• Journal of the Korean Society of Radiology
• /
• v.83 no.6
• /
• pp.1298-1311
• /
• 2022

Purpose To develop and validate a deep learning-based screening tool for the early diagnosis of scoliosis using chest radiographs with a semi-supervised generative adversarial network (GAN). Materials and Methods Using a semi-supervised learning framework with a GAN, a screening tool for diagnosing scoliosis was developed and validated through the chest PA radiographs of patients at two different tertiary hospitals. Our proposed method used training GAN with mild to severe scoliosis only in a semi-supervised manner, as an upstream task to learn scoliosis representations and a downstream task to perform simple classification for differentiating between normal and scoliosis states sensitively. Results The area under the receiver operating characteristic curve, negative predictive value (NPV), positive predictive value, sensitivity, and specificity were 0.856, 0.950, 0.579, 0.985, and 0.285, respectively. Conclusion Our deep learning-based artificial intelligence software in a semi-supervised manner achieved excellent performance in diagnosing scoliosis using the chest PA radiographs of young individuals; thus, it could be used as a screening tool with high NPV and sensitivity and reduce the burden on radiologists for diagnosing scoliosis through health screening chest radiographs.

• Journal of the Korean Society of Radiology
• /
• v.83 no.6
• /
• pp.1259-1272
• /
• 2022

Purpose As part of ongoing efforts to improve the current e-learning center, a survey was conducted regarding user experience and satisfaction to identify areas of improvement. Materials and Methods Radiologists (n = 454/617) and radiology residents (n = 163/617) of the Korean Society of Radiology were asked to answer a survey via email. The questionnaire asked for basic user information as well as user experiences relating to the e-learning center, such as workplace, frequency of use, overall satisfaction levels, reasons for satisfaction or dissatisfaction, and other suggestions for improvement. Results Annual members and all members of the e-learning center reported above average satisfaction levels of 67% and 42%, respectively. Approximately 30% of respondents viewed e-learning center lectures more than 5 times a month, with residents having a particularly high usage frequency. There was a high demand for additional lectures covering more diverse specialties (e-learning for annual members only: n = 28/97, e-learning for all members: n = 72/166), a smoother and more convenient searching platform/interface (n = 37/97 and n = 58/166, respectively), and regular content updates. In addition, many of the members suggested the addition of user-friendly functions such as playback speed control, a way to save viewing history, as well as requests for improved system stability. Conclusion Based on survey results, the educational committee plans to continue its efforts to improve the e-learning center by increasing the quality and quantity of available lectures, and increasing technical support to improve the stability and convenience of the e-learning digital system.

• Journal of the Korean Society of Radiology
• /
• v.83 no.6
• /
• pp.1312-1326
• /
• 2022

Purpose To investigate the added value of right down decubitus (RDD) CT when determining adjacent organ invasion in cases of advanced gastric cancer (AGC). Materials and Methods A total of 728 patients with pathologically confirmed T4a (pT4a), surgically confirmed T4b (sT4b), or pathologically confirmed T4b (pT4b) AGCs who underwent dedicated stomach-protocol CT, including imaging of the left posterior oblique (LPO) and RDD positions, were included in this study. Two radiologists scored the T stage of AGCs using a 5-point scale on LPO CT with and without RDD CT at 2-week intervals and recorded the presence of "sliding sign" in the tumors and adjacent organs and compared its incidence of appearance. Results A total of 564 patients (77.4%) were diagnosed with pT4a, whereas 65 (8.9%) and 99 (13.6%) patients were diagnosed with pT4b and sT4b, respectively. When RDD CT was performed additionally, both reviewers deemed that the area under the curve (AUC) for differentiating T4b from T4a increased (p < 0.001). According to both reviewers, the AUC for differentiating T4b with pancreatic invasion from T4a increased in the subgroup analysis (p < 0.050). Interobserver agreement improved from fair to moderate (weighted kappa value, 0.296-0.444). Conclusion RDD CT provides additional value compared to LPO CT images alone for determining adjacent organ invasion in patients with AGC due to their increased AUC values and improved interobserver agreement.

