Angela Soeun Lee

Prof. Angela Soeun Lee

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2021 in Asian Journal of Surgery
Verified
Journal Article
Open access
SCSumin Chae
Sumin Chae
EKEun-Kyu Kim
Eun-Kyu Kim
YJYe Rang Jang
Ye Rang Jang
Angela Soeun LeeAngela Soeun Lee
Angela Soeun Lee
SKSeul Ki Kim
Seul Ki Kim
EKEunyoung Kang
Eunyoung Kang
This study aimed to compare the quality of life (QOL), psychosocial status, sexual function, and menopausal symptoms between the risk-reducing salpingo-oophorectomy (RRSO) and non-RRSO groups comprising BRCA mutation carriers and to evaluate the effect of timing of RRSO on those aspects. This cross-sectional study recruited BRCA mutation carriers aged ≥35 years between September 2015 and September 2016. Demographic data of carriers were collected. Outcomes were measured using the questionnaires addressing QOL, anxiety, depression, optimism, sexual function, and menopausal symptoms. Of 52 participants, 30 (57.7%) underwent RRSO, whereas 22 (42.3%) did not. In the RRSO group, 16 (53.3%) and 14 (46.7%) women underwent RRSO before and after menopause, respectively. The mean age in the RRSO group was higher than that in the non-RRSO group (49.8 vs. 42.1 years, respectively, p = 0.002). The scores for QOL, anxiety, depression, optimism, sexual function, and menopausal symptoms were similar between both groups. In the multivariate analysis, RRSO uptake was associated with worse physical QOL (coefficient, -5.350; 95% confidence interval, -10.593 to -0.108). With respect to the timing of RRSO, only the mental QOL was significantly lower in the postmenopausal RRSO group than in the premenopausal RRSO group (39.2 vs. 43.7, respectively, p = 0.043). We could not find any difference in mental QOL, psychosocial status, sexual function, and menopausal symptoms between the RRSO and non-RRSO groups. RRSO uptake only affected worse physical QOL. These results will help physicians counsel BRCA mutation carriers about the effect of RRSO on QOL.

10 February 2024 in Medicina
Verified
Journal Article
Open access
PDF file
JKJae Hong Kim
Jae Hong Kim
YKYun-Gyoung Kim
Yun-Gyoung Kim
KSKeun-Yeong Song
Keun-Yeong Song
HLHyung-Guhn Lim
Hyung-Guhn Lim
JJJeong-Pil Jeong
Jeong-Pil Jeong
HPHeung Kyu Park
Heung Kyu Park
Background and Objectives: The surge in breast-related surgeries in Korea underscores the critical need for an accurate early diagnosis of silicone breast implant-related issues. Complications such as BIA-ALCL and BIA-SCC add complexity to breast health concerns, necessitating vigilant monitoring. Despite advancements, discrepancies persist between ultrasonographic and pathologic classifications of silicone implant ruptures, highlighting a need for enhanced diagnostic tools. This study explores the reliability of ultrasonography in diagnosing silicone breast implant ruptures and determining the extent of silicone migration, specifically with a focus on guiding potential capsulectomy based on pathology. Materials and Methods: A comprehensive review of medical records encompassing 5557 breast implants across 2790 patients who underwent ultrasound-assisted examinations was conducted. Among the screened implants, 8.9% (249 cases) were diagnosed with silicone breast implant rupture through ultrasonography. Subsequently, 89 women underwent revisional surgery, involving capsulectomy. The pathological analysis of 111 periprosthetic capsules from these cases aimed to assess the extent of silicone migration, and the findings were juxtaposed with the existing ultrasonographic rupture classification. Results: The diagnostic agreement between preoperative sonography and postoperative findings reached 100% for silicone breast implant ruptures. All eighty prosthetic capsules exhibiting a snowstorm sign in ultrasonography demonstrated silicone migration to capsules upon pathologic findings. Conclusions: High-resolution ultrasonography emerged as a valuable and reliable imaging modality for diagnosing silicone breast implant ruptures, with a notable ability to ascertain the extent of free silicone migration to capsules. This diagnostic precision is pivotal in informing decisions about potential capsulectomy during revisional surgery. The study advocates for an update to the current binary ultrasonographic classification, suggesting a more nuanced categorization into three types (subcapsular, intracapsular, and extracapsular) based on pathology.

