Yu-Mee Sohn
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
Yu-Mee Sohn has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
Mirinae Seo
Department of Radiology, Kyung Hee University Hospital, College of Medicine, Kyung Hee University, Seoul
7 shared publications- Eun-Kyung Kim
Department of Radiology, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin, Korea
4 shared publications - Kyunghwa Han
Department of Radiology, Center for Clinical Imaging Data Science, Research Institute of Radiological Sciences, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
4 shared publications M. Seo
Department of Radiology, Kyung Hee University Hospital, College of Medicine, Kyung Hee University, Seoul, South Korea
3 shared publications- Mirinae Seo
Department of Radiology, Kyung Hee University Hospital, Kyung Hee University College of Medicine, Seoul, Korea
3 shared publications Eun Jee Song
Department of Radiology, Kyung Hee University Hospital, College of Medicine, Kyung Hee University, Seoul, South Korea
2 shared publications
Latest Publications
- Open Access
- 1 January 2025
- Published by XMLink in Journal of Breast Cancer
- Vol. 28 (5) , 299-310
The Clinical Application of Artificial Intelligence in Breast Imaging: Current Insights, Challenges, and Future Directions
Sohn YM, et al. J Breast Cancer. 2025 Sep;28:e32. https://doi.org/10.4048/jbc.2025.0123
- 1 January 2025
- Published by XMLink in Journal of Breast Cancer
- Vol. 28 (5) , 299-310
Open AccessThe Clinical Application of Artificial Intelligence in Breast Imaging: Current Insights, Challenges, and Future Directions
Sohn YM, et al. J Breast Cancer. 2025 Sep;28:e32. https://doi.org/10.4048/jbc.2025.0123
- Open Access
- 1 January 2021
- Published by Korean Society of Ultrasound in Medicine in Ultrasonography
- Vol. 40 (1) , 115-125
Malignancy risk of thyroid nodules with nonshadowing echogenic foci
Purpose: This study was conducted to determine the malignancy risk and diagnostic value of various types of nonshadowing echogenic foci (NEF) in the risk stratification of thyroid nodules. Methods: A total of 1,018 consecutive thyroid nodules (>= 1 cm) with final diagnoses were included. The presence of NEF was determined and types of NEF were classified according to the presence of a comet tail artifact (CTA), location, and size through a prospective evaluation. The associations with malignancy, malignancy risk, and diagnostic value of various types of NEF were assessed. Results: Intrasolid punctate NEF without CTA was the only type of NEF that was an independent predictor of malignancy (P<0.001). The malignancy risk of intrasolid punctate NEF without CTA was substantially higher in solid hypoechoic nodules than in isoechoic or nonsolid nodules (71.3% vs. 9.2%, P0.05). Conclusion: Intrasolid punctate NEF without CTA was the only independent predictor of malignancy. However, solid hypoechoic nodules with intrasolid punctate NEF should be classified as high-suspicion nodules regardless of coexisting CTA. Other types of NEF had no added value for detecting malignancy compared to intrasolid punctate NEF without CTA.
- 1 January 2021
- Published by Korean Society of Ultrasound in Medicine in Ultrasonography
- Vol. 40 (1) , 115-125
Open AccessMalignancy risk of thyroid nodules with nonshadowing echogenic foci
Purpose: This study was conducted to determine the malignancy risk and diagnostic value of various types of nonshadowing echogenic foci (NEF) in the risk stratification of thyroid nodules. Methods: A total of 1,018 consecutive thyroid nodules (>= 1 cm) with final diagnoses were included. The presence of NEF was determined and types of NEF were classified according to the presence of a comet tail artifact (CTA), location, and size through a prospective evaluation. The associations with malignancy, malignancy risk, and diagnostic value of various types of NEF were assessed. Results: Intrasolid punctate NEF without CTA was the only type of NEF that was an independent predictor of malignancy (P<0.001). The malignancy risk of intrasolid punctate NEF without CTA was substantially higher in solid hypoechoic nodules than in isoechoic or nonsolid nodules (71.3% vs. 9.2%, P0.05). Conclusion: Intrasolid punctate NEF without CTA was the only independent predictor of malignancy. However, solid hypoechoic nodules with intrasolid punctate NEF should be classified as high-suspicion nodules regardless of coexisting CTA. Other types of NEF had no added value for detecting malignancy compared to intrasolid punctate NEF without CTA.
