dose during an examination and obtain good quality images at the same time. This study compared the beam harding effect according to the baseline superior orbito meatal line(SOML), orbito meatal line(OML), inferior orbito metal line(OML) and measured the exposure dose of the lens, especially in brain CT examinations, which generally apply to head diease patients. The beam harding effect assessment of each image along the baseline was performed quantitatively using the Image J program, and the exposure dose of the lens was detected by OSLDs and compared. As a result, As a result, when the SOML was used as the reference line, the dose of the lens was decreased by 85.08% at 80 kV and by 79.7% at 80 kV, compared to when IOML was used as the baseline. If the gantry angle at brain CT was parallel scan to SOML, there were no significant differences in the exposure to the lens and between the OML and IOML. Therefore, this study has shown that it is efficient to have a parallel scan on SOML as a protocol during Brain CT examinations.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.23 no.1
• /
• pp.69-74
• /
• 2019

Purpose $^{18}F$-FDOPA using amino acid is particularly attractive for imaging of brain tumors because of the high uptake in tumor tissue and the low uptake in normal brain tissue. But, on the other hand, $^{18}F$-FDG is highly uptake in both tumor tissue and normal brain tissue. The purpose of study is to evaluate comparison of contrasts in $^{18}F$-FDOPA Brain PET/CT and $^{18}F$-FDG Brain PET/CT and to find out optimal scan time by analysis of variation in SUV with the passage of uptake time. Materials and Methods A region of interest of approximately $350mm^2$ at the center of the tumor and cerebellum in 12 patients ($51.4{\pm}12.8yrs$) who $^{18}F$-FDG Brain PET/CT and $^{18}F$-FDOPA Brain PET/CT were examined more than once each. The $SUV_{max}$ was measured, and the $SUV_{max}$ ratio (T/C ratio) of the tumor cerebellum was calculated. In the analysis of SUV, T/C ratio was calculated for each frame after dividing into 15 frames of 2 minutes each using List mode data in 25 patients ($49.{\pm}10.3yrs$). SPSS 21 was used to compare T/C ratio of $^{18}F$-FDOPA and T/C ratio of $^{18}F$-FDG. Results The T/C ratio of $^{18}F$-FDOPA Brain PET/CT was higher than the T/C ratio of $^{18}F$-FDG Brain, and show a significant difference according to a paired t-test(t=-5.214, p=0.000). As a result of analyzing changes in $SUV_{max}$ and T/C ratio, the peak point of $SUV_{max}$ was $5.6{\pm}2.9$ and appeared in the fourth frame (6 to 8 minutes), and the peak of T/C ratio also appeared in the fourth frame (6 to 8 minutes). Taking this into consideration and comparing the existing 10 to 30 minutes image and 6 to 26 minutes image, the $SUV_{max}$ and T/C ratio increased by 0.2 and 0.1 each, compared to the 10 to 30 minutes image for 6 to 26 minutes image. Conclusion From this study, $^{18}F$-FDOPA Brain PET/CT is effective when reading the image, because the T/C ratio of $^{18}F$-FDOPA Brain PET/CT was higher than T/C ratio of $^{18}F$-FDG Brain PET/CT. In addition, in the case of $^{18}F$-FDOPA Brain PET/CT, there was no difference between the existing 10 to 30 minutes image and 6 to 26 minutes image. Through continuous research, we can find possibility of shortening examination time in $^{18}F$-FDOPA Brain PET/CT. Also, we can help physician to accurate reading using additional scan data.

• Progress in Medical Physics
• /
• v.24 no.4
• /
• pp.265-270
• /
• 2013

Correct target volume delineation is an important part of radiosurgery treatment planning process. We designed head phantom and performed target delineation to evaluate the volume differences due to radiosurgery treatment planning systems and image acquisition system, CT/MR. Delineated mean target volume from CT scan images was $2.23{\pm}0.08cm^3$ on BrainSCAN (NOVALS), $2.13{\pm}0.07cm^3$ on Leksell gamma plan (Gamma Knife) and $2.24{\pm}0.10cm^3$ on Multi plan (Cyber Knife). For MR images, $2.08{\pm}0.06cm^3$ on BrainSCAN, $1.94{\pm}0.05cm^3$ on Leksell gamma plan and $2.15{\pm}0.06cm^3$ on Multi plan. As a result, Differences of delineated mean target volume due to radiotherapy planning system was 3% to 6%. And overall mean target volume from CT scan images was 6.36% larger than those of MR scan images.

• Journal of Radiation Protection and Research
• /
• v.43 no.1
• /
• pp.1-9
• /
• 2018

Background: In this study, we investigate the image quality of virtual monochromatic images synthesized from dual-energy computed tomography (DECT) at voltages of 80/140 kV and 100/140 kV. Materials and Methods: Virtual monochromatic images of a phantom are synthesized from DECT scans from 40 to 70 keV in steps of 1 keV under the two combinations of tube voltages. The dose allocation of dual-energy (DE) scan is 50% for both low- and high-energy tubes. The virtual monochromatic images are compared to single-energy (SE) images at the same radiation dose. In the DE images, noise is reduced using the 100/140 kV scan at the optimal monochromatic energy. Virtual monochromatic images are reconstructed from 40 to 70 keV in 1-keV increments and analyzed using two quality indexes: noise and contrast-to-noise ratio (CNR). Results and Discussion: The DE scan mode with the 100/140 kV protocol achieved a better maximum CNR compared to the 80/140 kV protocol for various materials, except for adipose and brain. Image noise is reduced with the 100/140 kV protocol. The CNR values of DE with the 100/140 kV protocol is similar to or higher than that of SE at 120 kV at the same radiation dose. Furthermore, the maximum CNR with the 100/140 kV protocol is similar to or higher than that of the SE scan at 120 kV. Conclusion: It was found that the CNR achieved with the 100/140 kV protocol was better than that with the 80/140 kV protocol at optimal monochromatic energies. Virtual monochromatic imaging using the 100/140 kV protocol could be considered for application in breast, brain, lung, liver, and bone CT in accordance with the CNR results.

