Korea University · Medicine
Professor Bo Kyoung Seo's research lab specializes in diagnostic medical imaging and artificial intelligence, focusing on advancing breast cancer detection, characterization, and risk prediction. The lab integrates advanced imaging techniques—such as low-dose CT perfusion, ultrasound elastography, and mammography—with machine learning and radiomics to extract quantitative biomarkers for improved diagnosis and prognosis. Key research directions include optimizing imaging protocols for better lesion conspicuity, developing deep learning models for risk stratification in Asian populations, and exploring the correlation between imaging features and molecular subtypes of breast cancer. The lab emphasizes clinical translation, aiming to enhance early detection and personalized treatment planning through innovative imaging and data science approaches.
Figures are computed from collected data and may differ slightly.
At CT, SMM appears as a result of malignant neoplasms, inflammation, or vascular disorders.
Real-time compound and pulse-inversion harmonic imaging procedures are superior to conventional sonography in terms of both lesion conspicuity and the further characterization of breast nodules. Real-time compound imaging is the best technique for evaluation of the margin and internal echotexture of nodules, while pulse-inversion harmonic imaging is very effective for the evaluation of the posterior echo patterns.
Low-dose perfusion CT in the prone position is feasible to quantify tumor vascularity in breast cancers, and CT perfusion indexes are significantly correlated with prognostic biomarkers and molecular subtypes of breast cancer.
This prospective study enrolled 147 women with invasive breast cancer who underwent low-dose breast CT (80 kVp, 25 mAs, 1.01-1.38 mSv) before treatment. From each tumor, we extracted eight perfusion parameters using the maximum slope algorithm and 36 texture parameters using the filtered histogram technique. Relationships between CT parameters and histological factors were analyzed using five machine learning algorithms. Performance was compared using the area under the receiver-operating charac
The purpose of this study was to develop a mammography-based deep learning (DL) model for predicting the risk of breast cancer in Asian women. This retrospective study included 287 examinations in 153 women in the cancer group and 736 examinations in 447 women in the negative group, obtained from the databases of two tertiary hospitals between November 2012 and March 2022. All examinations were labeled as either dense breast or nondense breast, and then randomly assigned to either training, vali
Open papers in the app to read, cite, and organize with AI.
