1.Evaluation of Image Quality and Scan Time Efficiency in Accelerated 3D T1-Weighted Pediatric Brain MRI Using Deep Learning-Based Reconstruction
Hyunsuk YOO ; Hee Eun MOON ; Soojin KIM ; Da Hee KIM ; Young Hun CHOI ; Jeong-Eun CHEON ; Joon Sung LEE ; Seunghyun LEE
Korean Journal of Radiology 2025;26(2):180-192
Objective:
This study evaluated the effect of an accelerated three-dimensional (3D) T1-weighted pediatric brain MRI protocol using a deep learning (DL)-based reconstruction algorithm on scan time and image quality.
Materials and Methods:
This retrospective study included 46 pediatric patients who underwent conventional and accelerated, pre- and post-contrast, 3D T1-weighted brain MRI using a 3T scanner (SIGNA Premier; GE HealthCare) at a single tertiary referral center between March 1, 2023, and April 30, 2023. Conventional scans were reconstructed using intensity Filter A (Conv), whereas accelerated scans were reconstructed using intensity Filter A (Fast_A) and a DL-based algorithm (Fast_DL).Image quality was assessed quantitatively based on the coefficient of variation, relative contrast, apparent signal-to-noise ratio (aSNR), and apparent contrast-to-noise ratio (aCNR) and qualitatively according to radiologists’ ratings of overall image quality, artifacts, noisiness, gray-white matter differentiation, and lesion conspicuity.
Results:
The acquisition times for the pre- and post-contrast scans were 191 and 135 seconds, respectively, for the conventional scan. With the accelerated protocol, these were reduced to 135 and 80 seconds, achieving time reductions of 29.3% and 40.7%, respectively. DL-based reconstruction significantly reduced the coefficient of variation, improved the aSNR, aCNR, and overall image quality, and reduced the number of artifacts compared with the conventional acquisition method (all P < 0.05). However, the lesion conspicuity remained similar between the two protocols.
Conclusion
Utilizing a DL-based reconstruction algorithm in accelerated 3D T1-weighted pediatric brain MRI can significantly shorten the acquisition time, enhance image quality, and reduce artifacts, making it a viable option for pediatric imaging.
2.Evaluation of Image Quality and Scan Time Efficiency in Accelerated 3D T1-Weighted Pediatric Brain MRI Using Deep Learning-Based Reconstruction
Hyunsuk YOO ; Hee Eun MOON ; Soojin KIM ; Da Hee KIM ; Young Hun CHOI ; Jeong-Eun CHEON ; Joon Sung LEE ; Seunghyun LEE
Korean Journal of Radiology 2025;26(2):180-192
Objective:
This study evaluated the effect of an accelerated three-dimensional (3D) T1-weighted pediatric brain MRI protocol using a deep learning (DL)-based reconstruction algorithm on scan time and image quality.
Materials and Methods:
This retrospective study included 46 pediatric patients who underwent conventional and accelerated, pre- and post-contrast, 3D T1-weighted brain MRI using a 3T scanner (SIGNA Premier; GE HealthCare) at a single tertiary referral center between March 1, 2023, and April 30, 2023. Conventional scans were reconstructed using intensity Filter A (Conv), whereas accelerated scans were reconstructed using intensity Filter A (Fast_A) and a DL-based algorithm (Fast_DL).Image quality was assessed quantitatively based on the coefficient of variation, relative contrast, apparent signal-to-noise ratio (aSNR), and apparent contrast-to-noise ratio (aCNR) and qualitatively according to radiologists’ ratings of overall image quality, artifacts, noisiness, gray-white matter differentiation, and lesion conspicuity.
Results:
The acquisition times for the pre- and post-contrast scans were 191 and 135 seconds, respectively, for the conventional scan. With the accelerated protocol, these were reduced to 135 and 80 seconds, achieving time reductions of 29.3% and 40.7%, respectively. DL-based reconstruction significantly reduced the coefficient of variation, improved the aSNR, aCNR, and overall image quality, and reduced the number of artifacts compared with the conventional acquisition method (all P < 0.05). However, the lesion conspicuity remained similar between the two protocols.
Conclusion
Utilizing a DL-based reconstruction algorithm in accelerated 3D T1-weighted pediatric brain MRI can significantly shorten the acquisition time, enhance image quality, and reduce artifacts, making it a viable option for pediatric imaging.
