Mobile Networks and Applications

, Volume 23, Issue 6, pp 1669–1679 | Cite as

Extraction of GGO Candidate Regions on Thoracic CT Images using SuperVoxel-Based Graph Cuts for Healthcare Systems

  • Huimin LuEmail author
  • Masashi Kondo
  • Yujie Li
  • JooKooi Tan
  • Hyoungseop Kim
  • Seiichi Murakami
  • Takotoshi Aoki
  • Shoji Kido


In this paper, we propose a method to reduce artifacts on temporal difference images by improving the conventional method using a non-rigid registration method for ground glass opacification (GGO), which is light in concentration and difficult to detect early. In this method, global matching, local matching, and 3D elastic matching are performed on the current image and past image, and an initial temporal difference image is generated. After that, we use an Iris filter, which is the gradient vector concentration degree filter, to determine the initial GGO candidate regions and perform segmentation using SuperVoxel and Graph Cuts in which a superpixel is extended to three dimensions for each region of interest. For each extracted region, a support vector machine (SVM) is used to reduce the over-segmentation. Finally, in the method that greatly reduces artifacts other than the remaining GGO candidate regions, Voxel Matching is applied to generate the final temporal difference image, emphasizing the GGO regions while reducing the artifact. The resulting ratio of artifacts to lung volume is 0.101 with an FWHM of 28.3, which is an improvement over the conventional method and shows the proposed method’s effectiveness.


Computer aided diagnosis Temporal subtraction Iris filter Graph cuts SVM Voxel matching 



This work was supported by Leading Initiative for Excellent Young Researcher (LEADER) of MEXT-Japan (16809746), Grants-in-Aid for Scientific Research of JSPS (17 K14694), Research Fund of State Key Laboratory of Marine Geology at Tongji University (MGK1608),, Research Fund of The Telecommunications Advancement Foundation, Open Collaborative Research Program at National Institute of Informatics Japan (NII), Japan-China Scientific Cooperation Program (6171101454), and International Exchange Program of National Institute of Information and Communications (NICT), and Fundamental Research Developing Association for Shipbuilding and Offshore.


