Korean Journal of Radiology最新文献

{"title":"Multiparametric MRI for Diagnosing Dysthyroid Optic Neuropathy: Added Value of Magnetization Transfer Imaging.","authors":"Jiang Zhou, Quan Yuan, Xiong-Ying Pu, Jin-Ling Lu, Hu Liu, Huan-Huan Chen, Xiao-Quan Xu, Hao Hu, Fei-Yun Wu","doi":"10.3348/kjr.2024.1188","DOIUrl":"https://doi.org/10.3348/kjr.2024.1188","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the ability of magnetization transfer imaging (MTI) to diagnose dysthyroid optic neuropathy (DON) and to establish the added value of MTI to conventional T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI).</p><p><strong>Materials and methods: </strong>One hundred and forty-nine patients with thyroid-associated ophthalmopathy were included and divided into training (46 eyes with DON and 148 eyes without DON) and validation (20 eyes with DON and 64 eyes without DON) cohorts. The orbital magnetic resonance imaging (MRI) protocols included coronal MTI, fat-suppressed T2WI, and DWI. The minimum, mean, and maximum values of the magnetization transfer ratio (MTR), signal intensity ratio (SIR), apparent diffusion coefficient (ADC) of each optic nerve (ON), and modified muscle index (mMI) of each orbit were calculated and compared between the groups. Multi-variable logistic regression analysis was performed to identify the independent imaging predictors of DON. The performance of each imaging predictor and their combinations using a binary logistic regression model for diagnosing DON was evaluated using receiver operating characteristic (ROC) curve analysis.</p><p><strong>Results: </strong>Eyes with DON exhibited significantly lower MTRs and ADCs of the ON, increased SIRs of the ON, and increased mMI. The MTR_mean of the ON, ADC_mean of the ON, and mMI were independent predictors of DON. The multi-variable model incorporating these three variables yielded an area under the ROC curve (AUC) of 0.946 and showed significantly higher diagnostic performance than MTR_mean (AUC = 0.831), ADC_mean (AUC = 0.738), or mMI (AUC = 0.862) alone in the training cohort (all <i>P</i> < 0.001). In the validation cohort, the multi-variable model achieved satisfactory diagnostic performance (AUC = 0.926).</p><p><strong>Conclusion: </strong>MTI may be a useful non-invasive technique for diagnosing DON. MTR can provide additional value to conventional DWI in distinguishing patients with DON from those without DON.</p>","PeriodicalId":17881,"journal":{"name":"Korean Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144317320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantitative Analysis With Time-Dependent Diffusion MRI for Assessing WHO/ISUP Tumor Grade in Clear Cell Renal Cell Carcinoma.","authors":"Chunlei He, Enyu Yuan, Lei Ye, Hui Xu, Xiaoyong Zhang, Hao Zeng, Yuntian Chen, Jin Yao, Bin Song","doi":"10.3348/kjr.2024.1202","DOIUrl":"https://doi.org/10.3348/kjr.2024.1202","url":null,"abstract":"<p><strong>Objective: </strong>To investigate the feasibility of time-dependent diffusion-weighted imaging (<i>t_d</i>-<i>dMRI</i>) in assessing the pathological World Health Organization/International Society of Urological Pathology (WHO/ISUP) grade of clear cell renal cell carcinoma (ccRCC).</p><p><strong>Materials and methods: </strong>A total of 138 patients (median age, 58 years [interquartile range, 51-64 years]; 89 males) with surgically confirmed ccRCC, comprising 48 high-grade (WHO/ISUP grade III/IV) and 90 low-grade (WHO/ISUP grade I/II) tumors, were included in the study among patients who underwent preoperative <i>t_d</i>-<i>dMRI</i> for suspected RCC between May 2022 and May 2024. The <i>t_d</i>-<i>dMRI</i> microstructural parameters, including cell <i>diameter</i> (<i>d</i>), intracellular volume fraction (<i>f_in</i>), <i>cellularity</i>, and extracellular diffusivities (<i>D_ex</i>), were quantified using a two-compartment model. The solid tumor area was manually annotated to extract the mean values from each parameter map. We analyzed the differences in <i>t_d</i>-<i>dMRI</i> parameters between the high- and low-grade tumors and evaluated the ability of these parameters to distinguish between the two tumor groups. High-definition hematoxylin-and-eosin-stained slides were obtained from 92 patients. We assessed the correlation between <i>t_d</i>-<i>dMRI</i> parameters and pathologic nuclear fraction, which was quantified using an automated nucleus segmentation model (Hover-Net).