3.Evaluation of Image Quality and Scan Time Efficiency in Accelerated 3D T1-Weighted Pediatric Brain MRI Using Deep Learning-Based Reconstruction
Hyunsuk YOO ; Hee Eun MOON ; Soojin KIM ; Da Hee KIM ; Young Hun CHOI ; Jeong-Eun CHEON ; Joon Sung LEE ; Seunghyun LEE
Korean Journal of Radiology 2025;26(2):180-192
Objective:
This study evaluated the effect of an accelerated three-dimensional (3D) T1-weighted pediatric brain MRI protocol using a deep learning (DL)-based reconstruction algorithm on scan time and image quality.
Materials and Methods:
This retrospective study included 46 pediatric patients who underwent conventional and accelerated, pre- and post-contrast, 3D T1-weighted brain MRI using a 3T scanner (SIGNA Premier; GE HealthCare) at a single tertiary referral center between March 1, 2023, and April 30, 2023. Conventional scans were reconstructed using intensity Filter A (Conv), whereas accelerated scans were reconstructed using intensity Filter A (Fast_A) and a DL-based algorithm (Fast_DL).Image quality was assessed quantitatively based on the coefficient of variation, relative contrast, apparent signal-to-noise ratio (aSNR), and apparent contrast-to-noise ratio (aCNR) and qualitatively according to radiologists’ ratings of overall image quality, artifacts, noisiness, gray-white matter differentiation, and lesion conspicuity.
Results:
The acquisition times for the pre- and post-contrast scans were 191 and 135 seconds, respectively, for the conventional scan. With the accelerated protocol, these were reduced to 135 and 80 seconds, achieving time reductions of 29.3% and 40.7%, respectively. DL-based reconstruction significantly reduced the coefficient of variation, improved the aSNR, aCNR, and overall image quality, and reduced the number of artifacts compared with the conventional acquisition method (all P < 0.05). However, the lesion conspicuity remained similar between the two protocols.
Conclusion
Utilizing a DL-based reconstruction algorithm in accelerated 3D T1-weighted pediatric brain MRI can significantly shorten the acquisition time, enhance image quality, and reduce artifacts, making it a viable option for pediatric imaging.
4.Evaluation of Image Quality and Scan Time Efficiency in Accelerated 3D T1-Weighted Pediatric Brain MRI Using Deep Learning-Based Reconstruction
Hyunsuk YOO ; Hee Eun MOON ; Soojin KIM ; Da Hee KIM ; Young Hun CHOI ; Jeong-Eun CHEON ; Joon Sung LEE ; Seunghyun LEE
Korean Journal of Radiology 2025;26(2):180-192
Objective:
This study evaluated the effect of an accelerated three-dimensional (3D) T1-weighted pediatric brain MRI protocol using a deep learning (DL)-based reconstruction algorithm on scan time and image quality.
Materials and Methods:
This retrospective study included 46 pediatric patients who underwent conventional and accelerated, pre- and post-contrast, 3D T1-weighted brain MRI using a 3T scanner (SIGNA Premier; GE HealthCare) at a single tertiary referral center between March 1, 2023, and April 30, 2023. Conventional scans were reconstructed using intensity Filter A (Conv), whereas accelerated scans were reconstructed using intensity Filter A (Fast_A) and a DL-based algorithm (Fast_DL).Image quality was assessed quantitatively based on the coefficient of variation, relative contrast, apparent signal-to-noise ratio (aSNR), and apparent contrast-to-noise ratio (aCNR) and qualitatively according to radiologists’ ratings of overall image quality, artifacts, noisiness, gray-white matter differentiation, and lesion conspicuity.
Results:
The acquisition times for the pre- and post-contrast scans were 191 and 135 seconds, respectively, for the conventional scan. With the accelerated protocol, these were reduced to 135 and 80 seconds, achieving time reductions of 29.3% and 40.7%, respectively. DL-based reconstruction significantly reduced the coefficient of variation, improved the aSNR, aCNR, and overall image quality, and reduced the number of artifacts compared with the conventional acquisition method (all P < 0.05). However, the lesion conspicuity remained similar between the two protocols.
Conclusion
Utilizing a DL-based reconstruction algorithm in accelerated 3D T1-weighted pediatric brain MRI can significantly shorten the acquisition time, enhance image quality, and reduce artifacts, making it a viable option for pediatric imaging.
