Inyoung Youn
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Inyoung Youn has a total of 100 co-authors. Here are the top co-authors by number of shared publications:
- Mi-Ri Kwon
Department of Radiology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Korea
9 shared publications - Vivian Youngjean Park
Department of Radiology, Research Institute of Radiological Science, Yonsei University College of Medicine, Seoul, Republic of Korea
5 shared publications - Jung Min Chang
Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Korea
4 shared publications - Su Min Ha
Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea
4 shared publications - Bong Joo Kang
Department of Radiology, College of Medicine, Seoul St. Mary’s Hospital, The Catholic University of Korea, Seoul, Republic of Korea
3 shared publications - Eun Young Ko
Department of Radiology and Center for Imaging Science, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea
3 shared publications
Latest Publications
- Open Access
- 15 January 2026
- Published by Bioscientifica in European Thyroid Journal
- Vol. 15 (1)
Artificial intelligence-assisted risk stratification of thyroid nodules with atypia of undetermined significance
Objective: Given the limitations of conventional approaches in managing indeterminate thyroid nodules, there remains an unmet need for non-invasive assistant tools to improve risk stratification. This study aimed to evaluate the clinical applicability of an artificial intelligence (AI) model for thyroid nodules with atypia of undetermined significance (AUS) cytology. Methods: We retrospectively reviewed patients who underwent fine-needle aspiration (FNA) for thyroid nodules between January 2019 and December 2020 across five medical institutions in Korea. Nodules initially diagnosed as AUS and later confirmed as benign or malignant were included. A previously developed deep learning-based AI model, AI-Thyroid, was employed to provide binary classifications (benign or malignant) and malignancy risk estimates. Results: A total of 165 thyroid nodules were analyzed. The median (interquartile range) longest diameter was 1.30 cm (0.80–2.10), and the malignancy rate of the cohort was 39%. In binary classification tasks, the model achieved a sensitivity of 0.91 and a negative predictive value of 0.87. The area under the curve (AUC) based on estimated malignancy risk was 0.75 (95% confidence interval (CI): 0.68–0.83), and the AUC derived from K-TIRADS categories 2–5 was 0.76 (95% CI: 0.69–0.83), indicating comparable diagnostic accuracy with the traditional scoring system. Subgroup analyses demonstrated that the model achieved a sensitivity of 98% in nodules smaller than 1.5 cm. Conclusion: AI-assisted ultrasound analysis offers supplementary diagnostic information for thyroid nodules with AUS cytology. Its high sensitivity and negative predictive value may assist clinicians in decision-making processes, particularly for small, low-risk thyroid nodules.
- 15 January 2026
- Published by Bioscientifica in European Thyroid Journal
- Vol. 15 (1)
Open AccessArtificial intelligence-assisted risk stratification of thyroid nodules with atypia of undetermined significance
Objective: Given the limitations of conventional approaches in managing indeterminate thyroid nodules, there remains an unmet need for non-invasive assistant tools to improve risk stratification. This study aimed to evaluate the clinical applicability of an artificial intelligence (AI) model for thyroid nodules with atypia of undetermined significance (AUS) cytology. Methods: We retrospectively reviewed patients who underwent fine-needle aspiration (FNA) for thyroid nodules between January 2019 and December 2020 across five medical institutions in Korea. Nodules initially diagnosed as AUS and later confirmed as benign or malignant were included. A previously developed deep learning-based AI model, AI-Thyroid, was employed to provide binary classifications (benign or malignant) and malignancy risk estimates. Results: A total of 165 thyroid nodules were analyzed. The median (interquartile range) longest diameter was 1.30 cm (0.80–2.10), and the malignancy rate of the cohort was 39%. In binary classification tasks, the model achieved a sensitivity of 0.91 and a negative predictive value of 0.87. The area under the curve (AUC) based on estimated malignancy risk was 0.75 (95% confidence interval (CI): 0.68–0.83), and the AUC derived from K-TIRADS categories 2–5 was 0.76 (95% CI: 0.69–0.83), indicating comparable diagnostic accuracy with the traditional scoring system. Subgroup analyses demonstrated that the model achieved a sensitivity of 98% in nodules smaller than 1.5 cm. Conclusion: AI-assisted ultrasound analysis offers supplementary diagnostic information for thyroid nodules with AUS cytology. Its high sensitivity and negative predictive value may assist clinicians in decision-making processes, particularly for small, low-risk thyroid nodules.
