Young Hwan Chang

The paper develops a deep learning framework to identify and quantify rare hybrid cells in pancreatic cancer models using fluorescence microscopy.

This study uses spatial transcriptomic and proteomic profiling to identify cell interaction patterns that predict progression of Barrett's esophagus.

This study identifies RUNX1 as a key driver of tumor-immune hybrid cell invasion and dissemination in colorectal cancer, highlighting circulating hybrid cells as a biomarker for metastasis.

This paper introduces a trajectory-centric framework to model dynamic tumor-immune interactions, showing that treatment-phase TME states predict immunotherapy response better than pre-treatment states.

The paper develops MMIST, a computational approach linking live-cell morphodynamics to gene expression changes during cell state transitions.

miniMTI reduces the number of molecular markers needed for multiplex tissue imaging by combining H&E with a few measured markers, preserving biological and clinical information.

The paper introduces an algorithm to correct mislabeling and align object positions in longitudinal 3D cell culture imaging, improving data integrity and reproducibility.

The paper introduces a computational method to synthesize marker stains from H&E images, improving marker prediction and reducing reliance on experimental data.

UniFORM normalizes multiplex tissue imaging data by aligning negative populations and preserving positive variation, outperforming existing methods in batch effect mitigation and downstream analysis.

COEXIST integrates serial multiplexed tissue images at the single-cell level by combining molecular profiles with spatial information to improve profiling and platform validation.

The paper introduces a framework for mathematical modeling of multicellular systems using interpretable cell behavior rules derived from biological knowledge and multi-omics data.

AxonFinder segments axons in prostate tumor microenvironments using deep learning, showing correlation between axon density and cancer risk.

The paper introduces a computational method to reduce CyCIF panel size while preserving information content through masked imaging modeling and imputation.

The paper presents an image analysis pipeline for detecting circulating hybrid cells in immunofluorescence images with human-level accuracy using a β-VAE and SVM classifier.

This study uses multiplexed imaging to analyze immune and stromal cell changes in abdominal aortic aneurysms (AAAs) based on C-reactive protein (CRP) levels, revealing distinct immune cell distributions and macrophage phenotypes associated with CRP deposition.

The paper proposes deep learning methods to reconstruct 3D CyCIF images and select optimal ROIs from histology and MTI data for tumor representation.

This study creates a multimodal tumor atlas to analyze how metastatic HR+ breast cancers adapt to CDK4/6 inhibitors, revealing mechanisms like mTORC1 activation and immune microenvironment changes.

The paper discusses challenges in digital image analysis of cancerous tissues and outlines solutions developed during a 2022 hackathon.

The paper introduces a dual-modality imaging method combining high-resolution immunofluorescence and imaging mass cytometry to generate whole-slide IMC images with accurate single-cell segmentation.

The paper introduces a method to evaluate segmentation performance in multiplex tissue imaging without ground truth labels by comparing segmentations from an ensemble of models.

This paper proposes a treatment strategy that reduces long-term tumor burden by decreasing tumor adaptation rates through differential selective treatment.

The paper develops computational methods to reduce multiplex imaging panels while retaining maximum information in breast cancer tissue microarrays.

This paper introduces a morphodynamical trajectory embedding method to analyze live-cell imaging data, revealing ligand-specific cell state transitions and improving trajectory modeling compared to snapshot-based analysis.

The paper develops open-source tools for analyzing multiplex tissue imaging data and demonstrates their application on a human breast cancer dataset.

The paper introduces ME-VAE, a multi-encoder VAE for single-cell image analysis that extracts transform-invariant biologically meaningful features, improving cell population separation and phenotypic differences.

This paper introduces a cell tracking method based on Voronoi partition and stable matching to improve tracking accuracy from coarsely sampled live-cell imaging data.

The paper introduces a method to separate domain-specific information using a cross-domain autoencoder and orthogonal gate block for improved domain translation.

The paper introduces a deep learning tool for automated histologic feature quantification in murine pancreatic disease models, showing high correlation with immunostaining results and accurate differentiation of disease states.

This paper introduces a deep learning method called SHIFT that translates histological images into virtual immunofluorescence images, improving efficiency and reducing costs in cancer diagnostics.