Objective: To prospectively evaluate the effect of accelerated deep learning-based reconstruction (Accel-DL) on improving brain magnetic resonance imaging (MRI) quality and reducing scan time compared to that in conventional MRI. Materials and Methods: This study included 150 participants (51 male; mean age 57.3 ± 16.2 years). Each group of 50 participants was scanned using one of three 3T scanners from three different vendors. Conventional and Accel-DL MRI images were obtained from each participant and compared using 2D T1- and T2-weighted and 3D gradient-echo sequences. Accel-DL acquisition was achieved using optimized scan parameters to reduce the scan time, with the acquired images reconstructed using U-Net-based software to transform low-quality, undersampled k-space data into high-quality images. The scan times of Accel-DL and conventional MRI methods were compared. Four neuroradiologists assessed the overall image quality, structural delineation, and artifacts using Likert scale (5- and 3-point scales). Inter-reader agreement was assessed using Fleiss’ kappa coefficient. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated, and volumetric quantification of regional structures and white matter hyperintensities (WMHs) was performed. Results: Accel-DL showed a mean scan time reduction of 39.4% (range, 24.2%–51.3%). Accel-DL improved overall image quality (3.78 ± 0.71 vs. 3.36 ± 0.61, P < 0.001), structure delineation (2.47 ± 0.61 vs. 2.35 ± 0.62, P < 0.001), and artifacts (3.73 ± 0.72 vs. 3.71 ± 0.69, P = 0.016). Inter-reader agreement was fair to substantial (κ = 0.34–0.50). SNR and CNR increased in Accel-DL (82.0 ± 23.1 vs. 31.4 ± 10.8, P = 0.02; 12.4 ± 4.1 vs. 4.4 ± 11.2, P = 0.02). Bland-Altman plots revealed no significant differences in the volumetric measurements of 98.2% of the relevant regions, except in the deep gray matter, including the thalamus. Five of the six lesion categories showed no significant differences in WMH segmentation, except for leukocortical lesions (r = 0.64 ± 0.29). Conclusion Accel-DL substantially reduced the scan time and improved the quality of brain MRI in both spin-echo and gradientecho sequences without compromising volumetry, including lesion quantification.

Breast cancer is the most common cancer in women worldwide, and its early detection is critical for improving survival outcomes. As a diagnostic and screening tool, mammography can be less effective owing to the masking effect of fibroglandular tissue, but breast US has good sensitivity even in dense breasts. However, breast US is highly operator dependent, highlighting the need for artificial intelligence (AI)-driven solutions. Unlike other modalities, US is performed using a handheld device that produces a continuous real-time video stream, yielding 12000–48000 frames per examination. This can be significantly challenging for AI development and requires real-time AI inference capabilities. In this review, we classified AI solutions as computer-aided diagnosis and computer-aided detection to facilitate a functional understanding and review commercial software supported by clinical evidence.In addition, to bridge healthcare gaps and enhance patient outcomes in geographically under resourced areas, we propose a novel framework by reviewing the existing AI-based triage workflows including mobile ultrasound.

High-flow nasal cannula (HFNC) is a noninvasive respiratory support system that delivers air that is heated at 31°C−38°C, humidified 100%, and oxygen-enriched at a constant high flow rate of 15−60 L/min. Because of its numerous physiological benefits, convenience, and minimal side effects, HFNC has been increasingly used over the past decade in patients with acute hypoxemic respiratory failure, yet the clinical benefits of long-term HFNC remain uncertain. Several studies have suggested its potential use as an alternative home oxygen therapy for patients with chronic stable lung diseases, such as chronic obstructive pulmonary disease (COPD), interstitial lung disease, and bronchiectasis. The use of long-term home HFNC in patients with chronic respiratory failure is an emerging area with promising potential. Despite limited clinical research, this review aims to describe the physiology of HFNC use and summarize the current evidence on its long-term application, to provide healthcare providers with insights and perspectives on the potential role of long-term home HFNC.