5.Evaluation of Image Quality and Scan Time Efficiency in Accelerated 3D T1-Weighted Pediatric Brain MRI Using Deep Learning-Based Reconstruction
Hyunsuk YOO ; Hee Eun MOON ; Soojin KIM ; Da Hee KIM ; Young Hun CHOI ; Jeong-Eun CHEON ; Joon Sung LEE ; Seunghyun LEE
Korean Journal of Radiology 2025;26(2):180-192
Objective:
This study evaluated the effect of an accelerated three-dimensional (3D) T1-weighted pediatric brain MRI protocol using a deep learning (DL)-based reconstruction algorithm on scan time and image quality.
Materials and Methods:
This retrospective study included 46 pediatric patients who underwent conventional and accelerated, pre- and post-contrast, 3D T1-weighted brain MRI using a 3T scanner (SIGNA Premier; GE HealthCare) at a single tertiary referral center between March 1, 2023, and April 30, 2023. Conventional scans were reconstructed using intensity Filter A (Conv), whereas accelerated scans were reconstructed using intensity Filter A (Fast_A) and a DL-based algorithm (Fast_DL).Image quality was assessed quantitatively based on the coefficient of variation, relative contrast, apparent signal-to-noise ratio (aSNR), and apparent contrast-to-noise ratio (aCNR) and qualitatively according to radiologists’ ratings of overall image quality, artifacts, noisiness, gray-white matter differentiation, and lesion conspicuity.
Results:
The acquisition times for the pre- and post-contrast scans were 191 and 135 seconds, respectively, for the conventional scan. With the accelerated protocol, these were reduced to 135 and 80 seconds, achieving time reductions of 29.3% and 40.7%, respectively. DL-based reconstruction significantly reduced the coefficient of variation, improved the aSNR, aCNR, and overall image quality, and reduced the number of artifacts compared with the conventional acquisition method (all P < 0.05). However, the lesion conspicuity remained similar between the two protocols.
Conclusion
Utilizing a DL-based reconstruction algorithm in accelerated 3D T1-weighted pediatric brain MRI can significantly shorten the acquisition time, enhance image quality, and reduce artifacts, making it a viable option for pediatric imaging.
6.Development and Assessment of a Novel Ulcerative Colitis–Specific Quality of Life Questionnaire:A Prospective, Multi-Institutional Study
Jihye PARK ; Hyun-Soo ZHANG ; Chung Mo NAM ; Joo Sung KIM ; Young-Ho KIM ; Dong Il PARK ; Byong Duk YE ; Yoon Tae JEEN ; Sehyun KIM ; Jae Hee CHEON
Yonsei Medical Journal 2024;65(11):636-644
Purpose:
Interest in the quality of life (QoL) of patients with inflammatory bowel disease (IBD) has recently increased. Although measurement tools have been devised for IBD in general, there is no specific tool for measuring the QoL of patients with ulcerative colitis (UC). Therefore, we developed a QoL questionnaire specifically for patients with UC.
Materials and Methods:
The Korean Ulcerative Colitis-Specific Questionnaire (K-UCSQ) was developed through item generation, raw-scale construction, focus group meetings, and multi-center field tests. Two hundred patients with UC were recruited for a field test of the K-UCSQ, and subsequent responses to the Inflammatory Bowel Disease Questionnaire (IBDQ) were also obtained. After performing factor analyses to ensure construct validity, the K-UCSQ was finalized as a four-domain, 28-item questionnaire. Subsequent analyses evaluated the reliability of the K-UCSQ in terms of Cronbach’s alpha, concurrent validity in comparison with the pre-established IBDQ, and predictive validity of the area under the ROC curve (AUC) for clinically relevant QoL outcomes.
Results:
A Cronbach’s alpha of 0.94 showed excellent reliability. Furthermore, correlation analyses demonstrated the concurrent validity of the K-UCSQ in comparison with the IBDQ. The K-UCSQ also showed high validity in predicting the perceived overall health (AUC of 0.812 vs. 0.797 using the IBDQ) and past 2-week QoL (AUC of 0.864 vs. 0.859 using the IBDQ).
Conclusion
The newly developed K-UCSQ is concise, bathroom problem-emphasizing, and UC-specific, suggesting that it could be a valid and reliable UC-specific instrument for QoL measurement.
