Kwonmoo Lee

This paper develops a 3D glioblastoma model with deep learning to predict drug responses and invasion patterns.

This study shows survivin enhances VSMC migration in stiff environments, suggesting it could be a therapeutic target for arterial stiffness-related diseases.

This paper introduces PHet, a method for selecting features that preserve disease heterogeneity and improve subtype discovery in single-cell data.

HoloNet is a deep learning model that analyzes holographic images of breast cancer cells to classify cell types and quantify molecular markers, identifying new subtypes.

This paper introduces DeepHACX, a self-training deep learning framework for interpretable fine-grained phenotyping of live cell dynamics, revealing specific responses to pharmacological perturbations in migrating epithelial cells.

MARS-Net is a deep learning pipeline that improves cell edge segmentation across multiple live cell microscopy types, enabling accurate morphodynamics analysis.

The paper proposes a modeling framework to predict heterogeneous subcellular protrusion dynamics using ARX models trained on subcellular time series data from migrating cells.

This paper uses deep learning to detect cryptic lamellipodia edges in fluorescence time-lapse movies of collective cell migration, improving accuracy over conventional methods.