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 aimed to characterize the clinical patterns and severity of brain injury in neonates who survived extracorporeal membrane oxygenation (ECMO) therapy for acute respiratory failure during the neonatal period, to evaluate their short-term neurodevelopmental outcomes, and to identify the factors associated with these outcomes. Methods: We retrospectively reviewed the medical records of neonates who survived ECMO between 2018 and 2024. Based on brain magnetic resonance imaging (MRI) findings, the patients were classified into two groups: no/mild and moderate/severe brain injury. Neurodevelopmental outcomes were assessed at 12–40 months of age using the Bayley Scale of Infant Development II/III and/or the Korean Developmental Screening Test. Results: Among the 19 neonates included in the study, 18 (94.7%) showed varying degrees of brain injury on MRI (mild: 12, moderate: 1, severe: 5). Neonates with moderate/severe brain injury had significantly longer durations of ECMO support and extended durations of mechanical ventilation and were more likely to receive continuous renal replacement therapy than those with no or mild injury. Developmental delay was identified in 36.8% of survivors and was significantly associated with prolonged mechanical ventilation, longer neonatal intensive care unit stays, and a higher incidence of seizures. Conclusion Brain injury is frequently observed on MRI in neonates treated with ECMO. However, its direct association with adverse neurodevelopmental outcomes is not definitive. Since MRI findings alone cannot predict developmental outcomes, clinical and environmental factors should be integrated into prognostic assessments.

Purpose: Congenital hypothyroidism (CH) is a major preventable cause of intellectual disability, particularly in very low birth weight (VLBW) infants, who are at increased risk due to hypothalamic-pituitary-thyroid axis immaturity. Early differentiation between transient CH (TCH) and permanent CH (PCH) is crucial to optimize L-thyroxine (LT4) treatment duration. This study aimed to determine the incidence of PCH among Korean VLBW infants and to identify clinical factors that may aid in distinguishing TCH from PCH. Methods: This retrospective cohort study included VLBW infants diagnosed with CH and treated with LT4 at a single tertiary neonatal intensive care unit between 2011 and 2020. Infants requiring LT4 beyond 3 years were classified as PCH, while those who discontinued earlier were considered TCH. Clinical characteristics, neonatal morbidities, and thyroid-related parameters were compared between the groups. Results: Among 1,292 VLBW infants, 122 (9.4%) were diagnosed with CH. After excluding deaths and those lost to follow-up, 73 infants were included in the final analysis (TCH, n=50; PCH, n=23). The PCH group had a significantly higher mean gestational age and greater LT4 requirements at both 12 and 36 months of age. Major anomalies were more frequently observed in PCH infants, including congenital heart defects. In multivariate analysis, higher gestational age, the presence of major anomalies, screening thyroid-stimulating hormone (TSH) >10 μIU/mL, and higher LT4 dose at 36 months were significantly associated with PCH. Conclusion The incidence of PCH in Korean VLBW infants was relatively higher than that reported in previous studies studies. Screening TSH level and LT4 dose requirements may support individualized follow-up and help distinguish PCH from TCH.

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 aimed to characterize the clinical patterns and severity of brain injury in neonates who survived extracorporeal membrane oxygenation (ECMO) therapy for acute respiratory failure during the neonatal period, to evaluate their short-term neurodevelopmental outcomes, and to identify the factors associated with these outcomes. Methods: We retrospectively reviewed the medical records of neonates who survived ECMO between 2018 and 2024. Based on brain magnetic resonance imaging (MRI) findings, the patients were classified into two groups: no/mild and moderate/severe brain injury. Neurodevelopmental outcomes were assessed at 12–40 months of age using the Bayley Scale of Infant Development II/III and/or the Korean Developmental Screening Test. Results: Among the 19 neonates included in the study, 18 (94.7%) showed varying degrees of brain injury on MRI (mild: 12, moderate: 1, severe: 5). Neonates with moderate/severe brain injury had significantly longer durations of ECMO support and extended durations of mechanical ventilation and were more likely to receive continuous renal replacement therapy than those with no or mild injury. Developmental delay was identified in 36.8% of survivors and was significantly associated with prolonged mechanical ventilation, longer neonatal intensive care unit stays, and a higher incidence of seizures. Conclusion Brain injury is frequently observed on MRI in neonates treated with ECMO. However, its direct association with adverse neurodevelopmental outcomes is not definitive. Since MRI findings alone cannot predict developmental outcomes, clinical and environmental factors should be integrated into prognostic assessments.