7.Development and Assessment of a Novel Ulcerative Colitis–Specific Quality of Life Questionnaire:A Prospective, Multi-Institutional Study
Jihye PARK ; Hyun-Soo ZHANG ; Chung Mo NAM ; Joo Sung KIM ; Young-Ho KIM ; Dong Il PARK ; Byong Duk YE ; Yoon Tae JEEN ; Sehyun KIM ; Jae Hee CHEON
Yonsei Medical Journal 2024;65(11):636-644
Purpose:
Interest in the quality of life (QoL) of patients with inflammatory bowel disease (IBD) has recently increased. Although measurement tools have been devised for IBD in general, there is no specific tool for measuring the QoL of patients with ulcerative colitis (UC). Therefore, we developed a QoL questionnaire specifically for patients with UC.
Materials and Methods:
The Korean Ulcerative Colitis-Specific Questionnaire (K-UCSQ) was developed through item generation, raw-scale construction, focus group meetings, and multi-center field tests. Two hundred patients with UC were recruited for a field test of the K-UCSQ, and subsequent responses to the Inflammatory Bowel Disease Questionnaire (IBDQ) were also obtained. After performing factor analyses to ensure construct validity, the K-UCSQ was finalized as a four-domain, 28-item questionnaire. Subsequent analyses evaluated the reliability of the K-UCSQ in terms of Cronbach’s alpha, concurrent validity in comparison with the pre-established IBDQ, and predictive validity of the area under the ROC curve (AUC) for clinically relevant QoL outcomes.
Results:
A Cronbach’s alpha of 0.94 showed excellent reliability. Furthermore, correlation analyses demonstrated the concurrent validity of the K-UCSQ in comparison with the IBDQ. The K-UCSQ also showed high validity in predicting the perceived overall health (AUC of 0.812 vs. 0.797 using the IBDQ) and past 2-week QoL (AUC of 0.864 vs. 0.859 using the IBDQ).
Conclusion
The newly developed K-UCSQ is concise, bathroom problem-emphasizing, and UC-specific, suggesting that it could be a valid and reliable UC-specific instrument for QoL measurement.
8.Cohort profile: Multicenter Networks for Ideal Outcomes of Rare Pediatric Endocrine and Metabolic Diseases in Korea (OUTSPREAD study)
Yun Jeong LEE ; Chong Kun CHEON ; Junghwan SUH ; Jung-Eun MOON ; Moon Bae AHN ; Seong Hwan CHANG ; Jieun LEE ; Jin Ho CHOI ; Minsun KIM ; Han Hyuk LIM ; Jaehyun KIM ; Shin-Hye KIM ; Hae Sang LEE ; Yena LEE ; Eungu KANG ; Se Young KIM ; Yong Hee HONG ; Seung YANG ; Heon-Seok HAN ; Sochung CHUNG ; Won Kyoung CHO ; Eun Young KIM ; Jin Kyung KIM ; Kye Shik SHIM ; Eun-Gyong YOO ; Hae Soon KIM ; Aram YANG ; Sejin KIM ; Hyo-Kyoung NAM ; Sung Yoon CHO ; Young Ah LEE
Annals of Pediatric Endocrinology & Metabolism 2024;29(6):349-355
Rare endocrine diseases are complex conditions that require lifelong specialized care due to their chronic nature and associated long-term complications. In Korea, a lack of nationwide data on clinical practice and outcomes has limited progress in patient care. Therefore, the Multicenter Networks for Ideal Outcomes of Pediatric Rare Endocrine and Metabolic Disease (OUTSPREAD) study was initiated. This study involves 30 centers across Korea. The study aims to improve the long-term prognosis of Korean patients with rare endocrine diseases by collecting comprehensive clinical data, biospecimens, and patient-reported outcomes to identify complications and unmet needs in patient care. Patients with childhood-onset pituitary, adrenal, or gonadal disorders, such as craniopharyngioma, congenital adrenal hyperplasia (CAH), and Turner syndrome were prioritized. The planned enrollment is 1,300 patients during the first study phase (2022–2024). Clinical, biochemical, and imaging data from diagnosis, treatment, and follow-up during 1980–2023 were retrospectively reviewed. For patients who agreed to participate in the prospective cohort, clinical data and biospecimens will be prospectively collected to discover ideal biomarkers that predict the effectiveness of disease control measures and prognosis. Patient-reported outcomes, including quality of life and depression scales, will be evaluated to assess psychosocial outcomes. Additionally, a substudy on CAH patients will develop a steroid hormone profiling method using liquid chromatography-tandem mass spectrometry to improve diagnosis and monitoring of treatment outcomes. This study will address unmet clinical needs by discovering ideal biomarkers, introducing evidence-based treatment guidelines, and ultimately improving long-term outcomes in the areas of rare endocrine and metabolic diseases.
