• 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 Digestive Cancer Research
• /
• v.3 no.2
• /
• pp.108-112
• /
• 2015

A 54-year-old male patient who was diagnosed with advanced gastric cancer underwent a distal gastrectomy, D2 lymph node dissection, and adjuvant chemoradiotherapy. After a year, in a follow-up PET-CT, lymph node metastases were observed in the neck and abdomen, and therefore, the patient underwent chemotherapy. After treatment, the follow-up PET-CT revealed a growth of the posterior neck lymph node. Thus, an excisional biopsy was performed, and the growth was diagnosed as metastatic adenocarcinoma. Therefore, the patient received chemotherapy with FOLFIRI. Another follow-up PET-CT after chemotherapy revealed a growth in the right inguinal lymph node, and the patient underwent salvage radiotherapy for this lesion. The PET-CT taken for the response evaluation showed no evidence of further metastasis of the lymph node. We hereby report a case of advanced gastric cancer with neck and inguinal lymph node recurrence showing complete remission after palliative chemotherapy and salvage radiotherapy.

• Korean Journal of Radiology
• /
• v.23 no.7
• /
• pp.752-762
• /
• 2022

Objective: To compare a deep learning-based reconstruction (DLR) algorithm for pediatric abdominopelvic computed tomography (CT) with filtered back projection (FBP) and iterative reconstruction (IR) algorithms. Materials and Methods: Post-contrast abdominopelvic CT scans obtained from 120 pediatric patients (mean age ± standard deviation, 8.7 ± 5.2 years; 60 males) between May 2020 and October 2020 were evaluated in this retrospective study. Images were reconstructed using FBP, a hybrid IR algorithm (ASiR-V) with blending factors of 50% and 100% (AV50 and AV100, respectively), and a DLR algorithm (TrueFidelity) with three strength levels (low, medium, and high). Noise power spectrum (NPS) and edge rise distance (ERD) were used to evaluate noise characteristics and spatial resolution, respectively. Image noise, edge definition, overall image quality, lesion detectability and conspicuity, and artifacts were qualitatively scored by two pediatric radiologists, and the scores of the two reviewers were averaged. A repeated-measures analysis of variance followed by the Bonferroni post-hoc test was used to compare NPS and ERD among the six reconstruction methods. The Friedman rank sum test followed by the Nemenyi-Wilcoxon-Wilcox all-pairs test was used to compare the results of the qualitative visual analysis among the six reconstruction methods. Results: The NPS noise magnitude of AV100 was significantly lower than that of the DLR, whereas the NPS peak of AV100 was significantly higher than that of the high- and medium-strength DLR (p < 0.001). The NPS average spatial frequencies were higher for DLR than for ASiR-V (p < 0.001). ERD was shorter with DLR than with ASiR-V and FBP (p < 0.001). Qualitative visual analysis revealed better overall image quality with high-strength DLR than with ASiR-V (p < 0.001). Conclusion: For pediatric abdominopelvic CT, the DLR algorithm may provide improved noise characteristics and better spatial resolution than the hybrid IR algorithm.

• Progress in Medical Physics
• /
• v.11 no.1
• /
• pp.59-71
• /
• 2000

It is possible to obtain a fast CT scan during breath holding with spiral technique. But the risk of radiation is increased due to detailed and repeated scans. However, the limitation of X-ray doses is not fully specified on CT, yet. Therefore, the purpose of the present study is to define the limitation of X-ray doses on CT The CT unit was somatom plus 4. Alderson Rando phantom, Solenoid water phantom, TLD, and reader were used. For determining adequate position and size of organs, the measurement of distance(${\pm}$2mm) from the midline of vertebral body was performed in 40 women(20~40 years). On the brain scan for 8:8(8mm slice thickness, 8mm/sec movement velocity of the table) and 10:10(10mm slice thickness, 10mm/sec movement velocity of the table) methods, the absorption doses of exposed area of the 10:10 were slightly higher than those of 8:8. The doses of unexposed uterus were negligible on the brain scan for both 8:8 and 10:10. On the chest scan for 8:8, 8:10(8mm slice thickness, 10mm/sec movement velocity of the table), 10:10, 10:12(10mm slice thickness, 12mm/sec movement velocity of the table) and 10:15(10mm slice thickness, 15mm/sec movement velocity of the table) methods, 8:8 method of the absorption doses of exposure area was the most highest and 10:15 method was the most lowest. The absorption doses of 8:10 method was relatively lower than those of the other methods. In conclusion, the 8:10 method is the most suitable to give a low radiation burden to patient without distorting image quality.

