Location Registration and Recognition (LRR) for Longitudinal Evaluation of Corresponding Regions in CT Volumes

Authors:
Michal Sofka;Charles V. Stewart
Affiliations:
Department of Computer Science, Rensselaer Polytechnic Institute, Troy, New York, 12180---3590;Department of Computer Science, Rensselaer Polytechnic Institute, Troy, New York, 12180---3590
Venue:
MICCAI '08 Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II
Year:
2008

Citing 6
Cited 0

Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Automatic Panoramic Image Stitching using Invariant Features

International Journal of Computer Vision
Registration of Challenging Image Pairs: Initialization, Estimation, and Decision

IEEE Transactions on Pattern Analysis and Machine Intelligence
Non-parametric diffeomorphic image registration with the demons algorithm

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Automatic point landmark matching for regularizing nonlinear intensity registration: application to thoracic CT images

MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

The algorithm described in this paper takes (a) two temporally-separated CT scans, I1and I2, and (b) a series of locations in I1, and it produces, for each location, an affine transformation mapping the locations and their immediate neighborhood from I1to I2. It does this without deformable registration by using a combination of feature extraction, indexing, refinement and decision processes. Together these essentially "recognize" the neighborhoods. We show on lung CT scans that this works at near interactive speeds, and is at least as accurate as the Diffeomorphic Demons algorithm [1]. The algorithm may be used both for diagnosis and treatment monitoring.