• Korean Journal of Radiology
• /
• v.24 no.4
• /
• 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.

• Journal of the Korean Society of Radiology
• /
• v.84 no.1
• /
• pp.240-252
• /
• 2023

Purpose To assess the effect of deep learning image reconstruction (DLIR) for head CT in pediatric patients. Materials and Methods We collected 126 pediatric head CT images, which were reconstructed using filtered back projection, iterative reconstruction using adaptive statistical iterative reconstruction (ASiR)-V, and all three levels of DLIR (TrueFidelity; GE Healthcare). Each image set group was divided into four subgroups according to the patients' ages. Clinical and dose-related data were reviewed. Quantitative parameters, including the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), and qualitative parameters, including noise, gray matter-white matter (GM-WM) differentiation, sharpness, artifact, acceptability, and unfamiliar texture change were evaluated and compared. Results The SNR and CNR of each level in each age group increased among strength levels of DLIR. High-level DLIR showed a significantly improved SNR and CNR (p < 0.05). Sequential reduction of noise, improvement of GM-WM differentiation, and improvement of sharpness was noted among strength levels of DLIR. Those of high-level DLIR showed a similar value as that with ASiR-V. Artifact and acceptability did not show a significant difference among the adapted levels of DLIR. Conclusion Adaptation of high-level DLIR for the pediatric head CT can significantly reduce image noise. Modification is needed while processing artifacts.

• Korean Journal of Radiology
• /
• v.22 no.11
• /
• pp.1850-1857
• /
• 2021

Objective: The purpose of this study was to assess whether a deep learning (DL) algorithm could enable simultaneous noise reduction and edge sharpening in low-dose lumbar spine CT. Materials and Methods: This retrospective study included 52 patients (26 male and 26 female; median age, 60.5 years) who had undergone CT-guided lumbar bone biopsy between October 2015 and April 2020. Initial 100-mAs survey images and 50-mAs intraprocedural images were reconstructed by filtered back projection. Denoising was performed using a vendor-agnostic DL model (ClariCT.AI^TM, ClariPI) for the 50-mAS images, and the 50-mAs, denoised 50-mAs, and 100-mAs CT images were compared. Noise, signal-to-noise ratio (SNR), and edge rise distance (ERD) for image sharpness were measured. The data were summarized as the mean ± standard deviation for these parameters. Two musculoskeletal radiologists assessed the visibility of the normal anatomical structures. Results: Noise was lower in the denoised 50-mAs images (36.38 ± 7.03 Hounsfield unit [HU]) than the 50-mAs (93.33 ± 25.36 HU) and 100-mAs (63.33 ± 16.09 HU) images (p < 0.001). The SNRs for the images in descending order were as follows: denoised 50-mAs (1.46 ± 0.54), 100-mAs (0.99 ± 0.34), and 50-mAs (0.58 ± 0.18) images (p < 0.001). The denoised 50-mAs images had better edge sharpness than the 100-mAs images at the vertebral body (ERD; 0.94 ± 0.2 mm vs. 1.05 ± 0.24 mm, p = 0.036) and the psoas (ERD; 0.42 ± 0.09 mm vs. 0.50 ± 0.12 mm, p = 0.002). The denoised 50-mAs images significantly improved the visualization of the normal anatomical structures (p < 0.001). Conclusion: DL-based reconstruction may enable simultaneous noise reduction and improvement in image quality with the preservation of edge sharpness on low-dose lumbar spine CT. Investigations on further radiation dose reduction and the clinical applicability of this technique are warranted.

• The Korean Journal of Nuclear Medicine
• /
• v.39 no.1
• /
• pp.49-56
• /
• 2005

