An interactive lung field segmentation scheme with automated capability

https://doi.org/10.1016/j.dsp.2012.12.021Get rights and content

Abstract

Feasible clinical application of any automated segmenting methodology demands more than just accuracy. Amendment to the automated delineation is necessary when the algorithm fails, however, integrated solution to such a scenario is largely absent in literature. Hence in this survey we devised an architecture that does both the automated and interactive lung field localizations using a single segmenting engine—random walker algorithm—so that intuitive amendment is only necessary when the automated generated delineation is unsatisfactory. The algorithm proceeds by first extracting 18 intensity profiles running horizontally, each of them equally spacing apart, and in each intensity profile three extreme points denoting the two lungs and the esophagus are determined through profile matching. This done, the algorithm removes profiles that do not intersect with the lung, and the rest of the extreme points are plugged into random walker algorithm to perform segmentation. The achieved accuracy in localization by the above was 0.8875 in terms of overlap measure (the maximum value for this parameter is 1) over 341 images. In the case where unsatisfactory delineation prompts amendment necessary, the user can interactively segment the lung by just a shift on some of the previous-determined points to the desired locations, and random walker algorithm is run again with the amended input. By such a fusion, the benefits of both the automated and interactive segmentation are shared in a single architecture.

Section snippets

Jen Hong Tan, Ph.D., is an application research engineer of Ngee Ann Polytechnic, Singapore. He received both his B.Eng. (Mechanical) and Ph.D. in Nanyang Technological University of Singapore. He works on projects such as computer-aided diagnosis in chest radiography (in collaboration with SATA CommHealth Singapore), and non-contact tear evaporimetry using infrared thermography (with Singapore Eye Research Institute).

References (32)

  • J. Duryea et al.

    A fully automated algorithm for the segmentation of lung fields on digital chest radiographic images

    Med. Phys.

    (1995)
  • E. Pietka

    Lung segmentation in digital radiographs

    J. Digit. Imaging

    (1994)
  • X.W. Xu et al.

    Image feature analysis for computer-aided diagnosis: Accurate determination of ribcage boundary in chest radiographs

    Med. Phys.

    (1995)
  • X.W. Xu et al.

    Image feature analysis for computer-aided diagnosis: Detection of right and left hemidiaphragm edges and delineation of lung field in chest radiographs

    Med. Phys.

    (1996)
  • S.G. Armato et al.

    Automated lung segmentation in digital lateral chest radiographs

    Med. Phys.

    (1998)
  • M.F. McNitt-Gray et al.

    Pattern classification approach to segmentation of chest radiographs

    • Cited by (0)

    Jen Hong Tan, Ph.D., is an application research engineer of Ngee Ann Polytechnic, Singapore. He received both his B.Eng. (Mechanical) and Ph.D. in Nanyang Technological University of Singapore. He works on projects such as computer-aided diagnosis in chest radiography (in collaboration with SATA CommHealth Singapore), and non-contact tear evaporimetry using infrared thermography (with Singapore Eye Research Institute).

    U. Rajendra Acharya, Ph.D., D.Eng. is a Visiting faculty in Ngee Ann Polytechnic, Singapore. He is also (i) Adjunct Professor in University of Malaya, Malaysia, (ii) Adjunct faculty in Singapore Institute of Technology-University of Glasgow, Singapore, and (iii) Associate faculty in SIM University, Singapore. He received his Ph.D. from National Institute of Technology Karnataka, Surathkal, India, and D.Eng. from Chiba University, Japan. He has published more than 285 papers, in refereed international SCI-IF journals (178), international conference proceedings (48), textbook chapters (62), books (15 including in press) with h-index of 24 (h-index=21 without self-citations, Scopus) and 27 (Google scholar with more than 2600 citations). He has worked on various funded projects with grants worth more than 2 million SGD. Please visit http://urajendraacharya.webs.com/ for more details.

    Choo Min Lim, M.Eng., Ph.D. is a senior director in the school of Engineering, Ngee Ann Polytechnic, Singapore. He received the B.Eng., M.Eng. and Ph.D. degrees from the National University of Singapore in 1976, 1981 and 1986, respectively. He has published more than 80 international journal papers and edited a book. His research interests include neural network-based control, fuzzy logic control, bioinformatics, optimization and the development of hardware (training kit sets) and software for supporting mobile computing. He has secured numerous funding from external organizations and grant bodies.

    K. Thomas Abraham, MBA, Ph.D. is the CEO of SATA CommHealth, Singapore, a not-for-profit organization focusing on community health. He graduated with a B.Sc. Pharm degree from the National University of Singapore in 1981 and obtained his MBA in Health Services Management from the University of Dallas (USA) in 1998. He obtained his Ph.D. in Business and Management from the University of South Australia in 2007. In his role as CEO, he is responsible for the management and development of SATA CommHealthʼs business and community services. He has also delivered many talks and training programs both locally and overseas. He is currently a board member of the International Union Against Tuberculosis and Lung Diseases Asia Pacific. His research interests include branding, corporate reputation, and community health services.

    View full text
    Copyright © 2013 Elsevier Inc. All rights reserved.