• Journal of the Korean Society of Radiology
• /
• v.18 no.1
• /
• pp.37-44
• /
• 2024

Even though MR can reveal excellent soft-tissue contrast and functional information, CT is also required for electron density information for accurate dose calculation in Radiotherapy. For the fusion of MRI and CT images in RT treatment planning workflow, patients are normally scanned on both MRI and CT imaging modalities. Recently deep-learning-based generations of CT images from MR images became possible owing to machine learning technology. This eliminated CT scanning work. This study implemented a CycleGan deep-learning-based CT image generation from MR images. Three CT generators whose learning is based on T1- , T2- , or T1-&T2-weighted MR images were created, respectively. We found that the T1-weighted MR image-based generator can generate better than other CT generators when T1-weighted MR images are input. In contrast, a T2-weighted MR image-based generator can generate better than other CT generators do when T2-weighted MR images are input. The results say that the CT generator from MR images is just outside the practical clinics and the specific weight MR image-based machine-learning generator can generate better CT images than other sequence MR image-based generators do.

• Nuclear Engineering and Technology
• /
• v.51 no.6
• /
• pp.1610-1615
• /
• 2019

Positron emission tomography (PET)/magnetic resonance (MR) scanning has the advantage of less additional exposure to radiation than does PET/computed tomography (CT). In particular, MR based attenuation correction (MR AC) can greatly affect the image quality of PET and is frequently obtained using various MR sequences. Thus, the purpose of the current study was to quantitatively compare the image quality between MR non-AC (MR NAC) and MR AC in PET images with three MR sequences. Percent image uniformity (PIU), percent contrast recovery (PCR), and percent background variability (PBV) were estimated to evaluate the quality of PET images with MR AC. Based on the results of PIU, 15.2% increase in the average quality was observed for PET images with MR AC than for PET images with MR NAC. In addition, 28.6% and 71.1% improvement in the average results of PCR and PBV respectively, was observed for PET images with MR AC compared with that with MR NAC. Moreover, no significant difference was observed among the average values using three MR sequences. In conclusion, the current study demonstrated that PET with MR AC improved the image quality and can be help diagnosis in all MR sequence cases.

• Journal of Korean Neurosurgical Society
• /
• v.47 no.3
• /
• pp.203-209
• /
• 2010

Objective : The purpose of study was to evaluate the feasibility of brain magnetic resonance (MR) images of the rat obtained using a 1.5T MR machine in several blood-brain barrier (BBB) experiments. Methods : Male Sprague-Dawley rats were used. MR images were obtained using a clinical 1.5T MR machine. A microcatheter was introduced via the femoral artery to the carotid artery. Normal saline (group 1, n = 4), clotted autologous blood (group 2, n = 4), triolein emulsion (group 3, n = 4), and oleic acid emulsion (group 4, n = 4) were infused into the carotid artery through a microcatheter. Conventional and diffusion-weighted images, the apparent coefficient map, perfusion-weighted images, and contrast-enhanced MR images were obtained. Brain tissue was obtained and triphenyltetrazolium chloride (TTC) staining was performed in group 2. Fluorescein isothiocyanate (FITC)-labeled dextran images and endothelial barrier antigen (EBA) studies were performed in group 4. Results : The MR images in group 1 were of good quality. The MR images in group 2 revealed typical findings of acute cerebral infarction. Perfusion defects were noted on the perfusion-weighted images. The MR images in group 3 showed vasogenic edema and contrast enhancement, representing vascular damage. The rats in group 4 had vasogenic edema on the MR images and leakage of dextran on the FITC-labeled dextran image, representing increased vascular permeability. The immune reaction was decreased on the EBA study. Conclusion : Clinical 1.5T MR images using a rat depicted many informative results in the present study. These results can be used in further researches of the BBB using combined clinical MR machines and immunohistochemical examinations.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.16 no.2
• /
• pp.68-80
• /
• 2012

