IBM, the Cancer Institute of New Jersey (CINJ), and Rutgers will work together to develop cancer prognostic tools. The aim is to improve the accuracy of predicting patients’ responses to treatment and related clinical outcomes. The team recently received a $2.5 million grant from the NIH to facilitate this endeavor.
This project is an extension of the Help Defeat Cancer program in which IBM’s World Community Grid was used to characterize different types and stages of disease based on cancer tissue staining patterns. World Community Grid is a virtual supercomputer that taps into volunteers donating their unused computer time.
The central objective of the renewed collaboration is to build a deployable, grid-enabled, decision-support system that can automatically analyze and classify imaged cancer specimens more accurately. The team is also expanding the first phase of the project that studied breast, colon, and head and neck cancers.
An IBM team will concentrate on establishing high-performance medical imaging and informatics. Investigators at CINJ will also establish a Center for High-Throughput Data Analysis for Cancer Research. The primary objective of the center is to develop pattern recognition algorithms that can simultaneously take into consideration information contained in digitally archived cancer specimens, radiology images, and proteomic and genomic data for improved assessment of disease onset and progression.
The partners believe that it will be a useful tool in the selection of personalized treatments based on how patients with similar protein expression signatures and cancers have reacted to previous therapies.
“World Community Grid enabled us to validate our imaging and pattern recognition algorithms and establish a reference library of expression signatures for more than 100,000 digitally imaged tissue samples,” says David J. Foran, Ph.D., director of the Center for Biomedical Imaging & Informatics at CINJ and lead investigator for the project.
“The overarching goal of the new NIH grant is to expand the library to include signatures for a wider range of disorders and make it, along with the decision support technology, available to the research and clinical communities as grid-enabled, deployable software.”