Tracking Lung Tumors in Orthogonal X-RaysReport as inadecuate

Tracking Lung Tumors in Orthogonal X-Rays - Download this document for free, or read online. Document in PDF available to download.

Computational and Mathematical Methods in MedicineVolume 2013 2013, Article ID 650463, 7 pages

Research ArticleMitsubishi Electric Research Laboratories, Cambridge, MA 02139, USA

Received 30 May 2013; Accepted 12 July 2013

Academic Editor: Kayvan Najarian

Copyright © 2013 Feng Li and Fatih Porikli. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


This paper presents a computationally very efficient, robust,automatic tracking method that does not require any implanted fiducialsfor low-contrast tumors. First, it generates a set of motion hypotheses and computes corresponding feature vectors in local windows withinorthogonal-axis X-ray images. Then, it fits a regression model that mapsfeatures to 3D tumor motions by minimizing geodesic distances on motion manifold. These hypotheses can be jointly generated in 3D to learna single 3D regression model or in 2D through back projection to learntwo 2D models separately. Tumor is tracked by applying regression tothe consecutive image pairs while selecting optimal window size at everytime. Evaluations are performed on orthogonal X-ray videos of 10 patients. Comparative experimental results demonstrate superior accuracy~1 pixel average error and robustness to varying imaging artifacts andnoise at the same time.

Author: Feng Li and Fatih Porikli



Related documents