Lung Fields Segmentation Algorithm in Chest Radiography - Advances in Image and Graphics Technologies - page 137

Lung Fields Segmentation Algorithm
in Chest Radiography

Guodong Zhang, Lin Cong, Liu Wang, and Wei Guo *

School of Computer, Shenyang Aerospace University
110136 Shenyang, China
{zhanggd,guowei}@sau.edu.cn, [e-mail],
[e-mail]

Abstract. Accurate segmentation of lung fields in chest radiography is an es-
sential part of computer-aided detection. We proposed a segmentation method
by use of feature images, gray and shape cost, and modification method. The
outline of lung fields in the training set was marked and aligned to create an ini-
tial outline. Then, dynamic program was employed to determine the optimal
one in terms of the gray and shape cost in the six feature images. Finally, the
lung outline was modified by Active Shape Model. The experimental results
show that the average segmentation overlaps without and with feature images
achieve 82.18% and 89.07%, respectively. After the modification of segmenta-
tion, the average overlap can reach 90.26%.

Keywords: Feature image, gray and shape cost, Active Shape Model.

1 Introduction

Lung cancer has become one of the most serious threatens to human life and health.
Especially in recent years with environmental degradation caused by air pollution and
a significant increase of smokers, the morbidity and mortality of lung cancer are
growing fast. In American, an estimated 228,190 new cases of lung cancer and
159,840 deaths cases were expected in 2013, the death cases accounting for about
27% of all the cancer deaths[1]. In our country, the estimated 493,348 deaths in
2008[2], the mortality increased by 60% compared to 2004-2005. Chinese Cancer
Prevention and Control Plan (2004-2010) considered lung cancer as an important
issue [3]. Studies had shown that, if the cancer can be diagnosed and treated early, the
number of the survival rate of patients with early stage lung cancer would be higher
than 90% after 10 years [4]. Therefore, early detection and treatment of lung cancer
becomes very critical.
With the development of computer-aided detection technology, the performance of
lung cancer detection is greatly improved. Currently, chest radiography was used in
most hospitals to detect lung cancer. The chest radiography has become the primary

* Corresponding author.