Probabilistic branching node detection using hybrid local features

Authors:
Haibin Ling;Michael Barnathan;Vasileios Megalooikonomou;Predrag R. Bakic;Andrew D. A. Maidment
Affiliations:
Center for Information Science and Technology, Department of Computer and Information Sciences, Philadelphia, PA;Data Engineering Laboratory, Department of Computer and Information Sciences, Philadelphia, PA;Data Engineering Laboratory, Department of Computer and Information Sciences, Philadelphia, PA;Department of Radiology, University of Pennsylvania, Philadelphia, PA;Department of Radiology, University of Pennsylvania, Philadelphia, PA
Venue:
ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Year:
2009

Citing 3
Cited 1

A decision-theoretic generalization of on-line learning and an application to boosting

Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
A review of vessel extraction techniques and algorithms

ACM Computing Surveys (CSUR)
Globally optimal active contours, sequential monte carlo and on-line learning for vessel segmentation

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III

Probabilistic branching node detection using adaboost and hybrid local features

ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro

Quantified Score

Hi-index	0.00

Visualization

Abstract

Probabilistic branching node inference is an important step for analyzing branching patterns involved in many anatomic structures. We propose combining machine learning techniques and hybrid image statistics to perform branching node inference, using a support vector machine as a probabilistic inference framework. Then, we use local image statistics at different image scales for feature representation, including the Harris cornerness, the Laplacian, and the eigenvalues of the Hessian. The proposed approach is applied to a breast imaging dataset. Despite the challenge of the task, our approach achieves very encouraging results, which are helpful for further analysis of the breast ducts and other branching structures.