- Open Access
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (8) , 798
Response to “Automated Breast Ultrasound in Dense-Breast Screening: Beyond Additional Cancer Detection”
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (8) , 798
Open AccessResponse to “Automated Breast Ultrasound in Dense-Breast Screening: Beyond Additional Cancer Detection”
- Open Access
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (7) , 684-685
Response to “Further Methodological Considerations for Evaluating T2-Weighted Imaging Features as Biomarkers in Invasive Breast Cancer”
Park VY, et al. Korean J Radiol. 2026 ;27:e51. https://doi.org/10.3348/kjr.2026.0544
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (7) , 684-685
Open AccessResponse to “Further Methodological Considerations for Evaluating T2-Weighted Imaging Features as Biomarkers in Invasive Breast Cancer”
Park VY, et al. Korean J Radiol. 2026 ;27:e51. https://doi.org/10.3348/kjr.2026.0544
- Open Access
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (6) , 605-606
Response to “Methodological Challenges in Associating T2-Weighted Imaging Features in Breast Cancer With Clinical and Pathologic Findings”
Park VY, et al. Korean J Radiol. 2026 Jun;27(6):605-606. https://doi.org/10.3348/kjr.2026.0543
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (6) , 605-606
Open AccessResponse to “Methodological Challenges in Associating T2-Weighted Imaging Features in Breast Cancer With Clinical and Pathologic Findings”
Park VY, et al. Korean J Radiol. 2026 Jun;27(6):605-606. https://doi.org/10.3348/kjr.2026.0543
- Open Access
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (6) , 601-602
Response to “Refining the Predictive Role of T2-Weighted Imaging Features in Breast Cancer: A Hypothesis Linking Tumor Characteristics to Extreme Chemoresistance”
Park VY, et al. Korean J Radiol. 2026 Jun;27(6):601-602. https://doi.org/10.3348/kjr.2026.0542
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (6) , 601-602
Open AccessResponse to “Refining the Predictive Role of T2-Weighted Imaging Features in Breast Cancer: A Hypothesis Linking Tumor Characteristics to Extreme Chemoresistance”
Park VY, et al. Korean J Radiol. 2026 Jun;27(6):601-602. https://doi.org/10.3348/kjr.2026.0542
- Open Access
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (4) , 305-317
Association of T2-Weighted Imaging Features in Invasive Breast Cancer With Clinicopathologic Features and Neoadjuvant Treatment Outcomes
Youn I, et al. Korean J Radiol. 2026 ;27:e22. https://doi.org/10.3348/kjr.2025.1382
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (4) , 305-317
Open AccessAssociation of T2-Weighted Imaging Features in Invasive Breast Cancer With Clinicopathologic Features and Neoadjuvant Treatment Outcomes
Youn I, et al. Korean J Radiol. 2026 ;27:e22. https://doi.org/10.3348/kjr.2025.1382
- Open Access
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (2) , 111-121
Comparison of Digital Mammography Plus Full ABUS Review and Digital Mammography Plus Selective ABUS Review Guided by ABUS Artificial Intelligence–Computer-Aided Diagnosis for Breast Cancer Screening
To compare two breast cancer screening strategies, digital mammography (DM) plus radiologist-interpreted automated breast ultrasound (ABUS) and DM plus selective ABUS review, in which only examinations positive for DM or flagged by ABUS artificial intelligence–computer-aided diagnosis (AI-CAD) were reviewed by radiologists. This retrospective study included asymptomatic women who underwent DM and ABUS screening for breast cancer between March 2022 and March 2023. The radiologists’ interpretations of DM and ABUS without AI assistance (DM + ABUS_radiologist) were collected from the clinical radiology reports. A selective DM plus ABUS reading strategy was simulated, in which only cases interpreted as positive in the radiologist’s DM report or flagged by retrospectively applied ABUS AI-CAD were triaged for further evaluation through a full review by radiologists (DM + ABUS_AI-CAD). The cancer detection rate (CDR), sensitivity, specificity, and abnormal interpretation rate (AIR) were calculated and compared between DM + ABUS_radiologist and DM + ABUS_AI-CAD groups using the McNemar’s test. Among 2,275 women (mean age, 56.1 ± 8.6 years), 12 cancers were diagnosed. The sensitivity, CDR and AIR for DM + ABUS_radiologist was 83.3% (10/12; 95% confidence interval [CI]: 51.6–97.9), 4.4 (10/2,275; 95% CI: 2.1–8.1) per 1,000 screening examinations and 16.7% (379/2,275; 95% CI: 15.1–18.3), respectively. DM + ABUS_AI-CAD triaged 84.0% (1,910/2,275) of the examinations as negative in both DM reports and retrospectively applied ABUS AI-CAD, requiring radiologist reassessment in only 16.0% (365/2,275). This approach reduced the AIR to 7.3% (167/2,275) and improved the specificity from 83.7% (1,894/2,263) to 93.1% (2,107/2,263) (all P < 0.001), while maintaining a CDR of 4.8 per 1,000 and a sensitivity of 91.7% (11/12) (all P > 0.999), compared to the DM + ABUS-radiologist. An AI-CAD-assisted selective ABUS reading strategy reduces unnecessary recalls and improves specificity, which may help optimize reading priorities and reduce the reading workload while maintaining cancer detection performance.
