Probabilistic branching node detection using adaboost and hybrid local features

Authors:
Tatyana Nuzhnaya;Michael Barnathan;Haibin Ling;Vasileios Megalooikonomou;Predrag R. Bakic;Andrew D. A. Maidmen
Affiliations:
Data Engineering Laboratory, Department of Computer and Information Sciences, Temple University, Philadelphia, PA;Data Engineering Laboratory, Department of Computer and Information Sciences, Temple University, Philadelphia, PA;Center for Information Science and Technology, Department of Computer and Information Sciences, Temple University, Philadelphia, PA;Data Engineering Laboratory, Department of Computer and Information Sciences, Temple University, Philadelphia, PA;Department of Radiology, University of Pennsylvania, Philadelphia, PA;Department of Radiology, University of Pennsylvania, Philadelphia, PA
Venue:
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Year:
2010

Citing 4
Cited 0

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)
Probabilistic branching node detection using hybrid local features

ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
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

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. Based on an approach we have developed previously, we investigate combining machine learning techniques and hybrid image statistics for probabilistic branching node inference, using adaptive boosting as a probabilistic inference framework. Then, we use local image statistics at different image scales for feature representation, including the Harris cornerness, Laplacian, eigenvalues of the Hessian, and Harralick texture features. The proposed approach is applied to a breast imaging dataset consisting of 30 images, 7 of which were previously reported. The use of boosting and the Harralick texture feature further improves upon our previous results, highlighting the role of texture in the analysis of the breast ducts and other branching structures.