- Open Access
- 24 December 2020
- Published by Wolters Kluwer Health in Medicine
- Vol. 99 (52) , e23654
Shear-wave elastography in thyroid ultrasound
This study aimed to investigate whether extrathyroidal extension (ETE) and cervical lymph node metastasis (LNM) can be predicted using elasticity parameters of shear-wave elastography (SWE) combined with B-mode ultrasound (US) of papillary thyroid carcinomas (PTCs). We retrospectively reviewed 111 patients who underwent preoperative SWE evaluation among PTC patients from July 1, 2016 to June 20, 2018. Patients were divided into 2 groups based on the presence or absence of ETE based on pathology reports. Univariate and multivariate analyses of clinical and radiologic features including B-mode US features, US patterns, and SWE parameters were performed. These analyses were repeated in LNM positive and negative groups. The diagnostic performance of SWE parameters were also evaluated. Of the 111 patients, 33 had ETE, 78 did not have ETE, 44 had LNM, and 67 did not have LNM. A taller-than-wide shape and T3 stage on US were associated with ETE. Female sex, total thyroidectomy, and T3 stage on US were associated with LNM. When B-mode US and SWE were combined, there was no improvement in diagnostic performance. Combination of SWE and B-mode US findings is not useful for predicting ETE and LNM status in PTC patients.
- 24 December 2020
- Published by Wolters Kluwer Health in Medicine
- Vol. 99 (52) , e23654
Open AccessShear-wave elastography in thyroid ultrasound
This study aimed to investigate whether extrathyroidal extension (ETE) and cervical lymph node metastasis (LNM) can be predicted using elasticity parameters of shear-wave elastography (SWE) combined with B-mode ultrasound (US) of papillary thyroid carcinomas (PTCs). We retrospectively reviewed 111 patients who underwent preoperative SWE evaluation among PTC patients from July 1, 2016 to June 20, 2018. Patients were divided into 2 groups based on the presence or absence of ETE based on pathology reports. Univariate and multivariate analyses of clinical and radiologic features including B-mode US features, US patterns, and SWE parameters were performed. These analyses were repeated in LNM positive and negative groups. The diagnostic performance of SWE parameters were also evaluated. Of the 111 patients, 33 had ETE, 78 did not have ETE, 44 had LNM, and 67 did not have LNM. A taller-than-wide shape and T3 stage on US were associated with ETE. Female sex, total thyroidectomy, and T3 stage on US were associated with LNM. When B-mode US and SWE were combined, there was no improvement in diagnostic performance. Combination of SWE and B-mode US findings is not useful for predicting ETE and LNM status in PTC patients.
- Open Access
- 1 May 2020
- Published by Korean Society of Otorhinolaryngology-Head and Neck Surgery in Clinical and Experimental Otorhinolaryngology
- Vol. 13 (2) , 186-193
Diagnostic Performance of a Combination of Shear Wave Elastography and B-Mode Ultrasonography in Differentiating Benign From Malignant Thyroid Nodules
Objectives. This study was conducted to compare clinicopathologic and radiologic factors between benign and malignant thyroid nodules and to evaluate the diagnostic performance of shear wave elastography (SWE) combined with B-mode ultrasonography (US) in differentiating malignant from benign thyroid nodules.Methods. This retrospective study included 92 consecutive patients with 95 thyroid nodules examined on B-mode US and SWE before US-guided fine-needle aspiration biopsy or surgical excision. B-mode US findings (composition, echogenicity, margin, shape, and calcification) and SWE elasticity parameters (maximum [Emax], mean, minimum, and nodule-to-normal parenchymal ratio of elasticity) were reviewed and compared between benign and malignant thyroid nodules. The diagnostic performance of B-mode US and SWE for predicting malignant thyroid nodules was analyzed. The optimal cutoff values of elasticity parameters for identifying malignancy were determined. Diagnostic performance was compared between B-mode US only, SWE only, and the combination of B-mode US with SWE.Results. On multivariate logistic regression analysis, age (odds ratio [OR], 0.90; P=0.028), a taller-than-wide shape (OR, 11.3; P=0.040), the presence of calcifications (OR, 15.0; P=0.021), and Emax (OR, 1.22; P=0.021) were independent predictors of malignancy in thyroid nodules. The combined use of B-mode US findings and SWE yielded improvements in sensitivity, the positive predictive value, the negative predictive value, and accuracy compared with the use of B-mode US findings only, but with no statistical significance.Conclusion. When SWE was combined with B-mode US, the diagnostic performance was better than when only B-mode US was used, although the difference was not statistically significant.