• Progress in Medical Physics
• /
• v.19 no.1
• /
• pp.49-55
• /
• 2008

This study aims to conduct the comparative analysis of the radiation dose according to before and after the calibration of the ionization chamber used for measuring radiation dose in the MDCT, as well as of $CTDI_w$ according to temperature and pressure correction factors in the CT room. A comparative analysis was conducted based on the measured MDCT (GE light speed plus 4 slice, USA) data using head and body CT dosimetric phantom, and Model 2026C electrometer (RADICAL 2026C, USA) calibrated on March 21, 2007. As a result, the $CTDI_w$ value which reflected calibration factors, as well as correction factors of temperature and pressure, was found to be the range of $0.479{\sim}3.162mGy$ in effective radiation dose than the uncorrected values. Also, under the routine abdomen routine CT image acquisition conditions used in reference hospitals, patient effective dose was measured to indicate the difference of the maximum of 0.7 mSv between before and after the application of such factors. These results imply that the calibration of the ion chamber, and the correction of temperature and pressure of the CT room are crucial in measuring and calculating patient effective dose. Thus, to measure patient radiation dose accurately, the detailed information should be made available regarding not only the temperature and pressure of the CT room, but also the humidity and recombination factor, characteristics of X-ray beam quality, exposure conditions, scan region, and so forth.

• Journal of radiological science and technology
• /
• v.40 no.4
• /
• pp.567-573
• /
• 2017

The purpose of this study was to evaluate whether or not there was artifact when the upper limb could not be lifted to the top of the head during multi-detector computed tomography(MDCT) scans of the chest and abdomen. Contrast radiography of the human and chest phantom was performed with 128channal MDCT. Under the same conditions(120 kVp, 110 mAs, standard algorithm)both hands lifted up and put down each time in the human experiment. In the chest phantom experiment, the radiography was carried out when the upper limb phantom was adjusted at a certain distance(0, 3, 7 cm) from the chest phantom. Subsequently, the values of Noise, CT number, SNR, and CNR were measured in the field of concern. The noise value of fat, rib, and muscle increased when the arm was lifted in humans(0.79, 47.8, 27%). Furthermore, when the upper limb was lowered, the noise value of muscle and lung increased in the phantom(31.2, 9.4%). In addition, the noise value of the muscles and lung decreased by 5, 25.12% and 5.6, 15.35% as the upper limb moved about 0,3,7cm away from the chest. When the chest and abdominal radiography were performed, in the case of the presence of other parts outside the inspection area, the probability of artifact was minimal while the distance was more than 3cm away from the upper limb to the chest and abdomen.

• Journal of radiological science and technology
• /
• v.35 no.1
• /
• pp.45-50
• /
• 2012

Nowadays, most of the hospital serves "one stop service" for CT scan. The patients could be taken the CT scan in the day they register for scan. On the contrary to the time convenience, patients are not satisfied with long waiting time and unkindness of staff. The objective of this study is to improve the patient's satisfaction for the CT scan, by analyzing inconvenience factors and improving the service qualities. From April 1 to August 30 in 2011, we investigated the satisfaction of patients who did examined abdomen CT scan with contrast media. We analyzed the 89 questionnaires before and after the service improvements from them. The worker's kindness, the environment of CT room and understanding about CT scan were answered by questionnaire and the waiting time of a day CT scan was drawn by medical information statistics. Also, the period before improvement was from April to June and the period after improvement was from July to September. And these questionnaire was analyzed through SPSS V. 15.0. In this study, kindness of staff, environment of CT room, intelligibility for CT scan and waiting time was explored and analyzed by SPSS V.15.0. The score of kindness was improved by 32%, satisfaction level of the environment was improved by 52.54%. The understanding level about CT scan was improved by 52.36% and the wating time of a day CT was shortened by 21% through our service enhancement programs. Consequentially, it is considered that these efforts would contribute to increase the revenue of hospital.

