Localization of a linear structure object in medical images based on hidden Markov model

Authors:
Xu Tao;Xing Hancheng
Affiliations:
Department of Computer Science and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China and Department of Computer Science and Engineering, Southeas ...;Department of Computer Science and Engineering, Southeast University, Nanjing, People's Republic of China
Venue:
CBMS'03 Proceedings of the 16th IEEE conference on Computer-based medical systems
Year:
2003

Citing 2
Cited 0

Use of Shape Models to Search Digitized Spine X-rays

CBMS '00 Proceedings of the 13th IEEE Symposium on Computer-Based Medical Systems (CBMS'00)
Image classification by a two-dimensional hidden Markov model

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a novel approach to localization of a linear structure object (spine) in medical images using one-dimensional Hidden Markov Model is proposed. Feature sequence of a linear structure object is extracted by using a horizontal-line sampling window with fixed width along the central axis of the object in training phase and the model training is performed through maximum likelihood estimation provided by the Baum-Welch algorithm. A specific localization method derived from Viterbi algorithm is presented for determining a feature sequence in a test image, from which the position of a linear structure object could be obtained. The use of heuristic information improves obviously the performance of localization and the computational complexity. The experiments demonstrate the effectiveness in localization application based on the simple feature expression and the proposed localization method.