Koung Mi Kang

Purpose: Deep learning reconstruction is a promising technique for improving head CT image quality compared to traditional methods. The purpose of this study was to compare image quality and the potential diagnostic impact of vendor-agnostic deep-learning reconstruction (DLR) versus hybrid iterative reconstruction (IR) for the evaluation of acute ischemic stroke on noncontrast head computed tomography (CT). Methods: This single-institution retrospective study included 100 patients (mean age 69.6 years; 44 women) who visited the emergency department with suspected acute stroke and underwent noncontrast head CT between November 2021 and November 2022. Fifty patients were confirmed to have acute infarction lesions via subsequent DWI, while the remaining 50 had negative DWI results. The CT images were reconstructed with both IR and DLR. Four reviewers (two radiology residents and two neuroradiologists) assessed subjective image quality and the conspicuity of acute ischemic lesions on a 5-point scale. Nonparametric comparisons of scores and ROC curve analysis were performed. Results: Compared with IR, DLR resulted in superior overall image quality (4.02 vs. 3.23, p < 0.01). While no significant differences were found in lesion conspicuity according to one neuroradiologist (3.90 vs. 3.70; p = 0.14), other experienced readers reported significantly enhanced conspicuity with DLR(3.60 vs. 3.12, p = 0.014; 3.84 vs. 3.12, p < 0.01; and 4.06 vs. 3.62, p = 0.018, respectively). ROC curve analysis revealed an increase in the area under the curve (AUC) for radiology resident readers (0.888 vs. 0.844, p = 0.002) and a decrease in AUC for neuroradiologists (0.857 vs. 0.911, p = 0.034). Conclusion: Our study demonstrates that DLR offers subjective improvements in image quality, tissue differentiation, and noise reduction. We observed improvement in the diagnostic performance of less experienced radiologists with DLR .

Background: Metformin has been proposed to have neuroprotective benefits, but its effects on AD-related brain changes remain unclear and may be influenced by apolipoprotein E ε4 ( APOE4 ) genotype, a major genetic risk factor for AD. Objective: To examine the association between metformin use and in vivo AD pathologies and to evaluate whether APOE4 status moderates these associations in older adults with type 2 diabetes mellitus (T2DM). Methods: This cross-sectional study used baseline data from 76 non-demented older adults with T2DM (aged 55–90 years), who were enrolled in the Korean Brain Aging Study for Early Diagnosis and Prediction of Alzheimer's Disease (KBASE). The participants underwent comprehensive clinical and neuropsychological assessment and multimodal neuroimaging, including global amyloid- β (Aβ) retention ([ ¹¹ C] PiB-PET), inferior temporal tau deposition ([ ¹⁸ F] AV-1451 PET), AD-signature cortical thickness (AD-CT), and white matter hyperintensity (WMH) volume. Global cognition was assessed using the Consortium to Establish a Registry for Alzheimer's Disease (CERAD) neuropsychological battery. Results: Among 76 participants, 55 (72%) were metformin users and 21 (28%) were non-users. Metformin use was significantly associated with greater AD-CT, but not with Aβ, tau, or WMH volume. A significant interaction between metformin use and APOE4 status was observed with respect to AD-CT. In APOE4 -stratified analyses, metformin use was significantly associated with greater AD-CT and better global cognition among APOE4 non-carriers, but not among carriers. Conclusions: Our findings indicate that metformin use is associated with greater AD-CT—independently of amyloid or tau pathology—particularly among APOE4 non-carriers, and this structural preservation is accompanied by better cognitive outcomes.

Jeon YH, et al. Korean J Radiol. 2026 ;27:e33. https://doi.org/10.3348/kjr.2025.1073

Gihwan Byeon, Min Soo Byun, Dahyun Yi, Hyejin Ahn, Gijung Jung, Bo Kyung Sohn, Joon Hyung Jung, Yoon Young Chang, Kyungtae Kim, Hyeji Choi, Yoon Hee Kim, Yu Kyeong Kim, Koung Mi Kang, Chul-Ho Sohn, Dong Young Lee; for the KBASE Research Group. Clin Psychopharmacol Neurosci 2025;23:256-65. https://doi.org/10.9758/cpn.24.1238

Choi KS, et al. Korean J Radiol. 2025 Jan;26(1):54-64. https://doi.org/10.3348/kjr.2024.0653

Purpose: The time-intensive nature of acquiring 3D T1-weighted MRI and analyzing brain volumetry limits quantitative evaluation of brain atrophy. We explore the feasibility and reliability of deep learning-based accelerated MRI scans for brain volumetry. Methods: This retrospective study collected 3D T1-weighted data using 3T from 42 participants for the simulated acceleration dataset and 48 for the validation dataset. The simulated acceleration dataset consists of three sets at different simulated acceleration levels (Simul-Accel) corresponding to level 1 (65% undersampling), 2 (70%), and 3 (75%). These images were then subjected to deep learning-based reconstruction (Simul-Accel-DL). Conventional images (Conv) without acceleration and DL were set as the reference. In the validation dataset, DICOM images were collected from Conv and accelerated scan with DL-based reconstruction (Accel-DL). The image quality of Simul-Accel-DL was evaluated using quantitative error metrics. Volumetric measurements were evaluated using intraclass correlation coefficients (ICCs) and linear regression analysis in both datasets. The volumes were estimated by two software, NeuroQuant and DeepBrain. Results: Simul-Accel-DL across all acceleration levels revealed comparable or better error metrics than Simul-Accel. In the simulated acceleration dataset, ICCs between Conv and Simul-Accel-DL in all ROIs exceeded 0.90 for volumes and 0.77 for normative percentiles at all acceleration levels. In the validation dataset, ICCs for volumes > 0.96, ICCs for normative percentiles > 0.89, and R² > 0.93 at all ROIs except pallidum demonstrated good agreement in both software. Conclusion: DL-based reconstruction achieves clinical feasibility of 3D T1 brain volumetric MRI by up to 75% acceleration relative to full-sampled acquisition.

Gihwan Byeon, Min Soo Byun, Dahyun Yi, Joon Hyung Jung, Nayeong Kong, Yoonyoung Chang, MUSUNG KEUM, Gijung Jung, Hyejin Ahn, Jun-Young Lee, Yu Kyeong Kim, Koung Mi Kang, Chul-Ho Sohn, Dong Young Lee; for the KBASE Research Group. Clin Psychopharmacol Neurosci 2024;22:610-23. https://doi.org/10.9758/cpn.24.1169