Purpose: Dedicated animal PET is useful equipment for the study of new PET tracer. recently, microPET R4 was installed in the Korea institute of radiology and medical science. In this study, we measured the characteristics of scanner. Materials and methods: Resolution was measured using a line source (F-18:65 ${\mu}Ci$, inner diameter: 0.5 mm). The line source was put in the axial direction and was moved from the center of field of view to outside with 1 mm interval. PET images were reconstructed using a filtered back-protection and ordered subset expectation maximization. line source (16.5 ${\mu}Ci$, 78 mm) was put on the tenter of axial direction to measure the sensitivity when the deadtime was under 1%. Images were acquired during 4 minutes respectively from center to 39 mm outward. Delayed count was subtracted from total count and then decay was corrected for the calculation of sensitivity. Noise equivalent count ratio and scatter fraction were calculated using cylindrical phantom. Results: Spatial resolution of reconstructed image using filtered back-projection was 1.86 mm(radial), 1.95 mm(tangential), 1.95 mm(axial) in the tenter of field of view, and 2.54 mm, 2.8 mm, 1.61 mm in 2 cm away from the center respectively. Sensitivity was 2.36% at the center of transaxial field of view. Scatter fraction was 20%. Maximal noise equivalent count ratio was 66.4 kcps at 242 kBq/mL. Small animal images were acquired for confirmation of performance. Conclusion: Performance characteristics of microPET R4 were similar with reported value. So this will be a useful tool for small animal imaging.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.15 no.2
• /
• pp.65-71
• /
• 2011

Purpose: The recently adopted multiple confocal SPECT SYSTEM (hereinafter called IQ SPECT$^{TM}$) has a high difference from the conventional myocardial perfusion SPECT in the collimator form, image capture method, and image reconstruction method. This study was conducted to compare this novice equipment with the conventional one to design a protocol meeting the IQ SPECT, and also determine the characteristics and usefulness of IQ SPECT. Materials and Methods: 1. For the objects of LEHR (Low energy high resolution) collimator and Multiple confocal collimator, $^{99m}Tc$ 37MBq was put in the acrylic dish then each sensitivity ($cpm/{\mu}Ci$) was measured at the distance of 5 cm, 10 cm, 20 cm, 30 cm, and 40 cm respectively. 2. Based on the sensitivity measure results, IQ SPECT Protocol was designed according to the conventional general myocardial SPECT, then respectively 278 kBq/mL, 7.4 kBq/mL, and 48 kBq/mL of $^{99m}Tc$ were injected into the myocardial and soft tissues and liver site by using the anthropomorphic torso phantom then the myocardial perfusion SPECT was run. 3. For the comparison of FWHMs (Full Width at Half Maximum) resulted from the image reconstruction of LEHR collimator, the FWHMs (mm) were measured with only algorithms changed, in the case of the FBP (Filtered Back projection) method- a reconstruction method of conventional myocardial perfusion SPECT, and the 3D OSEM (Ordered subsets expectation maximization) method of IQ SPECT, by using $^{99m}Tc$ Line source. Results: 1. The values of IQ SPECT collimator sensitivity ($cpm/{\mu}Ci$) were 302, 382, 655, 816, 1178, and those of LEHR collimator were measured as 204, 204, 202, 201, 198, both at the distance of 5 cm, 10 cm, 20 cm, 30 cm, and 40 cm respectively. It was found the difference of sensitivity increases up to 4 times at the distance of 30 cm in the cases of IQ SPECT and LEHR. 2. The myocardial perfusion SPECT Protocol was designed according to the geometric characteristics of IQ SPECT based on the sensitivity results, then the phantom test for the aforesaid protocol was conducted. As a result, it was found the examination time can be reduced 1/4 compared to the past. 3. In the comparison of FWHMs according to the reconstructed algorithm in the FBP method and 3D OSEM method followed after the SEPCT test using a LEHR collimator, the result was obtained that FWHM rose around twice in the 3D OSEM method. Conclusion : The IQ SPECT uses the Multiple confocal collimator for the myocardial perfusion SPECT to enhance the sensitivity and also reduces examination time and contributes to improvement of visual screen quality through the myocardial-specific geometric image capture method and image reconstruction method. Due to such benefits, it is expected patients will receive more comfortable and more accurate examinations and it is considered a further study is required using additional clinical materials.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.16 no.1
• /
• pp.12-16
• /
• 2012

