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.

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.

Purpose: This study analyzed the pathological complete response (pCR) rates, long-term outcomes, and biological features of human epidermal growth factor receptor 2 (HER2)-zero, HER2-low, and HER2-positive breast cancer patients undergoing neoadjuvant treatment. Methods: This single-center study included 1,667 patients who underwent neoadjuvant chemotherapy from 2008 to 2014. Patients were categorized by HER2 status, and their clinicopathological characteristics, chemotherapy responses, and recurrence-free survival (RFS) rates were analyzed. Results: Patients with HER2-low tumors were more likely to be older (p = 0.081), have a lower histological grade (p < 0.001), and have hormone receptor (HorR)-positive tumors (p < 0.001). The HER2-positive group exhibited the highest pCR rate (23.3%), followed by the HER2-zero (15.5%) and HER2-low (10.9%) groups. However, the pCR rate did not differ between HER2-low and HER2-zero tumors in the HorR-positive or HorR-negative subgroups.The 5-year RFS rates increased in the following order: HER2-low, HER2-positive, and HER2-zero (80.0%, 77.5%, and 74.5%, respectively) (log-rank test p = 0.017). A significant survival difference between patients with HER2-low and HER2-zero tumors was only identified in HorR-negative tumors (5-year RFS for HER2-low, 74.5% vs. HER2-zero, 66.0%; log-rank test p-value = 0.04). Multivariate survival analysis revealed that achieving a pCR was the most significant factor associated with improved survival (hazard ratio [HR], 4.279; p < 0.001).Compared with HER2-zero, the HRs for HER2-low and HER2-positive tumors were 0.787 (p = 0.042) and 0.728 (p = 0.005), respectively. After excluding patients who received HER2-targeted therapy, patients with HER2-low tumors exhibited better RFS than those with HER2-zero (HR 0.784, p = 0.04), whereas those with HER2-positive tumors exhibited no significant difference compared with those with HER2-low tumors (HR, 0.975; p = 0.953). Conclusion Patients with HER2-low tumors had no significant difference in pCR rate compared to HER2-zero but showed better survival, especially in HorR-negative tumors.Further investigation into biological differences is warranted.

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.

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.

Purpose: This study analyzed the pathological complete response (pCR) rates, long-term outcomes, and biological features of human epidermal growth factor receptor 2 (HER2)-zero, HER2-low, and HER2-positive breast cancer patients undergoing neoadjuvant treatment. Methods: This single-center study included 1,667 patients who underwent neoadjuvant chemotherapy from 2008 to 2014. Patients were categorized by HER2 status, and their clinicopathological characteristics, chemotherapy responses, and recurrence-free survival (RFS) rates were analyzed. Results: Patients with HER2-low tumors were more likely to be older (p = 0.081), have a lower histological grade (p < 0.001), and have hormone receptor (HorR)-positive tumors (p < 0.001). The HER2-positive group exhibited the highest pCR rate (23.3%), followed by the HER2-zero (15.5%) and HER2-low (10.9%) groups. However, the pCR rate did not differ between HER2-low and HER2-zero tumors in the HorR-positive or HorR-negative subgroups.The 5-year RFS rates increased in the following order: HER2-low, HER2-positive, and HER2-zero (80.0%, 77.5%, and 74.5%, respectively) (log-rank test p = 0.017). A significant survival difference between patients with HER2-low and HER2-zero tumors was only identified in HorR-negative tumors (5-year RFS for HER2-low, 74.5% vs. HER2-zero, 66.0%; log-rank test p-value = 0.04). Multivariate survival analysis revealed that achieving a pCR was the most significant factor associated with improved survival (hazard ratio [HR], 4.279; p < 0.001).Compared with HER2-zero, the HRs for HER2-low and HER2-positive tumors were 0.787 (p = 0.042) and 0.728 (p = 0.005), respectively. After excluding patients who received HER2-targeted therapy, patients with HER2-low tumors exhibited better RFS than those with HER2-zero (HR 0.784, p = 0.04), whereas those with HER2-positive tumors exhibited no significant difference compared with those with HER2-low tumors (HR, 0.975; p = 0.953). Conclusion Patients with HER2-low tumors had no significant difference in pCR rate compared to HER2-zero but showed better survival, especially in HorR-negative tumors.Further investigation into biological differences is warranted.