• Tuberculosis and Respiratory Diseases
• /
• v.42 no.4
• /
• pp.600-604
• /
• 1995

Lymphangioleiomyomatosis, a rare disease in women of childbearing age, is the result of benign nodular hypertrophy of the smooth muscle of the lypmhatics and other tissues of the abdomen and thorax. We report a 36-years-old woman with pulmonary and retroperitoneal lymphangioleiomyomat.osis who responded with hormone treatment. She developed vaginal pruritis and a pelvic ultraound was done given her significant past medical history. Ultrasound examination demonstrated a large mass in the right side of her pelvis. Therefore she was admitted to St. Michael's Hospital in Toronto for laparoscopy. Result of cytology was to be consistent with the diagnosis of retroperitoneal lymphangioleiomyomatosis. High resolution CT sacn of the thorax demonstrated multiple small cystic lesions, without associated nodularity compatible with a diagnosis of pulmonary lymphangioleiomyomatosis. She has been taking Provera tablets 100mg po tid since Dec. 15, 1993. We have given her a prescription for Depo provera 500mg IM monthly since she came back to Korea. and made arrangements for regular follow up monthly. We performed chest X-ray, CT of chest(high resolution), abdomen and pelvis, pulmonary function tests and arterial blood gas analysis. Chest X-ray and CT findings showed no significant change since July. 20, 1993.

• Journal of Biomedical Engineering Research
• /
• v.25 no.3
• /
• pp.189-194
• /
• 2004

Pixel values of contrast enhanced computed tomography (CE-CT) images are randomly changed. Also, the middle liver part has a problem to segregate the liver structure because of similar gray-level values of a pancreas in the abdomen. In this paper, an automatic liver segmentation method using a partial histogram threshold (PHT) algorithm is proposed for overcoming randomness of CE-CT images and removing the pancreas. After histogram transformation, adaptive multi-modal threshold is used to find the range of gray-level values of the liver structure. Also, the PHT algorithm is performed for removing the pancreas. Then, morphological filtering is processed for removing of unnecessary objects and smoothing of the boundary. Four CE-CT slices of eight patients were selected to evaluate the proposed method. As the average of normalized average area of the automatic segmented method II (ASM II) using the PHT and manual segmented method (MSM) are 0.1671 and 0.1711, these two method shows very small differences. Also, the average area error rate between the ASM II and MSM is 6.8339 ％. From the results of experiments, the proposed method has similar performance as the MSM by medical Doctor.

• Journal of Radiation Protection and Research
• /
• v.37 no.4
• /
• pp.231-236
• /
• 2012

This study derived measures to reduce exposure doses by identifying factors which affect the external radiation dose rate of patients treated with radiopharmaceuticals for PET-CT tests. The external radiation dose rates were measured on three parts of head, thorax and abdomen at a distance of 50cm from the surface of 60 PET-CT patients. It showed there are changes in factors affecting the external radiation dose rate over time after the administration of F-18 FDG. The external radiation dose rate was lower in the patients with more water intake than those with less water intake before the injection of radiopharmaceuticals at all three points: right after the injection of radiopharmaceuticals (average 4.17 mins), after the pre-PEET-CT urination step (average 77.47 mins), and right after the PET-CT test (average 114.15 mins). The study also found there is a need to increase the amount of water intake before the injection of radiopharmaceuticals in order to maintain a low external radiation dose rate in patients. This strategy is only possible under the assumption that the quality of the video has not changed after conducting this study on the relations between the image and quality. This study also found a need to use radiopharmaceuticals with the minimum amount needed for each patient because F-FDG doses affects the external radiation dose rate at the point right after the injection of radiopharmaceuticals. Urination frequency was the most significant factor to affect the external radiation dose rates at the point right after the PET-CT test and the point after the pre-PET-CT urination step. There is a need to realize the strategy to increase the urination frequency of patients to maintain the external radiation dose rate low (average 77.47 mins) before and after the injection of radiopharmaceuticals. In addition, at this point, there is a need to take advantage of personal strategies because the external radiation dose rate is lower if the fasting time is shorter, the contrast medium is used, and the amount of water intake is increased after the administration of radiopharmaceuticals. Finally this study found the need to be able to generalize these findings through an in-depth research on the factors affecting the external radiation dose rate, which includes radiopharmaceutical dose, urination frequency, the amount of water intake, fasting time and the use of contrast medium.