Purpose : In conventional PET image reconstruction, iterative reconstruction methods such as OSEM (Ordered Subsets Expectation Maximization) have now generally replaced traditional analytic methods such as filtered back-projection. This includes improvements in components of the system model geometry, fully 3D scatter and low noise randoms estimates. SharpIR algorithm is to improve PET image contrast to noise by incorporating information about the PET detector response into the 3D iterative reconstruction algorithm. The aim of this study is evaluation of SharpIR reconstruction method in PET/CT. Materials and Methods: For the measurement of detector response for the spatial resolution, a capillary tube was filled with FDG and scanned at varying distances from the iso-center (5, 10, 15, 20 cm). To measure image quality for contrast recovery, the NEMA IEC body phantom (Data Spectrum Corporation, Hillsborough, NC) with diameters of 1, 13, 17 and 22 for simulating hot and 28 and 37 mm for simulating cold lesions. A solution of 5.4 kBq/mL of $^{18}F$-FDG in water was used as a radioactive background obtaining a lesion of background ratio of 4.0. Images were reconstructed with VUE point HD and VUE point HD using SharpIR reconstruction algorithm. For the clinical evaluation, a whole body FDG scan acquired and to demonstrate contrast recovery, ROIs were drawn on a metabolic hot spot and also on a uniform region of the liver. Images were reconstructed with function of varying iteration number (1~10). Results: The result of increases axial distance from iso-center, full width at half maximum (FWHM) is also increasing in VUE point HD reconstruction image. Even showed an increasing distances constant FWHM. VUE point HD with SharpIR than VUE point HD showed improves contrast recovery in phantom and clinical study. Conclusion: By incorporating more information about the detector system response, the SharpIR algorithm improves the accuracy of underlying model used in VUE point HD. SharpIR algorithm improve spatial resolution for a line source in air, and improves contrast recovery at equivalent noise levels in phantoms and clinical studies. Therefore, SharpIR algorithm can be applied as through a longitudinal study will be useful in clinical.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.17 no.1
• /
• pp.18-24
• /
• 2013

Purpose: Myocardial perfusion SPECT using $^{201}Tl$ is an important method for viability of left ventricle and quantitative evaluation of cardiac function and now various reconstruction methods are used to improve the image quality. But in case of small sized heart, you should always be careful because of the Partial Volume Effect which may cause errors of quantitative indices at the reconstruction step. So, In this study, we compared those quantitative indices of left ventricle according to the reconstruction method of myocardial perfusion SPECT with the Echocardiography and verified the degree of the differences between them. Materials and Methods: Based on ESV 30 mL of Echocardiography, we divided 278 patients (male;98, female;188, Mean age;$65.5{\pm}11.1$) who visited the Asan medical center from February to September, 2012 into two categories; below the criteria to small sized heart, otherwise, normal or large sized heart. Filtered and output each case, we applied the method of FBP and OSEM to each of them, and calculated EDV, ESV and LVEF, and we conducted statistical processing through Repeated Measures ANOVA with indices that measured in Echocardiography. Results: In case of men and women, there were no significant difference in EDV between FBP and OSEM (p=0.053, p=0.098), but in case of Echocardiography, there were meaningful differences (p<0.001). The change of ESV especially women in small sized heard, significant differences has occurred among FBP, OSEM and Echocardiography. Also, in LVEF, there were no difference in men and women who have normal sized heart among FBP, OSEM and Echocardiography (p=0.375, p=0.969), but the women with small sized heart have showed significant differences (p<0.001). Conclusion: The change in quantitative indices of left ventricle between Nuclear cardiology image reconstruction, no difference has occurred in the patients with normal sized heart but based on ESV, under 30 mL of small sized heart, especially in female, there were significant differences in FBP, OSEM and Echocardiography. We found out that overestimated LVEF caused by PVE can be reduced in average by applying OSEM to all kinds of gamma camera, which are used in analyzing the differences.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.16 no.2
• /
• pp.29-34
• /
• 2012

Purpose : Presently, hardwares and softwares for reducing radiation exposure are continually developed for PET/CT examination. Purpose of this study is to evaluate effectiveness of reducing radiation exposure dose of CT and SUV changes of PET when applied each kernel to ACCT (Attenuation Correction Computed Tomography) according to adopted IRIS (Iterative Reconstruction in Image Space) software. Materials and Methods : Biograph mCT (Siemens, Germany) was used as a PET/CT scanner. Using AAPM CT performance phantom, from standard (120 kVp, 100 mAs), 7 scans were conducted by reducing 15 mAs each. After image reconstruction by FBP (Filtered Back Projection) and IRIS, noise and spatial resolution were evaluated. The same method was applied to anthropomorphic chest phantom and acquired images were compared. NEMA IEC body phantom was used for SUV evaluation. Injected dose rate for hot sphere (hot) and background cylinder (BKG) were 1:8. CT dose condition (120 kVp, 50 mAs) was the same for each scan and PET scan durations were 1, 2, 3 and 4min. After scanning, each kernel of IRIS was applied to ACCT. And PET images were reconstructed by ACCT adopted IRIS for comparing SUV changes. Results : AAPM phantom test for noise evaluation, SD for FBP 100 mAs, IRIS 55 mAs were 8.8 and 8.9. FBP 85 mAs, IRIS 40 mAs were 9.5 and 9.7. FBP 70 mAs, IRIS 25 mAs were 11.9 and 11.1. Above mAs condition for FBP and IRIS, SD showed similar values. And for spatial resolution test, there was no significant difference. For chest phantom test, when applied the same mAs and kernel to both of FBP and IRIS, every applied kernels showed reduced noise. Lower mAs and higher kernel value showed higher noise reduction. There was no considerable difference only except for I70 very sharp kernel for SUV comparison using NEMA IEC body phantom. Conclusion : In this study, low mAs (55 mAs) applied IRIS and standard mAs (100 mAs) applied FBP showed similar noise. And only except for I70 kernel, there was no significant SUV changes. It is possible to reduce needless radiation exposure and acquire better image quality than FBP's through applying appropriate kernel of IRIS to PET/CT.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.15 no.1
• /
• pp.94-100
• /
• 2011