Purpose : More recently, combined PET/MR scanners have been developed in which the MR data can be used for both anatometabolic image formation and attenuation correction of the PET data. For quantitative PET information, correction of tissue photon attenuation is mandatory. The attenuation map is obtained from the CT scan in the PET/CT. In the case of PET/MR, the attenuation map can be calculated from the MR image. The purpose of this study was to assess the quantitative differences between MR-based and CT-based attenuation corrected PET images. Materials and Methods : Using the uniform cylinder phantom of distilled water which has 199.8 MBq of $^{18}F$-FDG put into the phantom, we studied the effect of MR-based and CT-based attenuation corrected PET images, of the PET-CT using time of flight (TOF) and non-TOF iterative reconstruction. The images were acquired from 60 minutes at 15-minute intervals. Region of interests were drawn over 70% from the center of the image, and the Scanners' analysis software tools calculated both maximum and mean SUV. These data were analyzed by one way-anova test and Bland-Altman analysis. MR images are segmented into three classes(not including bone), and each class is assigned to each region based on the expected average attenuation of each region. For clinical diagnostic purpose, PET/MR and PET/CT images were acquired in 23 patients (Ingenuity TF PET/MR, Gemini TF64). PET/CT scans were performed approximately 33.8 minutes after the beginnig of the PET/MR scans. Region of interests were drawn over 9 regions of interest(lung, liver, spleen, bone), and the Scanners' analysis software tools calculated both maximum and mean SUV. The SUVs from 9 regions of interest in MR-based PET images and in CT-based PET images were compared. These data were analyzed by paired t test and Bland-Altman analysis. Results : In phantom study, MR-based attenuation corrected PET images generally showed slightly lower -0.36~-0.15 SUVs than CT-based attenuation corrected PET images (p<0.05). In clinical study, MR-based attenuation corrected PET images generally showed slightly lower SUVs than CT-based attenuation corrected PET images (excepting left middle lung and transverse Lumbar) (p<0.05). And percent differences were -8.01.79% lower for the PET/MR images than for the PET/CT images. (excepting lung) Based on the Bland-Altman method, the agreement between the two methods was considered good. Conclusion : PET/MR confirms generally lower SUVs than PET/CT. But, there were no difference in the clinical interpretations made by the quantitative comparisons with both type of attenuation map.

• Progress in Medical Physics
• /
• v.32 no.4
• /
• pp.172-178
• /
• 2021

Purpose: This study aimed to develop a deep learning architecture combining two task models to generate synthetic computed tomography (sCT) images from low-tesla magnetic resonance (MR) images to improve metallic marker visibility. Methods: Twenty-three patients with cervical cancer treated with intracavitary radiotherapy (ICR) were retrospectively enrolled, and images were acquired using both a computed tomography (CT) scanner and a low-tesla MR machine. The CT images were aligned to the corresponding MR images using a deformable registration, and the metallic dummy source markers were delineated using threshold-based segmentation followed by manual modification. The deformed CT (dCT), MR, and segmentation mask pairs were used for training and testing. The sCT generation model has a cascaded three-dimensional (3D) U-Net-based architecture that converts MR images to CT images and segments the metallic marker. The performance of the model was evaluated with intensity-based comparison metrics. Results: The proposed model with segmentation loss outperformed the 3D U-Net in terms of errors between the sCT and dCT. The structural similarity score difference was not significant. Conclusions: Our study shows the two-task-based deep learning models for generating the sCT images using low-tesla MR images for 3D ICR. This approach will be useful to the MR-only workflow in high-dose-rate brachytherapy.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.5
• /
• pp.311-317
• /
• 2015

The aim of this study is to develop a 3D registration algorithm for positron emission tomography/computed tomography (PET/CT) and magnetic resonance (MR) images acquired from independent PET/CT and MR imaging systems. Combined PET/CT images provide anatomic and functional information, and MR images have high resolution for soft tissue. With the registration technique, the strengths of each modality image can be combined to achieve higher performance in diagnosis and radiotherapy planning. The proposed method consists of two stages: normalized mutual information (NMI)-based global matching and independent component analysis (ICA)-based refinement. In global matching, the field of view of the CT and MR images are adjusted to the same size in the preprocessing step. Then, the target image is geometrically transformed, and the similarities between the two images are measured with NMI. The optimization step updates the transformation parameters to efficiently find the best matched parameter set. In the refinement stage, ICA planes from the windowed image slices are extracted and the similarity between the images is measured to determine the transformation parameters of the control points. B-spline. based freeform deformation is performed for the geometric transformation. The results show good agreement between PET/CT and MR images.