• Journal of the Korean Society of Radiology
• /
• v.81 no.3
• /
• pp.610-619
• /
• 2020

Purpose The study aimed to investigate the role of Prostate Imaging Reporting and Data System version 2 (PI-RADS v2) in predicting incidental prostate cancer (PCa) or urothelial carcinoma (UCa) extension in urinary bladder (UB) cancer patients. Materials and Methods A total of 72 UB cancer patients who underwent radical cystoprostatectomy and 3 Tesla multiparametric MRI before surgery were enrolled. PI-RADS v2 ratings were assigned by two independent radiologists. All prostate specimens were examined by a single pathologist. We compared the multiparametric MRI findings rated using PI-RADS v2 with the pathologic data. Results Of the 72 UB cancer patients, 29 had incidental PCa (40.3%) and 20 showed UCa extension (27.8%), with an overlap for 3 patients. With a score of 4 as the cut-off value for predicting incidental PCa, the diagnostic accuracy was 65.3%, specificity was 90.7%, and positive predictive value (PPV) was 66.7%. The diagnostic accuracy for incidental UCa extension was 47.2%, specificity was 92.3%, and PPV was 83.3%. Conclusion Despite the low diagnostic accuracy, the PPV and specificity were relatively high. Therefore, PI-RADS v2 scores of 1, 2, or 3 may help exclude the probability of incidental PCa or UCa extension.

• Korean Journal of Radiology
• /
• v.25 no.6
• /
• pp.511-517
• /
• 2024

Objective: To prospectively investigate the influence of the menstrual cycle on the background parenchymal signal (BPS) and apparent diffusion coefficient (ADC) of the breast on diffusion-weighted MRI (DW-MRI) in healthy premenopausal women. Materials and Methods: Seven healthy premenopausal women (median age, 37 years; range, 33-49 years) with regular menstrual cycles participated in this study. DW-MRI was performed during each of the four phases of the menstrual cycle (four examinations in total). Three radiologists independently assessed the BPS visual grade on images with b-values of 800 sec/mm² (b800), 1200 sec/mm² (b1200), and a synthetic 1500 sec/mm² (sb1500). Additionally, one radiologist conducted a quantitative analysis to measure the BPS volume (%) and ADC values of the BPS (ADC_BPS) and fibroglandular tissue (ADC_FGT). Changes in the visual grade, BPS volume (%), ADC_BPS, and ADC_FGT during the menstrual cycle were descriptively analyzed. Results: The visual grade of BPS in seven women varied from mild to marked on b800 and from minimal to moderate on b1200 and sb1500. As the b-value increased, the visual grade of BPS decreased. On b800 and sb1500, two of the seven volunteers showed the highest visual grade in the early follicular phase (EFP). On b1200, three of the seven volunteers showed the highest visual grades in EFP. The BPS volume (%) on b800 and b1200 showed the highest value in three of the six volunteers with dense breasts in EFP. Three of the seven volunteers showed the lowest ADC_BPS in the EFP. Four of the seven volunteers showed the highest ADC_BPS in the early luteal phase (ELP) and the lowest ADC_FGT in the late follicular phase (LFP). Conclusion: Most volunteers did not exhibit specific BPS patterns during their menstrual cycles. However, the highest BPS and lowest ADC_BPS were more frequently observed in EFP than in the other menstrual cycle phases, whereas the highest ADC_BPS was more common in ELP. The lowest ADC_FGT was more frequent in LFP.

• Journal of the Korean Society of Radiology
• /
• v.81 no.4
• /
• pp.920-932
• /
• 2020

Purpose The aim of this study was to evaluate the diagnostic image quality of low dose abdominal digital radiography processed with a new post-processing technique. Materials and Methods Abdominal radiographs from phantom pilot studies were post-processed by the novel and conventional post-processing methods of our institution; the proper dose for the subsequent patient study of 49 subjects was determined by comparing image quality of the two preceding studies. Two radiographs of each patient were taken using the conventional and derived dose protocols with the proposed post-processing method. The image details and quality were evaluated by two radiologists. Results The radiation dose for the patient study was derived to be half of the conventional method. Overall half-dose image quality with the proposed method was significantly higher than that of the conventional method (p < 0.05) with moderate inter-rater agreement (κ = 0.60, 0.47). Conclusion By applying the new post-processing technique, half-dose abdominal digital radiography can demonstrate feasible image quality compared to the full-dose images.

