• Journal of the Korean Society of Radiology
• /
• v.14 no.3
• /
• pp.211-220
• /
• 2020

High-quality computed tomography (CT) images enable precise lesion detection and accurate diagnosis. A lot of studies have been performed to improve CT image quality while reducing radiation dose. Recently, deep learning-based techniques for improving CT image quality have been developed and show superior performance compared to conventional techniques. In this study, a super-resolution convolutional neural network (SRCNN) model was used to improve the spatial resolution of CT images, and image quality according to the hyperparameters, which determine the performance of the SRCNN model, was evaluated in order to verify the effect of hyperparameters on the SRCNN model. Profile, structural similarity (SSIM), peak signal-to-noise ratio (PSNR), and full-width at half-maximum (FWHM) were measured to evaluate the performance of the SRCNN model. The results showed that the performance of the SRCNN model was improved with an increase of the numbers of epochs and training sets, and the learning rate needed to be optimized for obtaining acceptable image quality. Therefore, the SRCNN model with optimal hyperparameters is able to improve CT image quality.

• Journal of radiological science and technology
• /
• v.33 no.4
• /
• pp.355-362
• /
• 2010

This study determines a range of CT parameter values in Brain CT which are minimizing patient absorption dose without compromising the image quality and optimal exposure condition. We measured dose and image noise using conventional CT parameters in Brain CT. In additon, we evaluated dose, SNR and PSNR of head phantom images while changing kVp and rotation time. In this study, effectiveness of dose that was achieved from dose reproducible experiments in conventional head CT condition is determined by changing kVp and rotation time. Dose and PSNR is related to low dose-high resolution condition. In conclusion, we suggest that using proposed conditions is effective for imaging to compare with conditions proposed by the manufacturer.

• Radiation Oncology Journal
• /
• v.20 no.2
• /
• pp.165-171
• /
• 2002

Purpose : In order to perform craniospinal irradiation (CSI) in the supine position on patients who are unable to lie in the prone position, a new simulation technique using a CT simulator was developed and its availability was evaluated. Materials and Method : A CT simulator and a 3-D conformal treatment planning system were used to develop CSI in the supine position. The head and neck were immobilized with a thermoplastic mask in the supine position and the entire body was immobilized with a Vac-Loc. A volumetrie image was then obtained using the CT simulator. In order to improve the reproducibility of the patients' setup, datum lines and points were marked on the head and the body. Virtual fluoroscopy was peformed with the removal of visual obstacles such as the treatment table or the immobilization devices. After the virtual simulation, the treatment isocenters of each field were marked on the body and the immobilization devices at the conventional simulation room. Each treatment field was confirmed by comparing the fluoroscopy images with the digitally reconstructed radiography (DRR)/digitally composite radiography (DCR) images from the virtual simulation. The port verification films from the first treatment were also compared with the DRR/DCR images for a geometrical verification. Results : CSI in the supine position was successfully peformed in 9 patients. It required less than 20 minutes to construct the immobilization device and to obtain the whole body volumetric images. This made it possible to not only reduce the patients' inconvenience, but also to eliminate the position change variables during the long conventional simulation process. In addition, by obtaining the CT volumetric image, critical organs, such as the eyeballs and spinal cord, were better defined, and the accuracy of the port designs and shielding was improved. The differences between the DRRs and the portal films were less than 3 mm in the vertebral contour. Conclusion : CSI in the supine position is feasible in patients who cannot lie on prone position, such as pediatric patienta under the age of 4 years, patients with a poor general condition, or patients with a tracheostomy.

• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.25-34
• /
• 2022

Brain computed tomography (CT) is useful for brain lesion diagnosis, such as brain hemorrhage, due to non-invasive methodology, 3-dimensional image provision, low radiation dose. However, there has been numerous misdiagnosis owing to a lack of radiologist and heavy workload. Recently, object detection technologies based on artificial intelligence have been developed in order to overcome the limitations of traditional diagnosis. In this study, the applicability of a deep learning-based YOLOv5s model was evaluated for brain hemorrhage detection using brain CT images. Also, the effect of hyperparameters in the trained YOLOv5s model was analyzed. The YOLOv5s model consisted of backbone, neck and output modules. The trained model was able to detect a region of brain hemorrhage and provide the information of the region. The YOLOv5s model was trained with various activation functions, optimizer functions, loss functions and epochs, and the performance of the trained model was evaluated in terms of brain hemorrhage detection accuracy and training time. The results showed that the trained YOLOv5s model is able to provide a bounding box for a region of brain hemorrhage and the accuracy of the corresponding box. The performance of the YOLOv5s model was improved by using the mish activation function, the stochastic gradient descent (SGD) optimizer function and the completed intersection over union (CIoU) loss function. Also, the accuracy and training time of the YOLOv5s model increased with the number of epochs. Therefore, the YOLOv5s model is suitable for brain hemorrhage detection using brain CT images, and the performance of the model can be maximized by using appropriate hyperparameters.