</p><p><strong>Results: </strong>Compared to high-grade tumors, low-grade tumors exhibited lower <i>cellularity</i> and <i>f_in</i> and higher <i>diameter</i> and <i>D_ex</i>. For differentiation between low- and high-grade ccRCC, the <i>f_in</i> exhibited the highest diagnostic performance (areas under the receiver operating characteristic curve [AUC] = 0.943; 95% confidence interval, 0.906-0.980), followed by <i>cellularity</i> (AUC = 0.931; 0.887-0.976), <i>D_ex</i> (AUC = 0.863; 0.800-0.926), and <i>diameter</i> (AUC = 0.690; 0.596-0.784). The nuclei on pathology slides were automatically segmented, and the nuclear fraction exhibited a moderate correlation with <i>f_in</i> (<i>r</i> = 0.65, <i>P</i> < 0.001).</p><p><strong>Conclusion: </strong><i>t_d</i>-<i>dMRI</i> parameters show potential for assessing pathological WHO/ISUP grades and may serve as promising noninvasive biomarkers for characterizing RCC.</p>","PeriodicalId":17881,"journal":{"name":"Korean Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144317322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FloWise Flow Diverter for Treatment of Unruptured Wide-Neck Intracranial Aneurysms: A Prospective, Multicenter, Single-Arm, Open-Label, Pivotal Study.","authors":"Hyun Jin Han, Keun Young Park, Byung Moon Kim, Yong Bae Kim, Hong-Jun Jeon, Sang Hyun Suh, Sangil Suh, Jung-Jae Kim, Jun-Hwee Kim, Chang Ki Jang, Dong Joon Kim, Jung Keun Lee, Sunghan Kim, Kyu Seon Chung, Solbi Kim, Sun Yoon, Min Jeoung Kim","doi":"10.3348/kjr.2024.1212","DOIUrl":"https://doi.org/10.3348/kjr.2024.1212","url":null,"abstract":"<p><strong>Objective: </strong>We evaluated the safety and efficacy of a new flow diverter in the treatment of unruptured wide-neck aneurysms.</p><p><strong>Materials and methods: </strong>Patients who had unruptured intracranial aneurysms with a neck diameter ≥4 mm or dome-to-neck ratio <2 and who met other eligibility criteria were enrolled from seven institutions. The patients were treated with a new flow diverter (FloWise; Taewoong Medical, Seoul, Korea) and followed at 1, 3, 6, and 12 months after treatment. The primary efficacy endpoint was the complete occlusion of the target aneurysm at 12 months. Safety endpoints included ipsilateral stroke (National Institutes of Health Stroke Scale score ≥5), newly developed neurological deficit (modified Rankin Scale score ≥3), death at 30 days, and ≥50% parent artery stenosis or occlusion at the 12-month follow-up. The superiority of FloWise over the predefined reference value (56.7%) was investigated using a one-sided binomial test with a statistical significance of <i>P</i> < 0.025.</p><p><strong>Results: </strong>Seventy patients (59.0 ± 9.9 years; male:female = 16:54) with 93 aneurysms (median diameter, 5.2 mm [range, 1.6-26.1 mm]; median neck diameter, 4.1 mm [range, 1.2-22.4 mm]) were included. Of these, 69 patients who completed the follow-up as planned constituted the efficacy analysis set. Complete aneurysm occlusion was achieved in 56 target aneurysms (81.2%; 95% confidence interval [CI], 69.9-89.6; <i>P</i> < 0.001). Procedural success and ≥50% aneurysm volume reduction were observed in 69 (100%) and 66 (95.7%; 95% CI, 87.8-99.1) target aneurysms, respectively. No ipsilateral strokes occurred in any of the 70 patients. Serious adverse events occurred in 6 patients; these events were causally related to the treatment in 4 (5.7%) cases and possibly related to the device in 2 (2.9%) cases.</p><p><strong>Conclusion: </strong>FloWise flow diverter is safe and effective for the treatment of unruptured wide-neck aneurysms.