Medical Imaging

Most of my undergraduate research experience was in content-based image retrieval (CBIR) systems for medical images, and particularly for computed tomography (CT) images of lung nodules. During the summer of 2006, I participated in the MedIX research experience for undergraduates (REU) program at DePaul University in Chicago.

BRISC Overview

I was on a team with two other undergraduate computer science students under the leadership of Dr. Daniela Raicu. We developed an image lookup tool for the database of lung nodule images provided by the Lung Image Database Consortium (LIDC). With this tool we compared the retrieval effectiveness of three different texture features extraction methods: Haralick co-occurrence matrices, Gabor filtering, and Markov Random Fields. I presented our results at the SPIE Medical Imaging ’07 conference in San Diego.

We were able to release the project source code under the GNU General Public License (GPL) and it is available on SourceForge. The figure above shows an overview of what the tool does. For more information, you can check out our documentation and papers on the website.

Project website:


  • M. Lam, T. Disney, D. Raicu, J. Furst, D.S. Channin, “BRISC – An Open Source Pulmonary Nodule Image Retrieval Framework”, Journal of Digital Imaging, Volume 20, Supplement 1; 63-71. 2007. (PDF)
  • T. Disney, M. Lam, D. Raicu, J. Furst, D. Channin, “A Lookup and Reference Tool for Pulmonary Computed Tomography Nodules”, The 2007 Annual Meeting of the Society for Imaging Informatics in Medicine (SIIM 2007), Rhode Island, June 2007. (PDF)
  • M. Lam, T. Disney, M. Pham, D. Raicu, J. Furst, R. Susomboon. “Content-Based Image Retrieval for Pulmonary Computed Tomography Nodule Images.” SPIE Medical Imaging Conference: San Diego, CA. February 2007. (PDF)


  • “Open source system aids pulmonary nodule detection.” Online article for PACSweb written by Douglas Page. 8 Nov 2007. (link)

Leave a Reply

Your email address will not be published. Required fields are marked *