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (2) , 111-121
Open AccessComparison of Digital Mammography Plus Full ABUS Review and Digital Mammography Plus Selective ABUS Review Guided by ABUS Artificial Intelligence–Computer-Aided Diagnosis for Breast Cancer Screening
To compare two breast cancer screening strategies, digital mammography (DM) plus radiologist-interpreted automated breast ultrasound (ABUS) and DM plus selective ABUS review, in which only examinations positive for DM or flagged by ABUS artificial intelligence–computer-aided diagnosis (AI-CAD) were reviewed by radiologists. This retrospective study included asymptomatic women who underwent DM and ABUS screening for breast cancer between March 2022 and March 2023. The radiologists’ interpretations of DM and ABUS without AI assistance (DM + ABUS_radiologist) were collected from the clinical radiology reports. A selective DM plus ABUS reading strategy was simulated, in which only cases interpreted as positive in the radiologist’s DM report or flagged by retrospectively applied ABUS AI-CAD were triaged for further evaluation through a full review by radiologists (DM + ABUS_AI-CAD). The cancer detection rate (CDR), sensitivity, specificity, and abnormal interpretation rate (AIR) were calculated and compared between DM + ABUS_radiologist and DM + ABUS_AI-CAD groups using the McNemar’s test. Among 2,275 women (mean age, 56.1 ± 8.6 years), 12 cancers were diagnosed. The sensitivity, CDR and AIR for DM + ABUS_radiologist was 83.3% (10/12; 95% confidence interval [CI]: 51.6–97.9), 4.4 (10/2,275; 95% CI: 2.1–8.1) per 1,000 screening examinations and 16.7% (379/2,275; 95% CI: 15.1–18.3), respectively. DM + ABUS_AI-CAD triaged 84.0% (1,910/2,275) of the examinations as negative in both DM reports and retrospectively applied ABUS AI-CAD, requiring radiologist reassessment in only 16.0% (365/2,275). This approach reduced the AIR to 7.3% (167/2,275) and improved the specificity from 83.7% (1,894/2,263) to 93.1% (2,107/2,263) (all P < 0.001), while maintaining a CDR of 4.8 per 1,000 and a sensitivity of 91.7% (11/12) (all P > 0.999), compared to the DM + ABUS-radiologist. An AI-CAD-assisted selective ABUS reading strategy reduces unnecessary recalls and improves specificity, which may help optimize reading priorities and reduce the reading workload while maintaining cancer detection performance.
- Open Access
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (1) , 14-26
Screening Outcomes of Supplemental Automated Breast Ultrasound in Women With Nondense Breasts Undergoing Mammography
Kwon MR, et al. Korean J Radiol. 2026 Jan;27(1):14-26. https://doi.org/10.3348/kjr.2025.1114
- 1 January 2026
- Published by XMLink in Korean Journal of Radiology
- Vol. 27 (1) , 14-26
Open AccessScreening Outcomes of Supplemental Automated Breast Ultrasound in Women With Nondense Breasts Undergoing Mammography
Kwon MR, et al. Korean J Radiol. 2026 Jan;27(1):14-26. https://doi.org/10.3348/kjr.2025.1114
- Open Access
- 30 November 2025
- Published by Korean Rhinologic Society in Journal of Rhinology
- Vol. 32 (3) , 141-149
Changes in Incidental Paranasal Sinus Abnormalities During the COVID-19 Era: A 5-Year MRI-Based Study
Background and Objectives: The coronavirus disease 2019 (COVID-19) pandemic and associated nonpharmaceutical interventions, including mask-wearing and hand hygiene, have led to a global decline in otorhinolaryngologic conditions, with the monthly incidence of chronic rhinosinusitis decreasing from 39.49 to 14.56 per 100,000 people. This study compared the prevalence and severity of paranasal sinus abnormalities observed on magnetic resonance imaging (MRI) before and during the COVID-19 pandemic.Methods: This retrospective study analyzed brain MRI scans from 3,762 individuals (1,881 men and 1,881 women; mean age, 56.2±9.8 years) performed at a single health-screening center in Seoul, South Korea, between January 2018 and December 2022. The study period was divided into pre-COVID-19 and COVID-19 phases, with March 2020 as the cutoff. A total of 428 scans demonstrating incidental paranasal sinus abnormalities, including mucosal thickening, retention cysts or polyps, fluid collection, and fungal balls, were evaluated using the Lund-Mackay (LM) scoring system.Results: The overall prevalence of incidental paranasal sinus abnormalities was 11.4% (428/3,762), with a significant decline from the pre-COVID-19 to the COVID-19 period (16.1% vs. 8.6%, p<0.001). However, the mean LM score among participants with abnormalities was significantly higher during the COVID-19 period than in the pre-COVID-19 period (3.64±3.22 vs. 3.01±2.58, p=0.026). The proportion of nasal polyps was also greater during the COVID-19 period than in the pre-COVID-19 period (10.8% vs. 5.8%, p=0.028).Conclusion: The prevalence of incidental paranasal sinus abnormalities on MRI decreased during the COVID-19 period compared to the pre-COVID-19 period, whereas the severity, as reflected by the LM score, increased.
