Graphics enhanced version of this site

Knowledge-Guided Deformable Registration
This project is no longer active.

Head: Takeo Kanade

Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213

Associated centers: VASC and MRTC

For more information, see this project's homepage.

The goal of this research is to match corresponding anatomical structures across individuals, and to detect possible pathologies. The current image data is Magnetic Resonance Imaging (MRI) of human brains. MRI datasets are volumetric images which provide 3-D anatomical information. They consist of parallel cross-sections scanned along one of three principal axes. The current approach is to deform a hand-segmented and labelled atlas (Courtesy of Harvard Medical School/Brigham and Women's Hospital) to match a patient's brain, so as to segment and label the patient's anatomical structures using information derived from the atlas. The algorithm applies a hierarchy of deformable models to the atlas to match with the patient at increasing accuracy. A prototype, ADORE (Anomaly Detection thrOugh REgistration), is developed to employ the registration algorithm to detect pathologies that cause morphological changes in the brain.

Name - Title <Email Address>
• [Home] Mei Chen - PhD Student, RI
• [Home] Takeo Kanade - U.A. and Helen Whitaker University Prof., RI/CS <tk@cs.cmu.edu>

• Bootstrap a statistical brain atlas
  M. Chen, T. Kanade, and D. Pomerleau
  Fifth IEEE Workshop on Applications of Computer Vision, December, 2000, pp. 114 - 119. [Abstract]
  Download: pdf [483 KB] copyrighted

• 3-D Deformable Registration Using a Statistical Atlas with Applications in Medicine
  M. Chen
  doctoral dissertation, tech. report CMU-RI-TR-99-20, Robotics Institute, Carnegie Mellon University, October, 1999. [Abstract]
  Download: pdf [1757 KB], ps.gz [4740 KB] copyrighted

• Probabilistic Registration of 3-D Medical Images
  M. Chen, T. Kanade, D. Pomerleau, and J. Schneider
  tech. report CMU-RI-TR-99-16, Robotics Institute, Carnegie Mellon University, July, 1999. [Abstract]
  Download: pdf [538 KB], ps.gz [1644 KB] copyrighted

• 3-D Deformable Registration of Medical Images Using a Statistical Atlas
  M. Chen, T. Kanade, D. Pomerleau, and J. Schneider
  tech. report CMU-RI-TR-98-35, Robotics Institute, Carnegie Mellon University, December, 1998. [Abstract]
  Download: pdf [373 KB], ps.gz [958 KB] copyrighted

• Medical Image - Atlas Registration Using Deformable Models for Anomaly Detection
  M. Chen, T. Kanade, and D. Pomerleau
  Proceedings of the Image Understanding Workshop, November, 1998. [Abstract]
  Download: pdf [552 KB], ps.gz [1703 KB] copyrighted

• Anomaly Detection through Registration
  M. Chen, T. Kanade, H. Rowley, and D. Pomerleau
  IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June, 1998, pp. 304 - 310. [Abstract]
  Download: pdf [807 KB], ps.gz [1800 KB] copyrighted

• Quantitative Study of Brain Anatomy
  M. Chen, T. Kanade, H. Rowley, and D. Pomerleau
  IEEE Workshop on Biomedical Image Analysis, June, 1998. [Abstract]
  Download: pdf [411 KB], ps.gz [1118 KB] copyrighted

• Quantitative Study of Brain Anatomy
  M. Chen, T. Kanade, H. Rowley, and D. Pomerleau
  tech. report CMU-RI-TR-98-05, Robotics Institute, Carnegie Mellon University, March, 1998. [Abstract]
  Download: pdf [417 KB], ps.gz [1069 KB] copyrighted

• Anomaly detection through registration
  M. Chen, T. Kanade, D. Pomerleau, and H. Rowley
  NASA Image Registration Workshop, November, 1997. [Abstract]
  Download: pdf [961 KB], ps.gz [2027 KB] copyrighted

• Anomaly Detection through Registration
  M. Chen, T. Kanade, H. Rowley, and D. Pomerleau
  tech. report CMU-RI-TR-97-41, Robotics Institute, Carnegie Mellon University, November, 1997. [Abstract]
  Download: pdf [966 KB], ps.gz [2047 KB] copyrighted