Research
Research Interests:
Quantitative Image analysis
Machine Learning / Deep Learning
Systems Biology
Control / Mathematical Modeling
COEXIST: Coordinated single-cell integration of serial multiplexed tissue images
https://github.com/heussner/coexist
Quantitative image analysis pipeline for detecting circulating hybrid cells in immunofluorescence images with human-level accuracy
MIM-CyCIF: Masked Imaging Modeling for Enhancing Cyclic Immunofluorescence (CyCIF) with Panel Reduction and Imputation
3D multiplexed tissue imaging reconstruction and optimized region-of-interest (ROI) selection through deep learning model of channels embedding
Dual-modality imaging of immunofluorescence and imaging mass cytometry for whole slide imaging and accurate segmentation
Analysis of Shared Morphologies Between Human breast cancer and Mice TMAs.
Luke Strgar, Eun-Na Kim, Bipasa Bose, Luke Ternes, Guillaume Thibault, Young Hwan Chang, "Evaluation of Nuclei Segmentations in Absence of Ground Truth Labels"
Erik Ames Burlingame, Jennifer Eng, Guillaume Thibault, Koei Chin, Joe W. Gray, Young Hwan Chang, "Toward reproducible, scalable, and robust data analysis across multiplex tissue imaging platforms"
Luke Ternes, Joe W Gray, Laura Heiser, Young Hwan Chang. "Feature controlled variational autoencoder to learn biologically meaningful features for single cell image analysis”
LINCS Virtual Symposium (November 19-20, 2020)
15th Machine Learning in Computational Biology (MLCB) meeting
Workshop on Learning Meaningful Representations of Life (LMRL) at NeurIPS 2020
Elizabeth Mitchell, Sonali Jindal, Tiffany Chan, Jayasri Narasimhan, Shamilene Sivagnanam, Elliot Gray, Young Hwan Chang, Sheila Weinmann, Pepper Schedin, "Loss of myoepithelial calponin-1 characterizes high risk ductal carcinoma in situ cases, which are further stratified by T cell composition", Molecular Carcinogenesis (special edition)
Luke Ternes et al, "Iterative Deep learning based segmentation on Cyclic Immunofluorescence imaging by using recursive refinement" (IEEE ISBI 2020)
Erik Burlingame et al, "Balanced learning of cell state representations", Learning Meaningful Representation of Life (NeurIPS 2019 Workshop)
Geoffrey F. Schau et al, "Estimating Mutual Information Content of Biomedical Data Modalities through Self-Supervised Domain Translation in Prostate Cancer", Learning Meaningful Representation of Life (NeurIPS 2019 Workshop, IEEE CDC 2020)
Geoffrey F. Schau et al, "Predicting Primary Site of Secondary Liver Cancer with a Neural Estimator of Metastatic Origin (NEMO)"
Geoffrey F. Schau et al, DL based unsupervised approach identify morphological features associated with metastatic origin
Automated single cell tracking for longitudinal imaging of neuro-degeneration (collaborated with Finkbeiner Lab @ UCSF)
Luke Ternes et al, "Utilizing deep learning to enhance and accelerate pancreatic disease quantification in murine cohorts"
Young Hwan Chang et al, "RESTORE: Robust intEnSiTy nORmalization mEthod for multiplexed imaging"
Erik Burlingame et al, "SHIFT: Speedy Histological-to-ImmunoFluorescent Translation of whole slide images using conditional generative adversarial networks"
Multiplexed imaging applications
Geoffrey Schau et al, "Variational Autoencoding Tissue Response to Microenvironment Perturbation"
Center for Cognitive Robot Research (KIST) (July 2006 - July 2008)
Humanoid Robot Walking & Balancing
Video clip
Hyudai-Kia R&D Center (Feb 2004 to June 2006)
Suspension & Steering System
S.P.M.D (Suspension Parameter Measurement Database, vehicle dynamics)
Intelligent System and Vibration Control Lab, KAIST (Sept 2002 to Feb 2004)
Fluid/structure and structure/control interaction problem by National Research Laboratory: “Development of EFPI sensor system and its application to flutter suppression”
Design of fiber optic sensor system and sensoriactuator
Smart Structure: fiber optic sensor, piezoelectric material