Sung Il Hwang

사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.

Background: Frontier text-to-image models can synthesise radiologic images of high realism, raising the question of whether expert radiologists can serve as a provenance safeguard for the medical image record. Methods: We conducted a prospective, pre-registered visual Turing test in which 60 invited Korean board-certified radiology faculty and trainees judged authentic (teaching-repository) and AI-generated radiologic images from a locked pool of 241 displayable cells (82 entities; nine subspecialties; six modalities; 60 readers x 60 trials = 3,600 reader–image observations) produced by two contemporary commercial generators. The primary endpoint was the confidence-weighted, reader-averaged multi-reader multi-case area under the curve for AI versus authentic images, conditional on the locked image pool; the key secondary endpoint was the Faculty-minus-Junior difference under a two one-sided tests equivalence framework. The pre-specified statistical analysis plan was registered on the Open Science Framework before data lock. Findings: All 60 readers completed the test. The pooled confidence-weighted area under the curve was 0.71 (95% CI, 0.69 to 0.74), above the null value of 0.5 but within the pre-specified modest tier (0.60 to 0.75). The Faculty-minus-Junior contrast was 0.04 (95% CI, −0.02 to 0.10), including zero, and the two one-sided tests established equivalence within the +/−0.10 margin. No reader stratum and no pre-specified sensitivity analysis reached the deployable-classifier threshold (area under the curve >= 0.75). Interpretation: In this single-country cohort, expert radiologists distinguished frontier-generated from authentic radiologic images only modestly, without a meaningful expertise gradient (equivalence within +/−0.10) and with no reader stratum reaching a standalone provenance safeguard. These findings support radiology AI-literacy training and pipeline-level provenance safeguards rather than reliance on reader judgment, and warrant retesting in an independent reader cohort. Funding: This research was supported by a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (grant number: RS-2025-02213531).

Hwang SI, et al. Korean J Radiol. 2026 Oct;27(10):929-935. https://doi.org/10.3348/kjr.2026.0914

Purpose: This study aimed to evaluate the predictive value of apparent diffusion coefficient (ADC) values from magnetic resonance imaging (MRI) in assessing pathologic response to neoadjuvant chemotherapy (NAC) in patients with muscle-invasive bladder cancer (MIBC) and the optimal cutoff value of ADC for predicting NAC response.Materials and Methods: Among 582 patients who underwent radical cystectomy between December 2011 and December 2024, we included 146 patients who received preoperative NAC and pretreatment MRI. Pathologic response was determined based on the surgical pathology results: patients with pathologic stage >pT2 and/or presence of nodal involvement (N+) were classified as nonresponders, while those with ≤pT2 and no nodal involvement (N0) were classified as responders. MRI-derived ADC values were compared between the 2 groups. The receiver operating characteristic (ROC) curve was used to determine the optimal cutoff value for predicting NAC response. Multivariate logistic regression analysis using preoperative parameter was performed and Kaplan-Meier survival analysis were utilized to assess overall survival (OS) and cancer-specific survival (CSS) according to NAC response.Results: Among the 146 patients, 90 (61.6%) were classified as responders, 56 (38.4%) were nonresponders. The mean ADC value was significantly higher in responders (1,100.35±249.12 mm2/sec) than in nonresponders (763.95±118.97 mm2/sec, p<0.001). ROC analysis demonstrated an area under the curve of 0.69, with an optimal cutoff value of 845.0 mm2/sec. Multivariate logistic regression identified ADC value as an independent predictor of NAC response (odds ratio, 1.025; 95% confidence interval, 1.006–1.043; p=0.008). During median follow-up 30.3 months, Kaplan-Meier analysis revealed that responders had significantly better 5-year OS (80.8% vs. 45.9%) and 5-year CSS (92.6% vs. 54.5%), with log-rank test p<0.001.Conclusion: MRI-derived ADC values are a reliable imaging biomarker for predicting pathologic response to NAC in MIBC. Further validation in large-scale prospective studies is required to confirm these findings.

사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.