• Journal of the Korean Society of Radiology
• /
• v.82 no.1
• /
• pp.99-115
• /
• 2021

Various sequences have been developed for MRI to aid in the radiologic diagnosis. Among the various MR sequences, susceptibility-weighted imaging (SWI) is a high-spatial-resolution, three-dimensional gradient-echo MR sequence, which is very sensitive in detecting deoxyhemoglobin, ferritin, hemosiderin, and bone minerals through local magnetic field distortion. In this regard, SWI has been used for the diagnosis and treatment of various neurologic disorders, and the improved image quality has enabled to acquire more useful information for radiologists. Here, we explain the principle of various signals on SWI arising in neurological disorders and provide a retrospective review of many cases of clinically or pathologically proven disease or components with distinctive imaging features of various neurological diseases. Additionally, we outline a short and condensed overview of principles of SWI in relation to neurological disorders and describe various cases with characteristic imaging features on SWI. There are many different types diseases involving the brain parenchyma, and they have distinct SWI features. SWI is an effective imaging tool that provides complementary information for the diagnosis of various diseases.

• Journal of the Korean Society of Radiology
• /
• v.82 no.3
• /
• pp.638-653
• /
• 2021

Purpose To compare the recurrence pattern, disease-free survival (DFS), and overall survival (OS) after curative surgery for pancreatic ductal adenocarcinoma (PDAC) in patients who underwent preoperative evaluation with CT alone or in combination with MRI, and to compare the prognosis according to the first recurrence site. Materials and Methods We retrospectively evaluated 152 patients who underwent R0 resection of PDAC. Preoperative CT or combined CT and MRI were performed for 103 and 49 patients, respectively. Two radiologists recorded the location and date of the first recurrence in consensus. The recurrence pattern, DFS, and OS were compared between the two groups. OS was analyzed according to the first recurrence site. Results In both groups, liver metastasis was the most common recurrence pattern. DFS (p = 0.247) or OS (p = 0.067) showed no significant difference between the two groups. OS according to the first recurrence site was the lowest for liver metastasis, followed by locoregional recurrence (p < 0.001). Conclusion There were no significant differences in the recurrence pattern, DFS, or OS between patients evaluated with preoperative CT alone or with CT and MRI after curative resection of PDAC. Liver metastasis was the most common tumor recurrence pattern with the lowest OS.

• Journal of the Korean Society of Radiology
• /
• v.81 no.2
• /
• pp.324-336
• /
• 2020

Cardiovascular calcifications can occur in various cardiovascular diseases and can serve as a biomarker for cardiovascular event prediction. Advances in CT have enabled evaluation of calcifications in cardiovascular structures not only on ECG-gated CT but also on non-ECG-gated CT. Therefore, many studies have been conducted on the clinical relevance of cardiovascular calcifications in patients. In this study, we divided cardiovascular calcifications into three classes, i.e., coronary artery, thoracic aorta, and cardiac valve calcifications, which are closely associated with cardiovascular events. Further, we briefly described pericardial calcifications, which can be found incidentally. Since the start of lung cancer screening in Korea in the second half of 2019, the number of non-enhanced, non-ECG-gated, low-dose chest CT has been increasing, and the number of incidentally found cardiovascular calcifications has also been increasing. Therefore, understanding the relevance of cardiovascular calcifications on non-enhanced, non-ECG-gated, low-dose chest CT and their proper reporting are important for radiologists.

• Journal of the Korean Society of Radiology
• /
• v.82 no.6
• /
• pp.1581-1588
• /
• 2021

Electronic cigarette (e-cigarette) or vaping product use-associated lung injury (EVALI) has emerged as a social issue as e-cigarette use is rapidly increasing worldwide and is related to many deaths in the United States. To our knowledge, this is the first case report of EVALI in South Korea of a 24-year-old man with acute respiratory symptoms and a history of e-cigarette use. Chest CT revealed diffuse bilateral ground-glass opacities with subpleural sparing, airspace consolidation, and centrilobular micronodules as typical patterns of EVALI with organizing pneumonia and diffuse alveolar damage. Infection was excluded with meticulous laboratory examinations, and the patients' illnesses were not attributed to other causes. EVALI was diagnosed by meeting the diagnostic criteria with consistent clinico-radiologic findings through a multidisciplinary approach. Radiologists should have good knowledge of EVALI radiologic findings and play a cardinal role in the proper diagnosis and management of EVALI.