25 March 2024 in JMIR Preprints
Verified
Preprint
Open access
HKHo Heon Kim
Ho Heon Kim
WJWon Chan Jeong
Won Chan Jeong
KPKyungran Pi
Kyungran Pi
Angela Soeun LeeAngela Soeun Lee
Angela Soeun Lee
MKMin Soo Kim
Min Soo Kim
JKJae Hong Kim
Jae Hong Kim
BACKGROUND Breast implants, including textured variants, have been widely used in aesthetic and reconstructive mammoplasty. However, the textured type, which is one of the shell texture types of breast implants, has been identified as a possible etiologic factor for lymphoma, specifically breast implant–associated anaplastic large cell lymphoma (BIA-ALCL). Identifying the shell texture type of the implant is critical to diagnosing BIA-ALCL. However, distinguishing the shell texture type can be difficult due to the loss of human memory and medical history. An alternative approach is to use ultrasonography, but this method also has limitations in quantitative assessment. OBJECTIVE This study aims to determine the feasibility of using a deep learning model to classify the shell texture type of breast implants and make robust predictions from ultrasonography images from heterogeneous sources. METHODS A total of 19,502 breast implant images were retrospectively collected from heterogeneous sources, including images captured from both Canon and GE devices, images of ruptured implants, and images without implants, as well as publicly available images. The Canon images were trained using ResNet-50. The model’s performance on the Canon dataset was evaluated using stratified 5-fold cross-validation. Additionally, external validation was conducted using the GE and publicly available datasets. The area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (PRAUC) were calculated based on the contribution of the pixels with Gradient-weighted Class Activation Mapping (Grad-CAM). To identify the significant pixels for classification, we masked the pixels that contributed less than 10%, up to a maximum of 100%. To assess the model’s robustness to uncertainty, Shannon entropy was calculated for 4 image groups: Canon, GE, ruptured implants, and without implants. RESULTS The deep learning model achieved an average AUROC of 0.98 and a PRAUC of 0.88 in the Canon dataset. The model achieved an AUROC of 0.985 and a PRAUC of 0.748 for images captured with GE devices. Additionally, the model predicted an AUROC of 0.909 and a PRAUC of 0.958 for the publicly available dataset. This model maintained the PRAUC values for quantitative validation when masking up to 90% of the least-contributing pixels and the remnant pixels in breast shell layers. Furthermore, the prediction uncertainty increased in the following order: Canon (0.066), GE (0072), ruptured implants (0.371), and no implants (0.777). CONCLUSIONS We have demonstrated the feasibility of using deep learning to predict the shell texture type of breast implants. This approach quantifies the shell texture types of breast implants, supporting the first step in the diagnosis of BIA-ALCL. CLINICALTRIAL

19 March 2024 in medRxiv
Verified
Preprint
Open access
PDF file
HKHo Heon Kim
Ho Heon Kim
WJWon Chan Jeong
Won Chan Jeong
KPKyungran Pi
Kyungran Pi
Angela Soeun LeeAngela Soeun Lee
Angela Soeun Lee
MKMin Soo Kim
Min Soo Kim
JKJae Hong Kim
Jae Hong Kim
Introduction Breast implants, including textured variants, have been widely used in aesthetic and reconstructive mammoplasty. However, the textured type, which is one of the shell types of breast implants, has been identified as a possible carcinogenic factor for lymphoma, specifically breast implant-associated anaplastic large cell lymphoma (BIA-ALCL). Identifying the texture type of the implant is critical to the diagnosis of BIA-ALCL. However, distinguishing the shell type can be difficult due to human memory or loss of medical history. An alternative approach is to use ultrasonography, but this method also has limitations in quantitative assessment. Objective The objective of this study is to determine the feasibility of using a deep learning model to classify the textured shell type of breast implants and make robust predictions from ultrasonography images from heterogeneous sources. Methods A total of 19,502 breast implant images were retrospectively collected from heterogeneous sources, including images from both Canon (D1) and GE (D2), images of ruptured implants (D3), and images without implants (D4), as well as publicly available images (D5). The Canon (D1) images were trained using Resnet-50. The performance of the model on D1 was evaluated using stratified 5-fold cross-validation. Additionally, external validation was conducted using D2 and D5. The AUROC and PRAUC were calculated based on the contribution of the pixels with Grad-CAM. To identify the significant pixels for classification, we masked the pixels that contributed less than 10%, up to a maximum of 100%. To assess model robustness to uncertainty, Shannon entropy was calculated for four image groups: Canon (D1), GE (D2), ruptured implant (D3), and without implants (D5). Result The deep learning model achieved an average AUROC of 0.98 and a PRAUC of 0.88 in the Canon dataset (D1). For images captured with GE (D2), the model achieved an AUROC of 0.985 and a PRAUC of 0.748. Additionally, the model predicted an AUROC of 0.909 and a PRAUC of 0.958 for a dataset available online. For quantitative validation, this model maintained PRAUC up to 90% masking of less contributing pixels, and the remnant pixels located in breast shell layers. Furthermore, the prediction uncertainty increased in the following order: Canon (D1), GE (D2), ruptured implant (D3), no implant (D5) (0.066; 0072; 0.371; 0.777, respectively). Conclusion We have demonstrated the feasibility of using deep learning to predict the shell types of breast implants. With this approach, the textured shell types of breast implants can be quantified, supporting the first step in the diagnosis of BIA-ALCL.