• Progress in Medical Physics
• /
• v.14 no.2
• /
• pp.90-98
• /
• 2003

Purpose : A new virtual simulation technique for craniospinal irradiation (CSI) that uses a CT-simulator was developed to improve the accuracy of field and shielding placement as well as patient positioning. Materials and Methods : A CT simulator (CT-SIM) and a 3-D conformal radiation treatment planning system (3D-CRT) were used to develop CSI. The head and neck were immobilized with a thermoplastic mask while the rest of the body was immobilized with a Vac-Loc. A volumetric image was then obtained with the CT simulator. In order to improve the reproducibility of the setup, datum lines and points were marked on the head and body. Virtual fluoroscopy was performed with the removal of visual obstacles, such as the treatment table or immobilization devices. After virtual simulation, the treatment isocenters of each field were marked on the body and on the immobilization devices at the conventional simulation room. Each treatment fields was confirmed by comparing the fluoroscopy images with the digitally reconstructed radiography (DRR) and digitally composited radiography (DCR) images from virtual simulation. Port verification films from the first treatment were also compared with the DRR/DCR images for geometric verification. Results : We successfully performed virtual simulations on 11 CSI patients by CT-SIM. It took less than 20 minutes to affix the immobilization devices and to obtain the volumetric images of the entire body. In the absence of the patient, virtual simulation of all fields took 20 min. The DRRs were in agreement with simulation films to within 5 mm. This not only reducee inconveniences to the patients, but also eliminated position-shift variables attendant during the long conventional simulation process. In addition, by obtaining CT volumetric image, critical organs, such as the eyes and the spinal cord, were better defined, and the accuracy of the port designs and shielding was improved. Differences between the DRRs and the portal films were less than 3 m in the vertebral contour. Conclusion : Our analysis showed that CT simulation of craniospinal fields was accurate. In addition, CT simulation reduced the duration of the patient's immobility. During the planning process. This technique can improve accuracy in field placement and shielding by using three-dimensional CT-aided localization of critical and target structures. Overall, it has improved staff efficiency and resource utilization by standard protocol for craniospinal irradiation.

• Journal of the Korean Society of Radiology
• /
• v.8 no.6
• /
• pp.279-285
• /
• 2014

This study is to have dose reduction and minimization of excessive use of contrast medium in the pediatric cardiac computed tomography and to suggest the optimization plan to acquire the enhancement image of the 4 chambers at the same time by formulating scan delay time in empirical method with considering variables such as contrast medium injection velocity and cardiac approaching time. Quantitative, qualitative and dose assessment were carried out for 30 pediatric patients who had taken the cardiac examination. In conclusion, image enhancement in 4 chambers of the cardiac shows over 300 HU which is proper to pediatric cardiac reading by applying the empirical method with calculating scan delay time according to weight and contrast medium volume and injection velocity. Qualitative image assessments in confidence sharpness and noise have excellence qualitatively. Exposure dose to pediatrics also decreases precisely. Therefore this study is judged to take a important role of making optimization images with advantages of dose reduction and less side effects caused by it's excessive use in clinic.

• Radiation Oncology Journal
• /
• v.10 no.1
• /
• pp.59-67
• /
• 1992

From March 1979 through December 1986, 124 patients with early stage carcinoma of the uterine cervix received curative radiation therapy. According to FIGO classification, 35 patients were stage IB and 89 were stge II A. In stage IB, five year locoregional control, five year disease free survival, and five year overall survival was $79.0\%$, $76.4\%$ and $81.8\%$, respectively. In stage II A, five year locoregional control, five year disease free survival, and five year overall survival were $78.0\%$, $66.8\%$, and $72.1\%$, respectively. To identify prognostic factors, pretreatment parameters including age, ECOG performance status, number of pregnancies, history of diabetes mellitus and hypertension, histology, size and shape of primary tumor, CT findings and blood parameters were retrospectively analyzed in terms of locoregional control, disease free survival and overall survival using univariate analysis and multivariate analysis. In univariate analysis, tumor size on physicai examination and rectal invasion on CT significantly affected locoregional control, disease free survival and overall survival. Parametrial involvement on CT was a significant prognostic factor on locoregional control and disease free survival. Hemoglobin level affected disease free survival and overall survival. Histology and age were significant prognostic factors on locoregional control. In multivariate analysis excluding CT finding, tumor size on physical examination was a significant factor in terms of locoregioal control and overall survival. Hemoglobin level was significant in terms of disease free survival. In multivariate analysis including CT, histology was a prognostic factor on locoregional control and disease free survival. Hemoglobin level and rectal invasion on CT were significant factors on locoregional control.