</p>","PeriodicalId":17881,"journal":{"name":"Korean Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144317317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of Deep Learning-Based Image Conversion on Fully Automated Coronary Artery Calcium Scoring Using Thin-Slice, Sharp-Kernel, Non-Gated, Low-Dose Chest CT Scans: A Multi-Center Study.","authors":"Cherry Kim, Sehyun Hong, Hangseok Choi, Won-Seok Yoo, Jin Young Kim, Suyon Chang, Chan Ho Park, Su Jin Hong, Dong Hyun Yang, Hwan Seok Yong, Marly van Assen, Carlo N De Cecco, Young Joo Suh","doi":"10.3348/kjr.2025.0177","DOIUrl":"https://doi.org/10.3348/kjr.2025.0177","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the impact of deep learning-based image conversion on the accuracy of automated coronary artery calcium quantification using thin-slice, sharp-kernel, non-gated, low-dose chest computed tomography (LDCT) images collected from multiple institutions.</p><p><strong>Materials and methods: </strong>A total of 225 pairs of LDCT and calcium scoring CT (CSCT) images scanned at 120 kVp and acquired from the same patient within a 6-month interval were retrospectively collected from four institutions. Image conversion was performed for LDCT images using proprietary software programs to simulate conventional CSCT. This process included 1) deep learning-based kernel conversion of low-dose, high-frequency, sharp kernels to simulate standard-dose, low-frequency kernels, and 2) thickness conversion using the raysum method to convert 1-mm or 1.25-mm thickness images to 3-mm thickness. Automated Agaston scoring was conducted on the LDCT scans before (LDCT-Org_auto) and after the image conversion (LDCT-CONV_auto). Manual scoring was performed on the CSCT images (CSCT_manual) and used as a reference standard. The accuracy of automated Agaston scores and risk severity categorization based on the automated scoring on LDCT scans was analyzed compared to the reference standard, using the Bland-Altman analysis, concordance correlation coefficient (CCC), and weighted kappa (κ) statistic.</p><p><strong>Results: </strong>LDCT-CONV_auto demonstrated a reduced bias for Agaston score, compared with CSCT_manual, than LDCT-Org_auto did (-3.45 vs. 206.7). LDCT-CONV_auto showed a higher CCC than LDCT-Org_auto did (0.881 [95% confidence interval {CI}, 0.750-0.960] vs. 0.269 [95% CI, 0.129-0.430]). In terms of risk category assignment, LDCT-Org_auto exhibited poor agreement with CSCT_manual (weighted κ = 0.115 [95% CI, 0.082-0.154]), whereas LDCT-CONV_auto achieved good agreement (weighted κ = 0.792 [95% CI, 0.731-0.847]).</p><p><strong>Conclusion: </strong>Deep learning-based conversion of LDCT images originally obtained with thin slices and a sharp kernel can enhance the accuracy of automated coronary artery calcium score measurement using the images.</p>","PeriodicalId":17881,"journal":{"name":"Korean Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144317318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contrast-Enhanced Abdominopelvic CT After Peripheral Venoarterial Extracorporeal Membrane Oxygenation.","authors":"Eun Sun Choi, Jong Keon Jang","doi":"10.3348/kjr.2025.0256","DOIUrl":"https://doi.org/10.3348/kjr.2025.0256","url":null,"abstract":"","PeriodicalId":17881,"journal":{"name":"Korean Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144317316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Letter Regarding \"Overview of South Korean Guidelines for Approval of Large Language or Multimodal Models as Medical Devices: Key Features and Areas for Improvement\".","authors":"Hye Jin Baek","doi":"10.3348/kjr.2025.0529","DOIUrl":"https://doi.org/10.3348/kjr.2025.0529","url":null,"abstract":"","PeriodicalId":17881,"journal":{"name":"Korean Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144317319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing Yttrium-90 Radioembolization Dosimetry for Hepatocellular Carcinoma: A Korean Perspective.","authors":"In Joon Lee, Hyo-Cheol Kim","doi":"10.3348/kjr.2025.0308","DOIUrl":"https://doi.org/10.3348/kjr.2025.0308","url":null,"abstract":"<p><p>Yttrium-90 