Purpose: Basal/Acetazolamide-challenged brain perfusion SPECT is very useful to assess cerebral perfusion and vascular reserve. However, as there is a trade off between sensitivity and spatial resolution in the selection of collimator, the selection of optimal collimator is crucial. In this study, we examined three collimators to select optimal one for 1-day brain perfusion SPECT. Materials and Methods: Three collimators, low energy high resolution-parallel beam (LEHR-par), ultra resolution-fan beam (LEUR-fan) and super fine-fan beam (LESFR-fan), were tested for 1-day imaging using Triad XLT 9 (TRIONIX). The SPECT images of Hoffman 3D brain phantom filled with 99mTc of 170 MBq and a normal volunteer were acquired with a protocol of 50 kcts/frame and detector rotation of 3 degree. Filterd backprojection (FBP) reconstruction with Butterworth filter (cut off frequencies, 0.3 to 0.5) was performed. The quantitative and qualitative assessments for three collimators were performed. Results: The blind tests showed that LESFR-fan provided the best image quality for Hoffman brain phantom and the volunteer. However, images for all the collimator were evaluated as 'acceptable'. On the other hand, in order to meet the equivalent signal-to-noise ratio (SNR), total acquisition time or radioactivity dose for LESFR-fan must have been increased up to almost twice of that for LEUR-fan and LEHR-par. The volunteer test indicated that total acquisition time could be reduced approximately by 10 to 14 min in clinical practice using LEUR-fan and LEHR-par without significant loss on image quality, in comparison with LESFR-fan. Conclusion: Although LESFR-fan provides the best image quality, it requires significantly more acquisition time than LEUR-fan and LEHR-par to provide reasonable SNR. Since there is no significant clinical difference between three collimators, LEUR-fan and LEHR-par can be recommended as optimal collimators for 1-day brain perfusion imaging with respect to image quality and SNR.

• Progress in Medical Physics
• /
• v.24 no.4
• /
• pp.253-258
• /
• 2013

The purpose of this study is to evaluate and analyze the relationship between the external radiation dose reconstruction which is transmitted from the patient who receives radiation treatment through electronic portal imaging device (EPID) and the internal dose derived from the Monte Carlo simulation. As a comparative analysis of the two cases, it is performed to provide a basic indicator for similar studies. The geometric information of the experiment and that of the radiation source were entered into Monte Carlo n-particle (MCNPX) which is the computer simulation tool and to derive the EPID images, a tally card in MCNPX was used for visualizing and the imaging of the dose information. We set to source to surface distance (SSD) 100 cm for internal measurement and EPID. And the water phantom was set to be 100 cm of the source to surface distance (SSD) for the internal measurement and EPID was set to 90 cm of SSD which is 10 cm below. The internal dose was collected from the water phantom by using mesh tally function in MCNPX, accumulated dose data was acquired by four-portal beam exposures. At the same time, after getting the dose which had been passed through water phantom, dose reconstruction was performed using back-projection method. In order to analyze about two cases, we compared the penetrated dose by calibration of itself with the absorbed one. We also evaluated the reconstructed dose using EPID and partially accumulated (overlapped) dose in water phantom by four-portal beam exposures. The sum dose data of two cases were calculated as each 3.4580 MeV/g (absorbed dose in water) and 3.4354 MeV/g (EPID reconstruction). The result of sum dose match from two cases shows good agreement with 0.6536% dose error.