Renyu Zhang

Moved to my new homepage.

I am a 4th year PhD from the University of Chicago. My research is at the interface between healthcare and machine learning. My advisor is Robert Grossman and I also work closely with Aly Khan and Yuxin Chen. I got my bachelor degree from Shandong University and master degree from The Institute of Computing Technology of the Chinese Academy of Sciences.

Email  /  Google Scholar  /  GitHub

profile photo
Research

Most of my research is about medical images and RNA seq.

Boundary_png Evaluating and interpreting caption prediction for histopathology images
Renyu Zhang, Christopher Weber, Robert Grossman, Aly Khan
Machine Learning for Healthcare Conference, 2020
poster / bibtex

We introduce PathCap, a deep learning multi-scale framework, to predict captions from histopathology images using multi-scale views of whole-slide images. We demonstrate that our framework outperforms a standard baseline caption model on a diverse set of human tissues and provides interpretable contextual cues for understanding predicted captions. Finally, we draw attention to a novel dataset of histopathology images with captions from the Genotype-Tissue Expression (GTEx) project, providing a valuable dataset for the machine learning and healthcare community to benchmark future caption prediction and interpretation methods.

Boundary_png Evaluation of Hyperbolic Attention in Histopathology Images
Renyu Zhang, Aly Khan, Robert Grossman
The 20th IEEE International Conference on BioInformatics And BioEngineering, 2020

We bring together into a common framework three key ideas — multi-scale medical image analysis, the attention mechanism, and hyperbolic embeddings.

H&E Image-based Consensus Molecular Subtype Classification of Colorectal Cancer Using Weak Labeling
Andrew J. Kruger, Lingdao Sha, Madhavi Kannan, Rohan P. Joshi, Benjamin D. Leibowitz, Renyu Zhang, Aly A. Khan, Martin Stumpe
ASCO Annual Meeting, 2020
bibtex

We implemented and trained a novel deep multiple instance learning (MIL) framework that requires only a single label per WSI to identify morphological biomarkers and accelerate CMS classification.


This webpage uses the template from source code.