transarterial radioembolization (TARE) has emerged as a valuable treatment option for hepatocellular carcinoma (HCC) and is being increasingly incorporated into clinical guidelines. Recent advancements in dosimetry, including personalized dosimetry and multi-compartment modeling, have significantly improved tumor response and clinical outcomes. Although high tumor-absorbed doses are associated with better oncologic control, careful dose adjustment is essential for minimizing toxicity to normal liver tissue and lungs. This review explores the key aspects of TARE dosimetry, including single- and multi-compartment modeling, differences between resin and glass microspheres, dose-response relationships, and strategies to mitigate hepatotoxicity and radiation pneumonitis. Various clinical applications of TARE have been discussed, ranging from curative-intent radiation segmentectomy and lobectomy to palliative treatment of diffuse and macrovascular invasion-associated HCCs. In South Korea, where cadaveric liver transplantation is limited, a multidisciplinary approach is particularly important for optimizing treatment strategies and preserving liver function for potential future interventions. As dosimetry continues to evolve, further research is required to refine dose optimization protocols and validate their clinical impact in different patient populations, including those in South Korea.</p>","PeriodicalId":17881,"journal":{"name":"Korean Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144317321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance of GPT-4 Turbo and GPT-4o in Korean Society of Radiology In-Training Examinations.","authors":"Arum Choi, Hyun Gi Kim, Moon Hyung Choi, Shakthi Kumaran Ramasamy, Youme Kim, Seung Eun Jung","doi":"10.3348/kjr.2024.1096","DOIUrl":"10.3348/kjr.2024.1096","url":null,"abstract":"<p><strong>Objective: </strong>Despite the potential of large language models for radiology training, their ability to handle image-based radiological questions remains poorly understood. This study aimed to evaluate the performance of the GPT-4 Turbo and GPT-4o in radiology resident examinations, to analyze differences across question types, and to compare their results with those of residents at different levels.</p><p><strong>Materials and methods: </strong>A total of 776 multiple-choice questions from the Korean Society of Radiology In-Training Examinations were used, forming two question sets: one originally written in Korean and the other translated into English. We evaluated the performance of GPT-4 Turbo (gpt-4-turbo-2024-04-09) and GPT-4o (gpt-4o-2024-11-20) on these questions with the temperature set to zero, determining the accuracy based on the majority vote from five independent trials. We analyzed their results using the question type (text-only vs. image-based) and benchmarked them against nationwide radiology residents' performance. The impact of the input language (Korean or English) on model performance was examined.</p><p><strong>Results: </strong>GPT-4o outperformed GPT-4 Turbo for both image-based (48.2% vs. 41.8%, <i>P</i> = 0.002) and text-only questions (77.9% vs. 69.0%, <i>P</i> = 0.031). On image-based questions, GPT-4 Turbo and GPT-4o showed comparable performance to that of 1st-year residents (41.8% and 48.2%, respectively, vs. 43.3%, <i>P</i> = 0.608 and 0.079, respectively) but lower performance than that of 2nd- to 4th-year residents (vs. 56.0%-63.9%, all <i>P</i> ≤ 0.005). For text-only questions, GPT-4 Turbo and GPT-4o performed better than residents across all years (69.0% and 77.9%, respectively, vs. 44.7%-57.5%, all <i>P</i> ≤ 0.039). Performance on the English- and Korean-version questions showed no significant differences for either model (all <i>P</i> ≥ 0.275).</p><p><strong>Conclusion: </strong>GPT-4o outperformed the GPT-4 Turbo in all question types. On image-based questions, both models' performance matched that of 1st-year residents but was lower than that of higher-year residents. Both models demonstrated superior performance compared to residents for text-only questions. The models showed consistent performances across English and Korean inputs.