5 November 2024 in JMIR Formative Research
Verified
Journal Article
Open access
HKHo Heon Kim
Ho Heon Kim
WJWon Chan Jeong
Won Chan Jeong
KPKyungran Pi
Kyungran Pi
Angela Soeun LeeAngela Soeun Lee
Angela Soeun Lee
MKMin Soo Kim
Min Soo Kim
JKJae Hong Kim
Jae Hong Kim
Background: Breast implants, including textured variants, have been widely used in aesthetic and reconstructive mammoplasty. However, the textured type, which is one of the shell texture types of breast implants, has been identified as a possible etiologic factor for lymphoma, specifically breast implant–associated anaplastic large cell lymphoma (BIA-ALCL). Identifying the shell texture type of the implant is critical to diagnosing BIA-ALCL. However, distinguishing the shell texture type can be difficult due to the loss of human memory and medical history. An alternative approach is to use ultrasonography, but this method also has limitations in quantitative assessment. Objective: This study aims to determine the feasibility of using a deep learning model to classify the shell texture type of breast implants and make robust predictions from ultrasonography images from heterogeneous sources. Methods: A total of 19,502 breast implant images were retrospectively collected from heterogeneous sources, including images captured from both Canon and GE devices, images of ruptured implants, and images without implants, as well as publicly available images. The Canon images were trained using ResNet-50. The model’s performance on the Canon dataset was evaluated using stratified 5-fold cross-validation. Additionally, external validation was conducted using the GE and publicly available datasets. The area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (PRAUC) were calculated based on the contribution of the pixels with Gradient-weighted Class Activation Mapping (Grad-CAM). To identify the significant pixels for classification, we masked the pixels that contributed less than 10%, up to a maximum of 100%. To assess the model’s robustness to uncertainty, Shannon entropy was calculated for 4 image groups: Canon, GE, ruptured implants, and without implants. Results: The deep learning model achieved an average AUROC of 0.98 and a PRAUC of 0.88 in the Canon dataset. The model achieved an AUROC of 0.985 and a PRAUC of 0.748 for images captured with GE devices. Additionally, the model predicted an AUROC of 0.909 and a PRAUC of 0.958 for the publicly available dataset. This model maintained the PRAUC values for quantitative validation when masking up to 90% of the least-contributing pixels and the remnant pixels in breast shell layers. Furthermore, the prediction uncertainty increased in the following order: Canon (0.066), GE (0072), ruptured implants (0.371), and no implants (0.777). Conclusions: We have demonstrated the feasibility of using deep learning to predict the shell texture type of breast implants. This approach quantifies the shell texture types of breast implants, supporting the first step in the diagnosis of BIA-ALCL.

1 January 2020 in Journal of Korean Medical Science
Verified
Journal Article
Open access
PDF file
JKJae Hong Kim
Jae Hong Kim
NPNam-Sun Paik
Nam-Sun Paik
MKMin Soo Kim
Min Soo Kim
HKHye Jin Kim
Hye Jin Kim
Angela Soeun LeeAngela Soeun Lee
Angela Soeun Lee
HPHeung Kyu Park
Heung Kyu Park
Lee JH, et al. J Korean Med Sci. 2020 Mar;35(18):e172. https://doi.org/10.3346/jkms.2020.35.e172