J
Juhun Lee
Researcher at University of Pittsburgh
Publications - 35
Citations - 267
Juhun Lee is an academic researcher from University of Pittsburgh. The author has contributed to research in topics: Breast cancer & Computer science. The author has an hindex of 7, co-authored 29 publications receiving 198 citations. Previous affiliations of Juhun Lee include University of Texas MD Anderson Cancer Center & University of California, Davis.
Papers
More filters
Journal ArticleDOI
Automated mammographic breast density estimation using a fully convolutional network.
Juhun Lee,Robert M. Nishikawa +1 more
TL;DR: A new deep learning based algorithm for mammographic breast density estimation using deep learning showed that the proposed algorithm correlated well with BI-RADS density assessments by radiologists and outperformed an existing state of the art algorithm.
Journal ArticleDOI
Validation of Stereophotogrammetry of the Human Torso
Juhun Lee,Manas M. Kawale,Fatima A. Merchant,June Weston,Michelle Cororve Fingeret,Dianne Ladewig,Greg P Reece,Melissa A. Crosby,Elisabeth K. Beahm,Mia K. Markey,Mia K. Markey +10 more
TL;DR: Stereophotogrammetry from 3D images obtained from the 3dMD torso system is effective for quantifying breast morphology and tools for surgical planning and evaluation based on stereophotograms have the potential to improve breast surgery outcomes.
Journal ArticleDOI
3D Symmetry Measure Invariant to Subject Pose During Image Acquisition
Manas M. Kawale,Juhun Lee,Shi Yin Leung,Michelle Cororve Fingeret,Greg P Reece,Melissa A. Crosby,Elisabeth K. Beahm,Mia K. Markey,Mia K. Markey,Fatima A. Merchant +9 more
TL;DR: The data suggests that the 3D pBRA index is linearly correlated with the 2D counterpart for both of the poses, and is independent of the localization of fiducial points within a tolerance limit of 7 mm.
Journal ArticleDOI
A Novel Quantitative Measure of Breast Curvature Based on Catenary
TL;DR: A novel quantitative measure of breast curvature based on catenary is introduced, which contains useful information for quantifying the curvature differences between breasts undergoing TE/Implant reconstruction and untreated breasts, and identifying the effect of patient variables on the breast shape.
Journal ArticleDOI
Local curvature analysis for classifying breast tumors: Preliminary analysis in dedicated breast CT
TL;DR: The normalized curvature measure contains useful information in classifying breast tumors and can reduce the number of features in a classifier, which may result in more robust classifiers for different datasets.