• Journal of Korean Neurosurgical Society
• /
• v.40 no.5
• /
• pp.351-356
• /
• 2006

Objective : Spondylodiscitis has been diagnosed by clinical, radiological and laboratory methods. MR imaging is well known as an excellent diagnostic tool for spondylodiscitis. However, the changes in MR images throughout the treatment process has not been studied. Thus we have analyzed the serial changes of MR images throughout the stages of infection. Methods : Ten patients were selected for retrospective reviewed who had been treated at our institute for infectious spondylodiscitis between 2000 and 2005. These patients had been followed-up at least six months and had taken more than a couple of series of MR scans. We classified the MR images into four groups according to the stages of treatment for the infection and compared them to the clinical and laboratory findings. Results : MR image signals changed minimally or appeared to be normal in the early stages. The progression of spondylodiscitis was characterized by a low T1 WI signal and a high T2 WI signal in disc and vertebral body. The signal changes of the MR images were then propagated and the end plate was destructed. During the treatment, the destructed endplate became stabilized and the signal intensity of both T1 and T2 WI were fixed to low-or iso-intensity. Conclusion : We can determine the serial signal changes based on MR images according to the treatment of spondylodiscitis. We can therefore determine the status of the infection and the stage of treatment, as well as the diagnosis of spondylodiscitis using serial MR images.

• The Journal of Korean Society for Radiation Therapy
• /
• v.23 no.1
• /
• pp.7-12
• /
• 2011

Purpose: To analyze availability of MR images before and after external beam radiotherapy in brachytherapy, we will acquire MR images before and after external beam radiotherapy and compare the change of direction of uterine cavity and analyze the accuracy of applicator insertion. Materials and Methods: From January 2009 to December 2010, we compared MR images before and after external beam radiotherapy for uterine cervical cancer only with radical purpose treatment. MR images which was acquired after external beam radiotherapy has done with inserted status of CT/MR applicator. Results: As a consequence, the tumor was markedly reduced after external beam radiotherapy. The change of anteflexion of uterus turned into retroflexion of the uterine cavity was 17.1%. The case of wrong insertion of tandem include direction or length was 14.3%. Conclusion: According to MR images taken after external beam radiotherapy, we recognized not only reduced the tumor volume but the marked change of exact direction or length of the uterine cavity. So the confirmation of accurate insertion based on MR images before brachytherapy could be very helpful for optimal brachytherapy treatment planning with reduced applicator insertion errors.

• Proceedings of the KOSOMBE Conference
• /
• v.1998 no.11
• /
• pp.60-61
• /
• 1998

In this paper, we propose an algorithm for automatic segmentation of 3-dimesional brain MR images. In order to segment 3-dimensional brain MR images, we start segmentation from a mid-sagittal brain MR image. Then the segmented mid-sagittal brain MR image is used as a mask that is applied to the remaining lateral slices. Then we apply preprocessing, which includes thresholding and region-labeling, to the lateral slices, resulting in simplified 3-D brain MR images. Finally, we remove remaining problematic regions in the 3-dimensional brain MR image using the connectivity-based thresholding segmentation algorithm. Experiments show satisfactory results.

• Journal of Korea Multimedia Society
• /
• v.14 no.3
• /
• pp.348-355
• /
• 2011

In this paper, we propose an automatic prostate segmentation method from dynamic magnetic resonance (MR) images. Our method detects contrast-enhanced images among the dynamic MR images using an average intensity analysis. Then, the candidate regions of prostate are detected by the B-spline non-rigid registration and subtraction between the pre-contrast and contrast-enhanced MR images. Finally, the prostate is segmented by performing a dilation operation outward, and sequential shape propagation inward. Our method was validated by ten data sets and the results were compared with the manually segmented results. The average volumetric overlap error was 6.8%, and average absolute volumetric measurement error was 2.5%. Our method could be used for the computer-aided prostate diagnosis, which requires an accurate prostate segmentation.