Purpose: This study evaluated the educational impact of an artificial intelligence (AI)–based decision support system for breast ultrasonography (US) on medical professionals not specialized in breast imaging. Methods: In this multi-case, multi-reader study, educational materials, including American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) descriptors, were provided alongside corresponding AI results during training. The AI system presented results in the form of AIheatmaps, AI scores, and AI-provided BI-RADS assessment categories. Forty-two readers evaluated the test set in three sessions: the first session (S1) occurred before the educational intervention, the second session (S2) followed education without AI assistance, and the third session (S3) took place after education with AI assistance. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and overall performance, were compared between the sessions. Results: The mean sensitivity increased from 66.5% (95% confidence interval [CI], 59.2% to 73.7%) to 88.7% (95% CI, 84.1% to 93.3%), with a statistically significant difference (P<0.001), and the AUC non-significantly increased from 0.664 (95% CI, 0.606 to 0.723) to 0.684 (95% CI, 0.620 to 0.748) (P=0.300). Both measures were higher in S2 than in S1. The AI-achieved AUC was comparable to that of the expert reader (0.747 [95% CI, 0.640 to 0.855] vs. 0.803 [95% CI, 0.706 to 0.900], P=0.217). Additionally, with AI assistance, the mean AUC for inexperienced readers was not significantly different from that of the expert reader (0.745 [95% CI, 0.660 to 0.830] vs. 0.803 [95% CI, 0.706 to 0.900], P=0.120). Conclusion The mean AUC and sensitivity improved after incorporating AI into breast US education and interpretation. AI systems with high-level performance for breast US can potentially be used as educational tools in the interpretation of breast US images.

Objective: As the demand for community mental health services continues to grow, the need for well-equipped and organized services has become apparent. This study aimed to optimize the roles and infrastructure of mental health services, by establishing, among other initiatives, standardized operating models. Methods: The study was conducted in multiple phases from May 12, 2021, to December 29, 2021. Stakeholders within South Korea and metropolitan mental health welfare centers were targeted, but addiction management support centers, including officials, patients, and their families, were integrated as well. A literature review and survey, focus group interviews, a Delphi survey, and expert consultation contributed to comprehensive revisions and improvements of the mental health service model. Results: The proposed model for community mental health welfare centers emphasizes the expansion of personnel and infrastructure, with a focus on severe mental illnesses and suicide prevention. The model for metropolitan mental health welfare centers delineates essential tasks in areas such as project planning and establishment, community research, and education about severe mental illnesses. The establishment of a 24-hour emergency intervention center was a crucial feature. In the integrated addiction support center model, the need to promote addiction management is defined as an essential task and the establishment of national governance for addiction policies is recommended. Conclusion This study proposed standard operating models for three types of mental health service centers. To meet the increasing need for community care, robust mental health service delivery systems are of primary importance.

The prevalence of prediabetes has steadily increased in Korea, driven by rising obesity rates and lifestyle changes. A structured lifestyle modification program has been shown to significantly reduce the prevalence of diabetes among adults with prediabetes, with this effect sustained over time. Lifestyle modifications including medical nutrition, exercise, and behavioral psychological therapy are effective for preventing and managing diabetes, with medical nutrition therapy playing a crucial role. This study reviews the latest academic guidelines and medical nutrition therapy for diabetes prevention and to introduce the KDPS-hLSM (Korean Diabetes Prevention Study hospital-based lifestyle modification).

Gestational diabetes mellitus (GDM) affects 2~10% of pregnant women worldwide, with an increasing prevalence in South Korea that reached 18.2% in 2021. Unmanaged GDM can lead to serious complications for both mother and fetus. Effective management requires blood glucose monitoring and lifestyle changes, but many women lack sufficient knowledge about the condition. This study explores the use of smart platforms, like continuous glucose monitoring devices and mobile apps, to improve GDM education. Devices such as Dexcom G7 and FreeStyle Libre 2 enable real-time blood glucose monitoring, while apps like Health2Sync help patients share data with healthcare providers. Although these technologies offer major benefits, challenges remain in patient engagement, data accuracy, and accessibility. In conclusion, while smart platforms can enhance GDM management, they must be combined with ongoing professional support to improve health outcomes.