Introduction: The population of the Republic of Korea often experiences heat-related illnesses during summer that are exacerbated by significant variations. With rising temperatures attributed to global warming and other environmental changes within the military, combined with the military medical services’ mission to uphold combat capabilities and promote health, it has become crucial to accurately understand the status of heat-related illnesses and integrate more comprehensive and systematic preventive measures. This study aimed to analyze data on heat-related illnesses between 2018 and 2022 to assess and reflect on the said diseases in the South Korean Military. Materials and Methods: We performed a secondary analysis using data provided by the Defense Medical Statistic Information System. This single-institution retrospective, cross-sectional study was approved by the Institutional Review Board of the Armed Forces Medical Command (approval number: AFMC-2023-11-001). Results: Over the past 5 years, the annual number of soldiers treated for heat-related illnesses, whether as outpatients or inpatients, at division medical facilities and military hospitals ranged from 846 to 1,250 cases per year. The proportion of severe cases fluctuates annually between 1.1% and 1.8%. Notably, 94 to 96% of all heat-related illnesses were recorded between May and September, with peak rates in July and August. Conclusion: The army reported the highest number of heat-related illnesses among military branches, with soldiers comprising the majority of cases. This highlights the urgent need for enhanced heat illness prevention measures within army ranks. Notably, the incidence of these illnesses peaked during July and August, underlining the critical periods for intensified preventive efforts.

Purpose To evaluate magnetic resonance imaging (MRI) findings for distinguishing ovarian lymphomas from other solid ovarian tumors. Methods This retrospective multicenter study included 14 women (median age, 46.5 years; range, 26–81 years) with surgically proven ovarian lymphoma and 28 women with solid ovarian tumors other than lymphoma. We conducted a subjective image analysis of factors including laterality, shape, composition, T2 signal intensity (SI), heterogeneity, diffusion restriction, enhancement, and presence of peripheral follicles. A generalized estimating equation was used to identify MRI findings that could be used to distinguish ovarian lymphomas from other solid ovarian tumors. Diagnostic performance of the identified MRI findings was assessed using the area under the receiver-operating characteristic curve (AUC). Results Ovarian lymphoma more frequently showed homogeneous high SI on T2-weighted imaging (81.8% vs. 19.4%, P < 0.001) and peripheral ovarian follicles (40.9% vs. 8.3%, P = 0.01) than other ovarian solid tumors did. Bilaterality, shape, size, diffusion restriction, and enhancement did not differ between the two groups (P > 0.05 for all). Homogeneous high SI on T2-weighted imaging was the only independent MRI finding (OR = 15.19; 95% CI 3.15–73.33; P = 0.001) in the multivariable analysis. Homogeneous high SI on T2-weighted imaging yielded an AUC of 0.82 with a sensitivity of 81.8% and specificity of 80.6% in distinguishing ovarian lymphomas from other solid ovarian tumors. Conclusion Homogeneous high signal intensity on T2-weighted imaging was helpful in distinguishing ovarian lymphomas from other solid ovarian tumors. Peripheral ovarian follicles might be an additional clue that suggests a diagnosis of ovarian lymphoma. Graphical abstract

Purpose: The objective of this study was to evaluate pain and image quality associated with the use of two different ultrasound transducers.Methods: Fifty healthy male participants aged 30 years or older were prospectively enrolled. All ultrasound procedures were performed using a V8 machine (Samsung Medison, Seoul, Korea) equipped with EA2-11 (conventional) and miniER7 (small-caliber) transrectal transducers, operated by a single genitourinary radiologist. To minimize bias, one group of volunteers underwent ultrasonography with the conventional transducer first, followed by the small transducer. For the remaining participants, the examinations were performed in the opposite order. Ultrasonography, including the measurement of total prostate and transitional zone volumes, was conducted in accordance with standard practice. After testing with both probes, participants were asked to rate their pain on a 10-point numerical rating scale (NRS). A radiologist then evaluated the quality of the images acquired with each probe using a 5-point numeric scale and compared the prostate volume measurements obtained by each method.Results: The mean NRS scores associated with the conventional and small transducers were 4.7±1.8 and 2.7±1.2, respectively (P0.05). The whole prostate gland volume as measured with the conventional transducer (mean±standard deviation, 24.2±9.1 mL) was greater than the measurement (22.1±8.7 mL) obtained with the small-caliber transducer (P<0.05). However, only two of the 50 whole gland volume measurements differed by more than two standard deviations.Conclusion: The use of a small transrectal probe significantly reduced pain without compromising image quality.