- 1 May 2020
- Published by Korean Society of Otorhinolaryngology-Head and Neck Surgery in Clinical and Experimental Otorhinolaryngology
- Vol. 13 (2) , 186-193
Open AccessDiagnostic Performance of a Combination of Shear Wave Elastography and B-Mode Ultrasonography in Differentiating Benign From Malignant Thyroid Nodules
Objectives. This study was conducted to compare clinicopathologic and radiologic factors between benign and malignant thyroid nodules and to evaluate the diagnostic performance of shear wave elastography (SWE) combined with B-mode ultrasonography (US) in differentiating malignant from benign thyroid nodules.Methods. This retrospective study included 92 consecutive patients with 95 thyroid nodules examined on B-mode US and SWE before US-guided fine-needle aspiration biopsy or surgical excision. B-mode US findings (composition, echogenicity, margin, shape, and calcification) and SWE elasticity parameters (maximum [Emax], mean, minimum, and nodule-to-normal parenchymal ratio of elasticity) were reviewed and compared between benign and malignant thyroid nodules. The diagnostic performance of B-mode US and SWE for predicting malignant thyroid nodules was analyzed. The optimal cutoff values of elasticity parameters for identifying malignancy were determined. Diagnostic performance was compared between B-mode US only, SWE only, and the combination of B-mode US with SWE.Results. On multivariate logistic regression analysis, age (odds ratio [OR], 0.90; P=0.028), a taller-than-wide shape (OR, 11.3; P=0.040), the presence of calcifications (OR, 15.0; P=0.021), and Emax (OR, 1.22; P=0.021) were independent predictors of malignancy in thyroid nodules. The combined use of B-mode US findings and SWE yielded improvements in sensitivity, the positive predictive value, the negative predictive value, and accuracy compared with the use of B-mode US findings only, but with no statistical significance.Conclusion. When SWE was combined with B-mode US, the diagnostic performance was better than when only B-mode US was used, although the difference was not statistically significant.
- 26 March 2019
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 92 (1097) , 20180341
Shear wave elastography for the diagnosis of small (≤2 cm) breast lesions: added value and factors associated with false results
Objective: We compared the diagnostic performance of B-mode ultrasound, shear wave elastography (SWE), and combined B-mode ultrasound and SWE in small breast lesions (≤ 2 cm), and evaluated the factors associated with false SWE results. Methods: A total of 428 small breast lesions (≤ 2 cm) of 415 consecutive patients between August 2013 and February 2017 were included. The diagnostic performance of each set was evaluated using the area under the receiver operating characteristic curve (AUC) analysis. Histologic diagnosis was used as reference standard. Multivariate logistic regression analyses identified the factors associated with false SWE results. Results: Of 428 lesions, 142 (33.2%) were malignant and 286 (66.8%) were benign. The AUC of the combined modality was higher than that of B-mode ultrasound (0.792 vs 0.572, p < 0.001) and that of SWE was higher than that of B-mode ultrasound (0.718 vs 0.572, p < 0.001). Multivariate analysis showed that the smaller lesion size and in situ cancer were associated with false negative, and patient’s age, high-risk lesion, shorter distance from the skin or chest wall, and deeper breast thickness were associated with false positive (all p < 0.05). Conclusions: The addition of SWE to B-mode ultrasound could improve the diagnostic performance in ≤ 2 cm lesions. However, ultrasound lesion size, pathology, and lesion location are likely to affect the SWE value and result in false results. Advances in knowledge: Despite the diagnostic usefulness of SWE in small breast lesions (≤ 2 cm), ultrasound lesion size, pathology, and lesion location were associated with false results.
