Seong-Hyeon Kang

Background/Objectives: Most brain magnetic resonance imaging (MRI) is performed in supine position, although posture may influence cerebrovascular signal characteristics through gravity-related physiological changes. However, posture-dependent vascular signal alterations on low-field MRI have not been sufficiently quantified. This study aimed to quantify posture-related internal carotid artery (ICA) signal alterations using low-field MRI by comparing seated and supine images with intensity-, noise-, and texture-based metrics. Methods: Nine healthy adults (20–69 years old; one female) underwent 0.25 T tilting MRI in supine and seated postures. 3D gradient echo T1-weighted images were obtained. The bilateral ICA regions of interest (ROI) and adjacent reference ROI were manually delineated. The signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), signal intensity ratio (SIR), gray-level co-occurrence matrix (GLCM) texture features (contrast, correlation, energy, and homogeneity) were extracted and compared between postures using Wilcoxon signed-rank tests. Results: Seated posture produced significantly higher ICA signal intensity metrics than the supine posture, with increased SNR (median 17.11 vs. 13.48), CNR (median 21.94 vs. 18.36), and SIR (median 10.84 vs. 9.54) (p = 0.004). GLCM texture analysis demonstrated a significant decrease in contrast in the seated position (median 62.01 vs. 145.92; p = 0.004), whereas correlation, energy, and homogeneity showed no significant between-posture differences. Conclusions: Low-field MRI was sensitive to posture-dependent ICA signal alterations. ICA-based metrics may provide quantitative markers of gravity-related cerebrovascular adaptation.

Brain magnetic resonance imaging (MRI) is highly susceptible to motion artifacts that degrade fine structural details and undermine quantitative analysis. Conventional U-Net-based deep learning approaches for motion artifact reduction typically operate only in the image domain and are often trained on data with simplified motion patterns, thereby limiting physical plausibility and generalization. We propose Sim-DDNet, a simulation-data-based dual-domain network that combines k-space-based motion simulation with a joint image-k-space reconstruction architecture. Motion-corrupted data were generated from T2-weighted Alzheimer’s Disease Neuroimaging Initiative brain MR scans using a k-space replacement scheme with three to five random rotational and translational events per volume, yielding 69,283 paired samples (49,852/6969/12,462 for training/validation/testing). Sim-DDNet integrates a real-valued U-Net-like image branch and a complex-valued k-space branch using cross attention, FiLM-based feature modulation, soft data consistency, and composite loss comprising L1, structural similarity index measure (SSIM), perceptual, and k-space-weighted terms. On the independent test set, Sim-DDNet achieved a peak signal-to-noise ratio of 31.05 dB, SSIM of 0.85, and gradient magnitude similarity deviation of 0.077, consistently outperforming U-Net and U-Net++ across all three metrics while producing less blurring, fewer residual ghost/streak artifacts, and reduced hallucination of non-existent structures. These results indicate that dual-domain, data-consistency-aware learning, which explicitly exploits k-space information, is a promising approach for physically plausible motion artifact correction in brain MRI.

Diffusion-weighted magnetic resonance (DWMR) images were acquired using a custom-designed, 3D-printed breast-mimicking phantom. The smoothing factor of the non-local means (NLM) algorithm was then optimized for noise reduction. Phantoms were fabricated using polylactic acid, polyethylene terephthalate, and various concentrations of polyvinylpyrrolidone. DWMR images were obtained across b-values ranging from zero to 2000 s/mm². Based on image contrast, the NLM algorithm was applied to the b = 1000 s/mm² image, testing smoothing factors from 0.001 to 0.150. The NLM algorithm’s performance was quantitatively evaluated using a single DWMR image acquired from this custom phantom. At the optimized smoothing factor, the signal-to-noise ratio (SNR) improved from 96.87 ± 3.42 to 215.81 ± 4.18, and the contrast-to-noise ratio (CNR) from 43.63 ± 2.97 to 131.98 ± 3.56, representing 2.22-fold and 3.02-fold enhancements, respectively. No formal statistical tests were conducted as the analysis was based on a single acquisition. The optimized NLM algorithm also outperformed conventional denoising methods—median, Wiener, and total variation—in both noise suppression and contrast preservation. These findings suggest that the NLM algorithm with optimized parameters is likely to be more effective than existing approaches for enhancing breast DWMR image quality. However, further validation using in vivo patient datasets is essential to confirm its diagnostic utility and clinical generalizability because of the absence of tissue heterogeneity, motion, and physiological noise in the phantom environment.

The purpose of this study was to propose a deep learning-based model for the super-resolution reconstruction of stained light microscopy images. To achieve this, perceptual loss was applied to the generator to reflect multichannel signal intensity, distribution, and structural similarity. A nested U-Net architecture was employed to address the representational limitations of the conventional U-Net. For quantitative evaluation, the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and correlation coefficient (CC) were calculated. In addition, intensity profile analysis was performed to assess the model’s ability to restore the boundary signals more precisely. The experimental results demonstrated that the proposed model outperformed both the signal and structural restoration compared to single U-Net and U-Net-based generative adversarial network (GAN) models. Consequently, the PSNR, SSIM, and CC values demonstrated relative improvements of approximately 1.017, 1.023, and 1.010 times, respectively, compared to the input images. In particular, the intensity profile analysis confirmed the effectiveness of the nested U-Net-based generator in restoring cellular boundaries and structures in the stained microscopy images. In conclusion, the proposed model effectively enhanced the resolution of stained light microscopy images acquired in a multichannel format.

The purpose of this study is to evaluate the various control parameters of a modeled fast non-local means (FNLM) noise reduction algorithm which can separate color channels in light microscopy (LM) images. To achieve this objective, the tendency of image characteristics with changes in parameters, such as smoothing factors and kernel and search window sizes for the FNLM algorithm, was analyzed. To quantitatively assess image characteristics, the coefficient of variation (COV), blind/referenceless image spatial quality evaluator (BRISQUE), and natural image quality evaluator (NIQE) were employed. When high smoothing factors and large search window sizes were applied, excellent COV and unsatisfactory BRISQUE and NIQE results were obtained. In addition, all three evaluation parameters improved as the kernel size increased. However, the kernel and search window sizes of the FNLM algorithm were shown to be dependent on the image processing time (time resolution). In conclusion, this work has demonstrated that the FNLM algorithm can effectively reduce noise in LM images, and parameter optimization is important to achieve the algorithm’s appropriate application.