Yonsei University · 医学
Professor Jung Hyun Yoon's research lab specializes in medical imaging and artificial intelligence, focusing on improving diagnostic accuracy and efficiency in breast and thyroid cancer screening. The lab investigates AI-driven applications in mammography, including digital mammography and tomosynthesis, to enhance early detection and risk stratification. Key research directions include elastography for improved specificity in ultrasound, computer-aided diagnosis systems, and the integration of AI tools like S-Detect to support radiologists across varying levels of expertise. The lab also evaluates the clinical feasibility and performance of emerging technologies to optimize patient management and reduce diagnostic variability.
Figures are computed from collected data and may differ slightly.
Both TIRADS and the ATA guidelines provide effective malignancy risk stratification for thyroid nodules. Nodules that do not meet the criteria for a specific pattern with the ATA guidelines have a relatively high risk of malignancy (18.2%).
Background There is considerable interest in the potential use of artificial intelligence (AI) systems in mammographic screening. However, it is essential to critically evaluate the performance of AI before it can become a modality used for independent mammographic interpretation. Purpose To evaluate the reported standalone performances of AI for interpretation of digital mammography and digital breast tomosynthesis (DBT). Materials and Methods A systematic search was conducted in PubMed, Google
Elastography improves the specificity, positive predictive value, and accuracy of ultrasound. However, significant interobserver variability exists, with real-time elastographic performance showing fair agreement.
In this study, US-FNAB appeared to be a relatively accurate method to evaluate thyroid nodules larger than 3 cm, with false-negative rates of about 2%. Much larger series would be required to determine its utility in this setting.
During the past decade, researchers have investigated the use of computer-aided mammography interpretation. With the application of deep learning technology, artificial intelligence (AI)-based algorithms for mammography have shown promising results in the quantitative assessment of parenchymal density, detection and diagnosis of breast cancer, and prediction of breast cancer risk, enabling more precise patient management. AI-based algorithms may also enhance the efficiency of the interpretation
S-Detect is a clinically feasible diagnostic tool that can be used to improve the specificity, PPV, and accuracy of breast US, with a moderate degree of agreement in final assessments, regardless of the experience of the radiologist.
Purpose To investigate the diagnostic performances of six guidelines used to assess thyroid nodules and to determine whether any of these guidelines identify cancers of aggressive form in this population. Materials and Methods From March 2007 to February 2010, 4696 thyroid nodules that were 1-2 cm in 4585 patients were diagnosed as benign or malignant on the basis of cytopathologic results. Ultrasonographic examinations of the thyroid nodules were retrospectively reviewed and categorized accordi
Fine needle aspiration (FNA) is currently accepted as an easy, safe, and reliable tool for the diagnosis of thyroid nodules. Nonetheless, a proportion of FNA samples are categorized into non-diagnostic or indeterminate cytology, which frustrates both the clinician and patient. To overcome this limitation of FNA, core needle biopsy (CNB) of the thyroid has been proposed as an additional diagnostic method for more accurate and decisive diagnosis for thyroid nodules of concern. In this review, we f
PDO sutures cause specific changes to the surrounding tissues that result in neo-collagenesis, a fibrous merging effect, fat reduction, tissue contracture, and an improved vascular environment. The results of this study explain the positive changes described in previous clinical research.
The follicular variant of papillary thyroid carcinoma tends to have relatively benign sonographic features, such as hypoechogenicity, well-defined margins, an oval shape, and no microcalcifications, but most lesions were correctly classified as malignant by both sonography and FNAB. The possibility of FVPTC should be considered when thyroid nodules with a relatively benign sonographic appearance have suspicious or malignant FNAB results.
Suspicious US features are useful in predicting malignancy among AUS subcategories but not in FLUS subcategories. Subcategorization into AUS and FLUS cytology may be helpful in deciding upon treatment or management of thyroid nodules.
Open papers in the app to read, cite, and organize with AI.