Purpose: Congenital hypothyroidism (CH) is a major preventable cause of intellectual disability, particularly in very low birth weight (VLBW) infants, who are at increased risk due to hypothalamic-pituitary-thyroid axis immaturity. Early differentiation between transient CH (TCH) and permanent CH (PCH) is crucial to optimize L-thyroxine (LT4) treatment duration. This study aimed to determine the incidence of PCH among Korean VLBW infants and to identify clinical factors that may aid in distinguishing TCH from PCH. Methods: This retrospective cohort study included VLBW infants diagnosed with CH and treated with LT4 at a single tertiary neonatal intensive care unit between 2011 and 2020. Infants requiring LT4 beyond 3 years were classified as PCH, while those who discontinued earlier were considered TCH. Clinical characteristics, neonatal morbidities, and thyroid-related parameters were compared between the groups. Results: Among 1,292 VLBW infants, 122 (9.4%) were diagnosed with CH. After excluding deaths and those lost to follow-up, 73 infants were included in the final analysis (TCH, n=50; PCH, n=23). The PCH group had a significantly higher mean gestational age and greater LT4 requirements at both 12 and 36 months of age. Major anomalies were more frequently observed in PCH infants, including congenital heart defects. In multivariate analysis, higher gestational age, the presence of major anomalies, screening thyroid-stimulating hormone (TSH) >10 μIU/mL, and higher LT4 dose at 36 months were significantly associated with PCH. Conclusion The incidence of PCH in Korean VLBW infants was relatively higher than that reported in previous studies studies. Screening TSH level and LT4 dose requirements may support individualized follow-up and help distinguish PCH from TCH.

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 aimed to characterize the clinical patterns and severity of brain injury in neonates who survived extracorporeal membrane oxygenation (ECMO) therapy for acute respiratory failure during the neonatal period, to evaluate their short-term neurodevelopmental outcomes, and to identify the factors associated with these outcomes. Methods: We retrospectively reviewed the medical records of neonates who survived ECMO between 2018 and 2024. Based on brain magnetic resonance imaging (MRI) findings, the patients were classified into two groups: no/mild and moderate/severe brain injury. Neurodevelopmental outcomes were assessed at 12–40 months of age using the Bayley Scale of Infant Development II/III and/or the Korean Developmental Screening Test. Results: Among the 19 neonates included in the study, 18 (94.7%) showed varying degrees of brain injury on MRI (mild: 12, moderate: 1, severe: 5). Neonates with moderate/severe brain injury had significantly longer durations of ECMO support and extended durations of mechanical ventilation and were more likely to receive continuous renal replacement therapy than those with no or mild injury. Developmental delay was identified in 36.8% of survivors and was significantly associated with prolonged mechanical ventilation, longer neonatal intensive care unit stays, and a higher incidence of seizures. Conclusion Brain injury is frequently observed on MRI in neonates treated with ECMO. However, its direct association with adverse neurodevelopmental outcomes is not definitive. Since MRI findings alone cannot predict developmental outcomes, clinical and environmental factors should be integrated into prognostic assessments.

Purpose: Congenital hypothyroidism (CH) is a major preventable cause of intellectual disability, particularly in very low birth weight (VLBW) infants, who are at increased risk due to hypothalamic-pituitary-thyroid axis immaturity. Early differentiation between transient CH (TCH) and permanent CH (PCH) is crucial to optimize L-thyroxine (LT4) treatment duration. This study aimed to determine the incidence of PCH among Korean VLBW infants and to identify clinical factors that may aid in distinguishing TCH from PCH. Methods: This retrospective cohort study included VLBW infants diagnosed with CH and treated with LT4 at a single tertiary neonatal intensive care unit between 2011 and 2020. Infants requiring LT4 beyond 3 years were classified as PCH, while those who discontinued earlier were considered TCH. Clinical characteristics, neonatal morbidities, and thyroid-related parameters were compared between the groups. Results: Among 1,292 VLBW infants, 122 (9.4%) were diagnosed with CH. After excluding deaths and those lost to follow-up, 73 infants were included in the final analysis (TCH, n=50; PCH, n=23). The PCH group had a significantly higher mean gestational age and greater LT4 requirements at both 12 and 36 months of age. Major anomalies were more frequently observed in PCH infants, including congenital heart defects. In multivariate analysis, higher gestational age, the presence of major anomalies, screening thyroid-stimulating hormone (TSH) >10 μIU/mL, and higher LT4 dose at 36 months were significantly associated with PCH. Conclusion The incidence of PCH in Korean VLBW infants was relatively higher than that reported in previous studies studies. Screening TSH level and LT4 dose requirements may support individualized follow-up and help distinguish PCH from TCH.