- 30 November 2025
- Published by Korean Rhinologic Society in Journal of Rhinology
- Vol. 32 (3) , 141-149
Open AccessChanges in Incidental Paranasal Sinus Abnormalities During the COVID-19 Era: A 5-Year MRI-Based Study
Background and Objectives: The coronavirus disease 2019 (COVID-19) pandemic and associated nonpharmaceutical interventions, including mask-wearing and hand hygiene, have led to a global decline in otorhinolaryngologic conditions, with the monthly incidence of chronic rhinosinusitis decreasing from 39.49 to 14.56 per 100,000 people. This study compared the prevalence and severity of paranasal sinus abnormalities observed on magnetic resonance imaging (MRI) before and during the COVID-19 pandemic.Methods: This retrospective study analyzed brain MRI scans from 3,762 individuals (1,881 men and 1,881 women; mean age, 56.2±9.8 years) performed at a single health-screening center in Seoul, South Korea, between January 2018 and December 2022. The study period was divided into pre-COVID-19 and COVID-19 phases, with March 2020 as the cutoff. A total of 428 scans demonstrating incidental paranasal sinus abnormalities, including mucosal thickening, retention cysts or polyps, fluid collection, and fungal balls, were evaluated using the Lund-Mackay (LM) scoring system.Results: The overall prevalence of incidental paranasal sinus abnormalities was 11.4% (428/3,762), with a significant decline from the pre-COVID-19 to the COVID-19 period (16.1% vs. 8.6%, p<0.001). However, the mean LM score among participants with abnormalities was significantly higher during the COVID-19 period than in the pre-COVID-19 period (3.64±3.22 vs. 3.01±2.58, p=0.026). The proportion of nasal polyps was also greater during the COVID-19 period than in the pre-COVID-19 period (10.8% vs. 5.8%, p=0.028).Conclusion: The prevalence of incidental paranasal sinus abnormalities on MRI decreased during the COVID-19 period compared to the pre-COVID-19 period, whereas the severity, as reflected by the LM score, increased.
- Open Access
- 19 August 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (16) , 2072
Prognosis of Breast Cancer in Women in Their 20s: Clinical and Radiological Insights
Background/Objectives: We analyzed clinical and radiological characteristics and prognostic factors specific to young patients with breast cancer (YBC) aged BRCA1 gene mutation, with preoperative neoadjuvant chemotherapy, no hormone therapy, larger tumor size, negative hormone receptor status, high Ki-67 expression, and some radiological findings, including asymmetry with calcifications on mammography, no sonographic echogenic rind of mass, and mild vascularity on Doppler study. Conclusions: Our study highlights the aggressive nature of breast cancer in YBC aged <30 years, with relatively high rates of recurrence and mortality. Significant factors affecting prognosis may guide personalized treatment approaches and predict the prognosis.
- 19 August 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (16) , 2072
Open AccessPrognosis of Breast Cancer in Women in Their 20s: Clinical and Radiological Insights
Background/Objectives: We analyzed clinical and radiological characteristics and prognostic factors specific to young patients with breast cancer (YBC) aged BRCA1 gene mutation, with preoperative neoadjuvant chemotherapy, no hormone therapy, larger tumor size, negative hormone receptor status, high Ki-67 expression, and some radiological findings, including asymmetry with calcifications on mammography, no sonographic echogenic rind of mass, and mild vascularity on Doppler study. Conclusions: Our study highlights the aggressive nature of breast cancer in YBC aged <30 years, with relatively high rates of recurrence and mortality. Significant factors affecting prognosis may guide personalized treatment approaches and predict the prognosis.