Segmenting lung fields in serial chest radiographs using both population-based and patient-specific shape statistics

Yonghong Shi, Feihu Qi, Zhong Xue, Liya Chen, Kyoko Ito, Hidenori Matsuo, Dinggang Shen

Research output: Contribution to journalArticle

98 Citations (Scopus)

Abstract

This paper presents a new deformable model using both population-based and patient-specific shape statistics to segment lung fields from serial chest radiographs. There are two novelties in the proposed deformable model. First, a modified scale invariant feature transform (SIFT) local descriptor, which is more distinctive than the general intensity and gradient features, is used to characterize the image features in the vicinity of each pixel. Second, the deformable contour is constrained by both population-based and patient-specific shape statistics, and it yields more robust and accurate segmentation of lung fields for serial chest radiographs. In particular, for segmenting the initial time-point images, the population-based shape statistics is used to constrain the deformable contour; as more subsequent images of the same patient are acquired, the patient-specific shape statistics online collected from the previous segmentation results gradually takes more roles. Thus, this patient-specific shape statistics is updated each time when a new segmentation result is obtained, and it is further used to refine the segmentation results of all the available time-point images. Experimental results show that the proposed method is more robust and accurate than other active shape models in segmenting the lung fields from serial chest radiographs.

Original languageEnglish
Article number4359073
Pages (from-to)481-494
Number of pages14
JournalIEEE Transactions on Medical Imaging
Volume27
Issue number4
DOIs
Publication statusPublished - 2008 Apr 1
Externally publishedYes

Fingerprint

Thorax
Statistics
Lung
Population
Pixels

Keywords

  • Deformable model
  • Scale invariant feature transform (SIFT) local descriptor
  • Segmentation
  • Serial chest radiographs
  • Shape statistics

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology
  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Segmenting lung fields in serial chest radiographs using both population-based and patient-specific shape statistics. / Shi, Yonghong; Qi, Feihu; Xue, Zhong; Chen, Liya; Ito, Kyoko; Matsuo, Hidenori; Shen, Dinggang.

In: IEEE Transactions on Medical Imaging, Vol. 27, No. 4, 4359073, 01.04.2008, p. 481-494.

Research output: Contribution to journalArticle

Shi, Yonghong ; Qi, Feihu ; Xue, Zhong ; Chen, Liya ; Ito, Kyoko ; Matsuo, Hidenori ; Shen, Dinggang. / Segmenting lung fields in serial chest radiographs using both population-based and patient-specific shape statistics. In: IEEE Transactions on Medical Imaging. 2008 ; Vol. 27, No. 4. pp. 481-494.
@article{91625ff4a40643a88c3ed720f79700b2,
title = "Segmenting lung fields in serial chest radiographs using both population-based and patient-specific shape statistics",
abstract = "This paper presents a new deformable model using both population-based and patient-specific shape statistics to segment lung fields from serial chest radiographs. There are two novelties in the proposed deformable model. First, a modified scale invariant feature transform (SIFT) local descriptor, which is more distinctive than the general intensity and gradient features, is used to characterize the image features in the vicinity of each pixel. Second, the deformable contour is constrained by both population-based and patient-specific shape statistics, and it yields more robust and accurate segmentation of lung fields for serial chest radiographs. In particular, for segmenting the initial time-point images, the population-based shape statistics is used to constrain the deformable contour; as more subsequent images of the same patient are acquired, the patient-specific shape statistics online collected from the previous segmentation results gradually takes more roles. Thus, this patient-specific shape statistics is updated each time when a new segmentation result is obtained, and it is further used to refine the segmentation results of all the available time-point images. Experimental results show that the proposed method is more robust and accurate than other active shape models in segmenting the lung fields from serial chest radiographs.",
keywords = "Deformable model, Scale invariant feature transform (SIFT) local descriptor, Segmentation, Serial chest radiographs, Shape statistics",
author = "Yonghong Shi and Feihu Qi and Zhong Xue and Liya Chen and Kyoko Ito and Hidenori Matsuo and Dinggang Shen",
year = "2008",
month = "4",
day = "1",
doi = "10.1109/TMI.2007.908130",
language = "English",
volume = "27",
pages = "481--494",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Segmenting lung fields in serial chest radiographs using both population-based and patient-specific shape statistics

AU - Shi, Yonghong

AU - Qi, Feihu

AU - Xue, Zhong

AU - Chen, Liya

AU - Ito, Kyoko

AU - Matsuo, Hidenori

AU - Shen, Dinggang

PY - 2008/4/1

Y1 - 2008/4/1

N2 - This paper presents a new deformable model using both population-based and patient-specific shape statistics to segment lung fields from serial chest radiographs. There are two novelties in the proposed deformable model. First, a modified scale invariant feature transform (SIFT) local descriptor, which is more distinctive than the general intensity and gradient features, is used to characterize the image features in the vicinity of each pixel. Second, the deformable contour is constrained by both population-based and patient-specific shape statistics, and it yields more robust and accurate segmentation of lung fields for serial chest radiographs. In particular, for segmenting the initial time-point images, the population-based shape statistics is used to constrain the deformable contour; as more subsequent images of the same patient are acquired, the patient-specific shape statistics online collected from the previous segmentation results gradually takes more roles. Thus, this patient-specific shape statistics is updated each time when a new segmentation result is obtained, and it is further used to refine the segmentation results of all the available time-point images. Experimental results show that the proposed method is more robust and accurate than other active shape models in segmenting the lung fields from serial chest radiographs.

AB - This paper presents a new deformable model using both population-based and patient-specific shape statistics to segment lung fields from serial chest radiographs. There are two novelties in the proposed deformable model. First, a modified scale invariant feature transform (SIFT) local descriptor, which is more distinctive than the general intensity and gradient features, is used to characterize the image features in the vicinity of each pixel. Second, the deformable contour is constrained by both population-based and patient-specific shape statistics, and it yields more robust and accurate segmentation of lung fields for serial chest radiographs. In particular, for segmenting the initial time-point images, the population-based shape statistics is used to constrain the deformable contour; as more subsequent images of the same patient are acquired, the patient-specific shape statistics online collected from the previous segmentation results gradually takes more roles. Thus, this patient-specific shape statistics is updated each time when a new segmentation result is obtained, and it is further used to refine the segmentation results of all the available time-point images. Experimental results show that the proposed method is more robust and accurate than other active shape models in segmenting the lung fields from serial chest radiographs.

KW - Deformable model

KW - Scale invariant feature transform (SIFT) local descriptor

KW - Segmentation

KW - Serial chest radiographs

KW - Shape statistics

UR - http://www.scopus.com/inward/record.url?scp=41649087417&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=41649087417&partnerID=8YFLogxK

U2 - 10.1109/TMI.2007.908130

DO - 10.1109/TMI.2007.908130

M3 - Article

C2 - 18390345

AN - SCOPUS:41649087417

VL - 27

SP - 481

EP - 494

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 4

M1 - 4359073

ER -