• Journal of the Korean Society of Radiology
• /
• v.17 no.1
• /
• pp.1-9
• /
• 2023

For optimal image quality of computer tomography angiography (CTA), different iodine concentrations and scan parameters were applied to quantitatively evaluate the image quality characteristics of filtered back projection (FBP), hybrid-iterative reconstruction (hybrid-IR), and deep learning reconstruction (DLR). A 320-row-detector CT scanner scanned a phantom with various iodine concentrations (1.2, 2.9, 4.9, 6.9, 10.4, 14.3, 18.4, and 25.9 mg/mL) located at the edge of a cylindrical water phantom with a diameter of 19 cm. Data obtained using each reconstruction technique was analyzed through noise, coefficient of variation (COV), and root mean square error (RMSE). As the iodine concentration increased, the CT number value increased, but the noise change did not show any special characteristics. COV decreased with increasing iodine concentration for FBP, adaptive iterative dose reduction (AIDR) 3D, and advanced intelligent clear-IQ engine (AiCE) at various tube voltages and tube currents. In addition, when the iodine concentration was low, there was a slight difference in COV between the reconstitution techniques, but there was little difference as the iodine concentration increased. AiCE showed the characteristic that RMSE decreased as the iodine concentration increased but rather increased after a specific concentration (4.9 mg/mL). Therefore, the user will have to consider the characteristics of scan parameters such as tube current and tube voltage as well as iodine concentration according to the reconstruction technique for optimal CTA image acquisition.

• Radiation Oncology Journal
• /
• v.10 no.2
• /
• pp.227-236
• /
• 1992

From March 1979 through December 1986, 232 previously untreated patients with invasive carcinoma of the uterine cervix stage IIB were treated at the Department of Therapeutic Radiology, Seoul National University Hospital. The patients studied were staged according to the FIGO recommendations and the majority of patients were treated with external beam whole pelvis radiation and intracavitary radiation. Pretreatment parameters, including physical examination findings, blood parameters, prior medical illnesses, histology and abdomino-pelvic CT findings were studied, employing univariate and multivariate analyses to identify the potentially significant prognostic factors on locoregional control, disease free survival and overall survival. Histology, extent of parametrial involvement on physical examination and paraaortic lymph node metastasis on CT were found to have prognostic significance in the carcinoma of uterine cervix stage IIB.

• Clinics in Shoulder and Elbow
• /
• v.12 no.2
• /
• pp.199-206
• /
• 2009

Purpose: Our goal for this study was to prospectively evaluate the functional & structural outcomes, by means of CT arthroscopy, of arthroscopic double-row fixation for treating rotator cuff tear. We also attempted to determine the variants that affect the functional & structural outcomes. Materials and Methods: Twenty seven consecutive patients underwent arthroscopic rotator cuff repair with double-row fixation. The average age at the time of the operation was fifty six years. The preoperative and postoperative examinations consisted of determining the Constant score, the score for the visual analogue scale for pain, the UCLA score, the American Shoulder and Elbow Surgeons (ASES) score, as well as a full physical examination of the shoulder. Preoperative MR arthrography was used to evaluate the integrity and atrophy of the rotator cuff. We measured the intraoperative tear size in the sagittal and coronal planes. Postoperative CT arthrography was used at one year postoperatively to evaluate the integrity and atrophy of the repaired tendons and muscles. Results: Preoperative MR arthrography revealed an average 29.22 mm tear size in the sagittal plane and an average 22.72 mm tear size in the coronal plane. Twelve cases of supraspinatus muscle atrophy and two cases of infraspinatus atrophy were observed on the preoperative MR arthrography. The average clinical outcome scores all significantly improved at the time of follow-up. At a mean of one year postoperatively, CT arthrography revealed 48.1% of the shoulders had healed, 11.1% showed incomplete healing and 40.7% showed retear of the repaired tendon. Conclusion: Arthroscopic double-row repair can result in improved clinical outcomes and good patient satisfaction. However, the problems about how to enhance healing of the repaired tendon still remain.