Robert Krueger
New York University, NY·Computer Science·Early-career
New spatial profiling technologies can scan human tissue and record both what cells look like and which genes they use, while keeping track of where each cell sits. That layout matters, because cancer growth, immune responses and the effects of therapy depend on how cells are arranged in tissue and how that arrangement changes over time.
- Fields
Computer Science
Biomedical Engineering
- Topics
visual analytics
data visualization
human-in-the-loop
- Grants
- 1 known grant, through Jun 2031
What they work on
- Design scalable algorithms that jointly represent tissue images and omics data from spatial profiling, so that very large multimodal datasets can be explored interactively.
- Integrate machine learning into interactive visual workflows that let biomedical experts steer and interpret AI analysis of how cells are arranged in tissue and change over time.
- Create narrative visualization tools and an interactive biomedical atlas to communicate spatial profiling findings, validated on real-world data from studies of cancer and immune responses.
More about the research
The resulting datasets are so large and complex that experts cannot explore them by eye, and fully automated AI analysis is unreliable for this kind of exploratory research.
Why it matters
Biomedical researchers studying cancer, immune responses and therapy effects in tissue need ways to make sense of huge imaging and gene-activity datasets. Interactive tools that let experts guide AI could help them find meaningful cell patterns more reliably, supporting progress toward precision medicine. The same approaches could carry over to spatial data in materials, geographic and astronomical sciences.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Alexander Endert
Georgia Institute of Technology, GA·Computer Science
Build an open-source software testbed with modular AI guidance components for chart creation and visual analysis of tabular data.
Alexis Battle
Johns Hopkins University, MD·Computer Science
Mentor early-stage investigators in study design, data pipelines and quantitative methods for multimodal, longitudinal data in aging and Alzheimer's disease research.
Jinhua Wang
University of Minnesota, MN·Computer Science
Develop new computational methods for single-cell multi-omics and spatial transcriptomics imaging, which maps where genes are active in tumor tissue, together with deep learning models that predict cancer outcomes.
The school
New York University: 72 labs on PI Pages, $1.5B a year on research, 540 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.