Purpose: This study analyzed the pathological complete response (pCR) rates, long-term outcomes, and biological features of human epidermal growth factor receptor 2 (HER2)-zero, HER2-low, and HER2-positive breast cancer patients undergoing neoadjuvant treatment. Methods: This single-center study included 1,667 patients who underwent neoadjuvant chemotherapy from 2008 to 2014. Patients were categorized by HER2 status, and their clinicopathological characteristics, chemotherapy responses, and recurrence-free survival (RFS) rates were analyzed. Results: Patients with HER2-low tumors were more likely to be older (p = 0.081), have a lower histological grade (p < 0.001), and have hormone receptor (HorR)-positive tumors (p < 0.001). The HER2-positive group exhibited the highest pCR rate (23.3%), followed by the HER2-zero (15.5%) and HER2-low (10.9%) groups. However, the pCR rate did not differ between HER2-low and HER2-zero tumors in the HorR-positive or HorR-negative subgroups.The 5-year RFS rates increased in the following order: HER2-low, HER2-positive, and HER2-zero (80.0%, 77.5%, and 74.5%, respectively) (log-rank test p = 0.017). A significant survival difference between patients with HER2-low and HER2-zero tumors was only identified in HorR-negative tumors (5-year RFS for HER2-low, 74.5% vs. HER2-zero, 66.0%; log-rank test p-value = 0.04). Multivariate survival analysis revealed that achieving a pCR was the most significant factor associated with improved survival (hazard ratio [HR], 4.279; p < 0.001).Compared with HER2-zero, the HRs for HER2-low and HER2-positive tumors were 0.787 (p = 0.042) and 0.728 (p = 0.005), respectively. After excluding patients who received HER2-targeted therapy, patients with HER2-low tumors exhibited better RFS than those with HER2-zero (HR 0.784, p = 0.04), whereas those with HER2-positive tumors exhibited no significant difference compared with those with HER2-low tumors (HR, 0.975; p = 0.953). Conclusion Patients with HER2-low tumors had no significant difference in pCR rate compared to HER2-zero but showed better survival, especially in HorR-negative tumors.Further investigation into biological differences is warranted.

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.

Background: Group genetic counseling has been implemented to meet growing demand.A metaverse platform, in which a society is built and activities are carried out in the virtual world, has not yet been implemented in group genetic counseling. We investigated whether a metaverse platform could be an alternative service-delivery model for group genetic counseling. Methods: Participants (N=131) were divided into three groups: patient (N=45), family (N= 43), and interested (N = 43) groups. Participants entered the metaverse through a link sent to their mobile phones and attended a 20-min group genetic counseling session reviewing hereditary breast cancer, followed by a 10-min question-and-answer period. Results: The overall median score of post-educational knowledge (9.0, range 8.0–10.0) significantly increased compared to that of pre-educational knowledge (6.0, range 3.0– 8.0) (P < 0.001). There was no significant difference in the pre- and post-educational knowledge scores among the three groups (P > 0.05). Most participants (95%) responded that their understanding of hereditary breast cancer had increased after the group genetic counseling session and that their satisfaction was high. The main advantage noted with metaverse was no limit of space and location while attending the session (97%), and the main disadvantage was a possibility of missing content due to an unstable internet connection (67%). Conclusions The metaverse platform would be acceptable as an alternative group genetic counseling service. More studies are needed to investigate how, for whom, and in what circumstances metaverse can be effectively utilized.

Purpose: To analyze changes in refractive error among elementary school children under the age of 13 who visited an outpatient clinic for eye examinations before and after the onset of the COVID-19 pandemic. Methods: A retrospective analysis of medical records was conducted to calculate the spherical equivalent refractive error of the right eye for 3,854 children aged 6 to 12 who attended our ophthalmology department from 2016 to 2023. We analyzed the average refractive error and myopia prevalence by year and subsequently performed a subgroup analysis by dividing the children into two age groups: 6-9 years old and 10-12 years old. To provide insight into long-term trends, data from 4,351 subjects aged 6-12 years from the 4th, 5th (2008-2012), and 7th (2016) Korea National Health and Nutrition Examination Surveys were also analyzed for reference. Results: The mean refractive error for subjects visiting our clinic throughout the study period was -1.51 ± 2.12 D. A trend of increasing myopic values in refractive error was observed from 2017 to 2021, with a more substantial change noted in 2020 compared to other years, though not reaching statistical significance. In the subgroup analysis, the change in refractive error for the 6-9-year-old group was more pronounced in 2020 but did not reach statistical significance, and no specific trend was identified in the 10-12-year-old group. Myopia prevalence exhibited a consistent increase since 2019 in the 6-9 age group, with a higher proportion of moderate myopia in 2020 compared to previous years. Conversely, no distinct trend was observed in the 10-12-year-old group. Conclusions Although statistical significance was not reached, it appears that the increase in indoor activities due to COVID-19 had an impact on the changes in refractive values for elementary school children, especially in the lower grades of elementary school in 2020.