- 26 March 2019
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 92 (1097) , 20180341
Shear wave elastography for the diagnosis of small (≤2 cm) breast lesions: added value and factors associated with false results
Objective: We compared the diagnostic performance of B-mode ultrasound, shear wave elastography (SWE), and combined B-mode ultrasound and SWE in small breast lesions (≤ 2 cm), and evaluated the factors associated with false SWE results. Methods: A total of 428 small breast lesions (≤ 2 cm) of 415 consecutive patients between August 2013 and February 2017 were included. The diagnostic performance of each set was evaluated using the area under the receiver operating characteristic curve (AUC) analysis. Histologic diagnosis was used as reference standard. Multivariate logistic regression analyses identified the factors associated with false SWE results. Results: Of 428 lesions, 142 (33.2%) were malignant and 286 (66.8%) were benign. The AUC of the combined modality was higher than that of B-mode ultrasound (0.792 vs 0.572, p < 0.001) and that of SWE was higher than that of B-mode ultrasound (0.718 vs 0.572, p < 0.001). Multivariate analysis showed that the smaller lesion size and in situ cancer were associated with false negative, and patient’s age, high-risk lesion, shorter distance from the skin or chest wall, and deeper breast thickness were associated with false positive (all p < 0.05). Conclusions: The addition of SWE to B-mode ultrasound could improve the diagnostic performance in ≤ 2 cm lesions. However, ultrasound lesion size, pathology, and lesion location are likely to affect the SWE value and result in false results. Advances in knowledge: Despite the diagnostic usefulness of SWE in small breast lesions (≤ 2 cm), ultrasound lesion size, pathology, and lesion location were associated with false results.
- 1 July 2018
- Published by Elsevier in Clinical Imaging
- Vol. 50, 258-263
Differentiation of benign and metastatic axillary lymph nodes in breast cancer: additive value of shear wave elastography to B-mode ultrasound
- 1 July 2018
- Published by Elsevier in Clinical Imaging
- Vol. 50, 258-263
Differentiation of benign and metastatic axillary lymph nodes in breast cancer: additive value of shear wave elastography to B-mode ultrasound
- Open Access
- 9 February 2018
- Published by Springer Nature in Scientific Reports
- Vol. 8 (1) , 1-8
Applying Data-driven Imaging Biomarker in Mammography for Breast Cancer Screening: Preliminary Study
We assessed the feasibility of a data-driven imaging biomarker based on weakly supervised learning (DIB; an imaging biomarker derived from large-scale medical image data with deep learning technology) in mammography (DIB-MG). A total of 29,107 digital mammograms from five institutions (4,339 cancer cases and 24,768 normal cases) were included. After matching patients’ age, breast density, and equipment, 1,238 and 1,238 cases were chosen as validation and test sets, respectively, and the remainder were used for training. The core algorithm of DIB-MG is a deep convolutional neural network; a deep learning algorithm specialized for images. Each sample (case) is an exam composed of 4-view images (RCC, RMLO, LCC, and LMLO). For each case in a training set, the cancer probability inferred from DIB-MG is compared with the per-case ground-truth label. Then the model parameters in DIB-MG are updated based on the error between the prediction and the ground-truth. At the operating point (threshold) of 0.5, sensitivity was 75.6% and 76.1% when specificity was 90.2% and 88.5%, and AUC was 0.903 and 0.906 for the validation and test sets, respectively. This research showed the potential of DIB-MG as a screening tool for breast cancer.
- 9 February 2018
- Published by Springer Nature in Scientific Reports
- Vol. 8 (1) , 1-8
Open AccessApplying Data-driven Imaging Biomarker in Mammography for Breast Cancer Screening: Preliminary Study
We assessed the feasibility of a data-driven imaging biomarker based on weakly supervised learning (DIB; an imaging biomarker derived from large-scale medical image data with deep learning technology) in mammography (DIB-MG). A total of 29,107 digital mammograms from five institutions (4,339 cancer cases and 24,768 normal cases) were included. After matching patients’ age, breast density, and equipment, 1,238 and 1,238 cases were chosen as validation and test sets, respectively, and the remainder were used for training. The core algorithm of DIB-MG is a deep convolutional neural network; a deep learning algorithm specialized for images. Each sample (case) is an exam composed of 4-view images (RCC, RMLO, LCC, and LMLO). For each case in a training set, the cancer probability inferred from DIB-MG is compared with the per-case ground-truth label. Then the model parameters in DIB-MG are updated based on the error between the prediction and the ground-truth. At the operating point (threshold) of 0.5, sensitivity was 75.6% and 76.1% when specificity was 90.2% and 88.5%, and AUC was 0.903 and 0.906 for the validation and test sets, respectively. This research showed the potential of DIB-MG as a screening tool for breast cancer.
- 1 October 2017
- Published by Elsevier in Clinical Radiology
- Vol. 72 (10) , 878-886
Comparison of 3D and 2D shear-wave elastography for differentiating benign and malignant breast masses: focus on the diagnostic performance
- 1 October 2017
- Published by Elsevier in Clinical Radiology
- Vol. 72 (10) , 878-886
Comparison of 3D and 2D shear-wave elastography for differentiating benign and malignant breast masses: focus on the diagnostic performance