9.Development and Assessment of a Novel Ulcerative Colitis–Specific Quality of Life Questionnaire:A Prospective, Multi-Institutional Study
Jihye PARK ; Hyun-Soo ZHANG ; Chung Mo NAM ; Joo Sung KIM ; Young-Ho KIM ; Dong Il PARK ; Byong Duk YE ; Yoon Tae JEEN ; Sehyun KIM ; Jae Hee CHEON
Yonsei Medical Journal 2024;65(11):636-644
Purpose:
Interest in the quality of life (QoL) of patients with inflammatory bowel disease (IBD) has recently increased. Although measurement tools have been devised for IBD in general, there is no specific tool for measuring the QoL of patients with ulcerative colitis (UC). Therefore, we developed a QoL questionnaire specifically for patients with UC.
Materials and Methods:
The Korean Ulcerative Colitis-Specific Questionnaire (K-UCSQ) was developed through item generation, raw-scale construction, focus group meetings, and multi-center field tests. Two hundred patients with UC were recruited for a field test of the K-UCSQ, and subsequent responses to the Inflammatory Bowel Disease Questionnaire (IBDQ) were also obtained. After performing factor analyses to ensure construct validity, the K-UCSQ was finalized as a four-domain, 28-item questionnaire. Subsequent analyses evaluated the reliability of the K-UCSQ in terms of Cronbach’s alpha, concurrent validity in comparison with the pre-established IBDQ, and predictive validity of the area under the ROC curve (AUC) for clinically relevant QoL outcomes.
Results:
A Cronbach’s alpha of 0.94 showed excellent reliability. Furthermore, correlation analyses demonstrated the concurrent validity of the K-UCSQ in comparison with the IBDQ. The K-UCSQ also showed high validity in predicting the perceived overall health (AUC of 0.812 vs. 0.797 using the IBDQ) and past 2-week QoL (AUC of 0.864 vs. 0.859 using the IBDQ).
Conclusion
The newly developed K-UCSQ is concise, bathroom problem-emphasizing, and UC-specific, suggesting that it could be a valid and reliable UC-specific instrument for QoL measurement.
10.Development and Assessment of a Novel Ulcerative Colitis–Specific Quality of Life Questionnaire:A Prospective, Multi-Institutional Study
Jihye PARK ; Hyun-Soo ZHANG ; Chung Mo NAM ; Joo Sung KIM ; Young-Ho KIM ; Dong Il PARK ; Byong Duk YE ; Yoon Tae JEEN ; Sehyun KIM ; Jae Hee CHEON
Yonsei Medical Journal 2024;65(11):636-644
Purpose:
Interest in the quality of life (QoL) of patients with inflammatory bowel disease (IBD) has recently increased. Although measurement tools have been devised for IBD in general, there is no specific tool for measuring the QoL of patients with ulcerative colitis (UC). Therefore, we developed a QoL questionnaire specifically for patients with UC.
Materials and Methods:
The Korean Ulcerative Colitis-Specific Questionnaire (K-UCSQ) was developed through item generation, raw-scale construction, focus group meetings, and multi-center field tests. Two hundred patients with UC were recruited for a field test of the K-UCSQ, and subsequent responses to the Inflammatory Bowel Disease Questionnaire (IBDQ) were also obtained. After performing factor analyses to ensure construct validity, the K-UCSQ was finalized as a four-domain, 28-item questionnaire. Subsequent analyses evaluated the reliability of the K-UCSQ in terms of Cronbach’s alpha, concurrent validity in comparison with the pre-established IBDQ, and predictive validity of the area under the ROC curve (AUC) for clinically relevant QoL outcomes.
Results:
A Cronbach’s alpha of 0.94 showed excellent reliability. Furthermore, correlation analyses demonstrated the concurrent validity of the K-UCSQ in comparison with the IBDQ. The K-UCSQ also showed high validity in predicting the perceived overall health (AUC of 0.812 vs. 0.797 using the IBDQ) and past 2-week QoL (AUC of 0.864 vs. 0.859 using the IBDQ).
Conclusion
The newly developed K-UCSQ is concise, bathroom problem-emphasizing, and UC-specific, suggesting that it could be a valid and reliable UC-specific instrument for QoL measurement.

Result Analysis
Print
Save
E-mail