Content-based Histopathology Image Retrieval with High Performance Computing

Overview of the Project:

Research in content-based image retrieval (CBIR) has emerged as an important focus of investigation in multiple image-related disciplines. We explore a broad spectrum of potential clinical applications in pathology with a newly developed set of retrieval algorithms that were fine-tuned for each class of digital pathology images, including peripheral blood smears, mammary glands, glomeruli (kidney) and Hematoxylin-stained breast tissue microarray (TMA). We utilized the CometCloud autonomic cloud engine to run the CBIR algorithms in parallel across federated computational resources.  The algorithms will determine the extent to which cell samples taken from patients match the images of cancerous cells stored in our database.


  1. David J. Foran and Xin Qi from the Center for Biomedical Imaging & Informatics, The Cancer Institute of New Jersey, New Brunswick, NJ
  2. Lin Yang from the Division of Biomedical Informatics, Department of Biostatistics, Department of Computer Science, University of Kentucky, Lexington, KY
  3. Javier Diaz-Montes , Manish Parashar, Ivan Rodero from  Rutgers Discovery Informatics Institute, Dept. of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