Yonsei University · Medicine
Professor Jiyoung Yoon's research lab specializes in medical imaging and molecular diagnostics, focusing on the integration of radiomics, artificial intelligence, and genomic biomarkers to improve noninvasive cancer detection and characterization. The lab investigates quantitative imaging features for predicting molecular markers such as PD-L1 and BRAFV600E mutations, while also exploring genetic alterations like 6q deletions in lymphomas. A key emphasis is placed on enhancing medical AI through advanced image augmentation techniques, such as GANs, to address data scarcity and improve diagnostic accuracy. The lab also examines the structural and functional properties of starches, linking molecular composition to resistant starch formation.
Figures are computed from collected data and may differ slightly.
Significant findings of the study Quantitative CT radiomic features can help predict PD-L1 expression, whereas none of the qualitative imaging findings is associated with PD-L1 positivity. What this study adds A prediction model composed of clinical variables and CT radiomic features may facilitate noninvasive assessment of PD-L1 expression.
Deep learning-based CAD for thyroid US can help us predict the BRAFV600E mutation in thyroid cancer. More multi-center studies with more cases are needed to further validate our study results.
Deletion of chromosome 6q has frequently been observed in natural killer (NK) cell lymphomas. The aim of this study, is to localize the commonly affected region in chromosome 6q and to compare the frequency of loss of heterozygosity (LOH) between the peripheral T and NK cell lymphomas. Eight cases of peripheral T cell lymphomas, not otherwise characterized (PTCL-NOC), and 5 cases of nasal-type NK/T cell lymphomas were enrolled for the study. Twelve polymorphic markers covering the regions from 6
Radiologists effectively classified chest pathologies with synthesized radiographs, suggesting that the images contained adequate clinical information. Furthermore, GAN augmentation enhanced CNN performance, providing a bypass to overcome data imbalance in medical AI training. CNN based methods rely on the amount and quality of training data; the present study showed that GAN augmentation could effectively augment training data for medical AI.
Influence of amylose content on formation and characteristics of enzyme-resistant starch (RS) was investigated by scanning electron microscopy, X-ray diffractometry and differential scanning calorimetry. RS yield increased up to 36.1% as the amylose content of com starch increased. Starch granules of Amylomaize Ⅴ and Ⅶ were more rounded and smaller than those of regular corn: some were elongated and had appendages. After autoclaving-cooling cycles, the granular structure disappeared and a contin
In patients with ILC, multifocality and the presence of NME on preoperative breast MRI were associated with positive resection margins.
• Predicting ductal carcinoma in situ upgrade is important, yet there is a lack of conclusive non-invasive biomarkers. • AI-CAD scores-raw numbers, ≥ 50%, and ≥ 75%-predicted ductal carcinoma in situ upgrade independently. • Quantitative AI-CAD results may help predict ductal carcinoma in situ upgrade and guide patient management.
Background Studies on the association between surveillance breast MRI in women with a personal history of breast cancer (PHBC) and advanced second breast cancer are lacking. Purpose To investigate the association between postoperative surveillance breast MRI and advanced second breast cancer in women with a PHBC by using propensity score matching (PSM). Materials and Methods Women who underwent breast cancer surgery between January 2009 and December 2014 were retrospectively identified at a sing
The Physical properties of corn starch were investigated by scanning electron microscopy, X-ray diffractometry and differential scanning calorimetry during the formation of enzyme-resistant starch (RS). Samples were studied in their native states and after annealing at 50, 55, 60 and 65℃ in excess water (starch : water=1 : 3) for 48 hr. Starch granules became smaller and more rounded after annealing than in their native state. Annealing did not change the X-ray profile of native corn starch. Aft
Purpose: Acute appendicitis is one of the most common surgical diseases and the accuracy of diagnosis has been reported to be between 71% and 85%. In this study we tried to determine whether abdominal sonographic examination is critical to the decision to operate and whether its use is essential before surgery of patients with clinically diagnosed or suspected acute appendicitis. Methods: A total of 552 patients with clinically diagnosed acute appendicitis from January 2000 to December 2001 were
Open papers in the app to read, cite, and organize with AI.