With the exponential growth in image data collection, more advanced analyses are focusing on making full use of the cancer images to improve personalized short and long-term decision making. Our goal is to address the fundamental challenges in high resolution imaging data across cancer continuum from prevention to survivorship by establishing the statistical and computational infrastructure for a more efficient analysis and provide the next generation of tools for imaging epidemiology.

We aim to advance the frontier of cancer imaging data analysis in three dimensions:

  1. Methodology: Developing new statistical methodologies to handle high resolution cancer imaging data to optimize risk prediction and assess texture-phenotype relationship and causality;
  2. Computation: Developing statistical solutions that are computationally efficient for high resolution cancer imaging data on a standard computer;
  3. Implementation: Establishing computational infrastructure with open-source code and platforms for real-time implementation in the clinical setting.