</p>","PeriodicalId":17881,"journal":{"name":"Korean Journal of Radiology","volume":" ","pages":"524-531"},"PeriodicalIF":4.4,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12123083/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144024638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Potential of C-X-C-Chemokine-Receptor-Type-4-Directed PET/CT Using [¹⁸F]AlF-NOTA-QHY-04 in Identifying Molecular Subtypes of Small Cell Lung Cancer.","authors":"Yuxi Luo, Kai Cheng, Jingru Liu, Jinli Pei, Shengnan Xu, Xinzhi Zhao, Shijie Wang, Kunlong Zhao, Wanhu Li, Jie Liu, Jinming Yu","doi":"10.3348/kjr.2024.1266","DOIUrl":"10.3348/kjr.2024.1266","url":null,"abstract":"<p><strong>Objective: </strong>Molecular subtyping of small-cell lung cancer (SCLC) has major implications for prognostic relevance and treatment guidance. This study aimed to explore the feasibility of a novel tracer targeting C-X-C-chemokine-receptor-type-4 (CXCR4) for distinguishing different SCLC subtypes.</p><p><strong>Materials and methods: </strong>Thirty-five patients with pathologically confirmed SCLC were enrolled in this prospective study. Immunohistochemical staining was performed to classify the molecular subtypes into SCLC-A, SCLC-N, SCLC-P, and SCLC-I. [¹⁸F]AlF-NOTA-QHY-04 PET/CT parameters were obtained, including the maximum, mean, and peak standard uptake values (SUV_max, SUV_mean, and SUV_peak, respectively) and the ratios of tumors (T) and normal tissues (NT) based on the SUV_max (T/NT). These parameters were compared among the molecular subtypes. A receiver operating characteristic (ROC) curve was used to analyze the performance of the parameters for distinguishing SCLC-N from other subtypes and neuroendocrine (NE) subtypes (SCLC-A and SCLC-N) from non-NE subtypes (SCLC-P and SCLC-I).</p><p><strong>Results: </strong>The molecular subtypes were SCLC-A (n = 17), SCLC-N (n = 6), SCLC-P (n = 7), and SCLC-I (n = 5). The SCLC-N subtype exhibited significantly higher uptake in both primary tumors and lymph node metastases than the other three subtypes (<i>P</i> < 0.05). When SCLC-N was compared with the other three subtypes combined (referred to as \"other SCLCs\"), all parameters were significantly higher in the SCLC-N group (<i>P</i> < 0.05). ROC analysis showed that these parameters had high accuracy in distinguishing SCLC-N from other SCLCs (area under ROC curve: 0.868-0.948 for primary tumors and 0.783-0.888 for lymph node metastases). Compared with the non-NE group, the SUV_max, SUV_mean, and T/NT_lung were significantly higher in the NE group for primary tumors. ROC analysis showed moderate accuracy in distinguishing between the NE and non-NE groups (ROC area: 0.692-0.786 for primary tumors and 0.692-0.815 for lymph node metastases).</p><p><strong>Conclusion: </strong>Our preliminary findings indicate that CXCR4-directed PET/CT imaging using [¹⁸F]AlF-NOTA-QHY-04 may differentiate between SCLC-N and other molecular subtypes and between NE and non-NE subtypes of SCLC.</p>","PeriodicalId":17881,"journal":{"name":"Korean Journal of Radiology","volume":"26 6","pages":"593-603"},"PeriodicalIF":4.4,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12123077/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144159816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Overview of South Korean Guidelines for Approval of Large Language or Multimodal Models as Medical Devices: Key Features and Areas for Improvement.","authors":"Seong Ho Park, Geraldine Dean, Ernest Montañà Ortiz, Joon-Il Choi","doi":"10.3348/kjr.2025.0257","DOIUrl":"10.3348/kjr.2025.0257","url":null,"abstract":"","PeriodicalId":17881,"journal":{"name":"Korean Journal of Radiology","volume":" ","pages":"519-523"},"PeriodicalIF":4.4,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12123075/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144032417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}