• Journal of the Korean Society of Radiology
• /
• v.9 no.1
• /
• pp.31-37
• /
• 2015

The cases of radiographic inspection for medical diagnosis in Korea have been continuously increasing year after year, which pays particularly more attention to CT which occupies over the half of medical radiation exposure. To find an effective alternative for reducing radiation exposure, the researchers conducted comparative experiments using some shields made of bismuth, aluminum 6mm, and silicone 22mm. These shielding materials have been used to reduce the entrance surface dose (ESD) on lenses, maintaining the CT number, noise, and uniformity in brain CT scanning which forms the largest part in CT scanning these days. These experiments showed that the doses in the spiral scan parallel to IOML and the conventional scan in Bismuth were 26.41% and 17.52%, respectively; in Aluminum 18.24% and 9.39%; in Silicone 19.47% and 14.39% lower than compared with those in the cases without any shields. In the items of the CT number, noise, and uniformity, the bismuth shield satisfied exceedingly the standards of the phantom image test while aluminum and silicone were within. To keep the graphic quality and get good shielding effect, we recommend the silicone shield which can be manufactured and purchased with ease.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.19 no.2
• /
• pp.68-73
• /
• 2015

Purpose The purpose of this study was to evaluate image quality change by truncated region in field of view (FOV) of attenuation correction computed tomography (AC-CT) in brain PET/CT. Materials and Methods Biograph Truepoint 40 with TrueV (Siemens) was used as a scanner. $^{68}Ge$ phantom scan was performed with and without applying brain holder using brain PET/CT protocol. PET attenuation correction factor (ACF) was evaluated according to existence of pallet in FOV of AC-CT. FBP, OSEM-3D and PSF methods were applied for PET reconstruction. Parameters of iteration 4, subsets 21 and gaussian 2 mm filter were applied for iterative reconstruction methods. Window level 2900, width 6000 and level 4, 200, width 1000 were set for visual evaluation of PET AC images. Vertical profiles of 5 slices and 20 slices summation images applied gaussian 5 mm filter were produced for evaluating integral uniformity. Results Patient pallet was not covered in FOV of AC-CT when without applying brain holder because of small size of FOV. It resulted in defect of ACF sinogram by truncated region in ACF evaluation. When without applying brain holder, defect was appeared in lower part of transverse image on condition of window level 4200, width 1000 in PET AC image evaluation. With and without applying brain holder, integral uniformities of 5 slices and 20 slices summation images were 7.2%, 6.7% and 11.7%, 6.7%. Conclusion Truncated region by small FOV results in count defect in occipital lobe of brain in clinical or research studies. It is necessary to understand effect of truncated region and apply appropriate accessory for brain PET/CT.

• Journal of Radiation Industry
• /
• v.12 no.4
• /
• pp.267-276
• /
• 2018

A Hoffman 3D Brain Phantom was used to evaluate two PET/CT scanners, BIO_40 and D_690, according to the radiation dose of CT (low, medium and high) at a fixed kilo-voltage-peak (kVp) with the tube current(mA) varied in 17~20 stages(Bio_40 PET/CT scanner: the tube voltage was fixed to 120 kVp, the effective tube current(mAs) was increased from 33 mAs to 190 mAs in 10 mAs increments, D_690 PET/CT scanner: the tube voltage was fixed to 140 kVp, tube current(mA) was increased from 10 mAs to 200 mAs in 10 mAs increments). After obtaining the PET image, an attenuation correction was conducted based on the attenuation map, which led to an analysis of the difference in the image. First, the ratio of white to gray matter for each scanner was examined by comparing the coefficient of variation (CV) depending on the average ratio. In addition, a blind test was carried out to evaluate the image. According to the study results, the BIO_40 and D_690 scanners showed a <1% change in CV value due to the tube current conversion. The change in the coefficients of white and gray matter showed that the Z value was negative for both scanners, indicating that the coefficient of gray matter was higher than that of white matter. Moreover, no difference was observed when the images were compared in a blind test.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.293-301
• /
• 2023

Unstandardized medical data collection and management are still being conducted manually, and studies are being conducted to classify CT data using deep learning to solve this problem. However, most studies are developing models based only on the axial plane, which is a basic CT slice. Because CT images depict only human structures unlike general images, reconstructing CT scans alone can provide richer physical features. This study seeks to find ways to achieve higher performance through various methods of converting CT scan to 2D as well as axial planes. The training used 1042 CT scans from five body parts and collected 179 test sets and 448 with external datasets for model evaluation. To develop a deep learning model, we used InceptionResNetV2 pre-trained with ImageNet as a backbone and re-trained the entire layer of the model. As a result of the experiment, the reconstruction data model achieved 99.33% in body part classification, 1.12% higher than the axial model, and the axial model was higher only in brain and neck in contrast classification. In conclusion, it was possible to achieve more accurate performance when learning with data that shows better anatomical features than when trained with axial slice alone.