  1. 1.
    Firmino M, Angelo G, Morais H, Dantas M, Valentim R (2016) Computer-aided detection (CADe) and diagnosis (CADx) system for lung cancer with likelihood of malignancy. Biomed Eng Online 15(2):1–17Google Scholar
  2. 2.
    Chen M, Li W, Hao Y, Qian Y, Humar I (2018) Edge cognitive computing based smart healthcare system. Futur Gener Comput Syst 86:403–411CrossRefGoogle Scholar
  3. 3.
    Chen M, Yang J, Zhou J, Hao Y, Zhang J, Youn C (2018) 5G-smart diabetes: toward personalized diabetes diagnosis with healthcare big data clouds. IEEE Commun Mag 56(4):16–23CrossRefGoogle Scholar
  4. 4.
    Chen M, Zhang Y, Qiu M, Guizani N, Hao Y (2018) SPHA: smart personal health advisor based on deep analytics. IEEE Commun Mag 56(3):164–169CrossRefGoogle Scholar
  5. 5.
    Chen M, Herrera F, Hwang K (2018) Cognitive computing: architecture, technologies and intelligent applications. IEEE Access 6:19774–19783CrossRefGoogle Scholar
  6. 6.
    Yoshino Y, Miyajima T, Lu H, Tan J, Kim H, Murakami S, Aoki T, Tachibana R, Hirano Y, Kido S (2017) Automatic classification of lung nodules on MDCT images with the temporal subtraction technique. Int J Comput Assist Radiol Surg 12(10):1789–1798CrossRefGoogle Scholar
  7. 7.
    Kano A, Doi K, MacMahon H, Hassell D, Giger M (1994) Digital image subtraction of temporally sequential chest images for detection of interval change. Med Phys 21(3):453–461CrossRefGoogle Scholar
  8. 8.
    Aoki T, Oda N, Yamashita Y, Yamamoto K, Korogi Y (2012) Usefulness of computerized method for lung nodule detection on digital chest radiographs using similar subtraction images from different patients. Eur J Radiol 81(5):1062–1067CrossRefGoogle Scholar
  9. 9.
    Tokisa T, Maeda S, Kim H, Tan J, Ishikawa S, Murakami S, Aoki T, Hirano Y, Kido S, Tachibana R (2012) A temporal subtraction technique for 3-D non-rigid wrapping method based on free form deformation from thoracic MDCT image. IEICE Technical Report 112(271):11–16Google Scholar
  10. 10.
    Yamada S, Ikeda Y, Maeda S, Kim H, Tan J, Ishikawa S, Murakami S, Aoki T (2014) Three-dimensional non-rigid registration of thoracic CT image based on finite element method. In: Proc. of 2014 Joint 7th International Conference on Soft Computing and Intelligent systems(SCIS) and 15th International Symposium on Advanced Intelligent Systems(ISIS), pp.1–6Google Scholar
  11. 11.
    Tokisa T, Miyake N, Maeda S, Kim H, Tan J, Ishikawa S, Murakami S, Aoki T (2012) Detection of lung nodule on temporal subtraction images based on artificial neural network. International Journal of Fuzzy Logic and Intelligent Systems 12(2):137–142CrossRefGoogle Scholar
  12. 12.
    Itai Y, Kim H, Ishikawa S, Katsuragawa S, Doi K (2008) A new registration method with voxel-matching technique for temporal subtraction images. Proc of the SPIE (Medical Imaging) 6915:311–318Google Scholar
  13. 13. Accessed 16 Jan 2017Google Scholar
  14. 14.
    Boykov Y, Kolmogorov V (2004) An experimental comparison of Min-Cut/Max-Flow algorithms for energy minimization in computer vision. IEEE Trans Pattern Anal Mach Intell 26(9):1124–1137CrossRefGoogle Scholar
  15. 15.
    Kobatake H (2006) A convergence index filter for vector fields and its application to medical image processing. Electronics and Communications in Japan 89(6):34–46CrossRefGoogle Scholar
  16. 16.
    Iwao Y (2015) Spatio-temporal analyzing system based on multimodal integration of chest CT and MR image. National Yokohama University Thesis, pp. 1–113Google Scholar
  17. 17.
    Davatzikos C (1997) Spatial transformation and registration of brain images using elastically deformable models. Comput Vis Image Underst 66(2):207–222CrossRefGoogle Scholar
  18. 18.
    Christensen G, Rabbitt R, Miller M (1996) Deformable templates using large deformation kinematics. IEEE Trans Image Process 5(10):1435–1447CrossRefGoogle Scholar
  19. 19.
    Murakami S, Hodu Y, Kim H, Tan J, Ishikawa S (2014) Segmentation of phalange regions and image registration method for detection of temporal changes in CR image. Biomedical Fuzzy Systems 16(2):11–17Google Scholar
  20. 20.
    Sato R, Shimizu A, Kobatake H, Oriuchi N, Endo K (2006) Improvement of computer-aided detection system using a pair of whole body FDG-PET and CT images. IEICE Technical Report 105(579):5–8Google Scholar
  21. 21.
    Uhlenbrock R, Kim K, Hoffmann H, Dolne J (2017) Rapid 3D registration using local subtree caching in iterative closest point (ICP) algorithm. Proc of SPIE 10410:1–10Google Scholar
  22. 22.
    Kido S, Shouno H (2007) Temporal subtracted images of thoracic CT by use of displacements of ribs and elastic object model. Medical Imaging and Information Sciences 24(4):126–130Google Scholar
  23. 23.
    Fukui M, Kitasaka T, Mori K, Suenaga Y, Mekada Y, Mori M, Takabatake H, Natori H (2006) A study on a method for finding corresponding pairs of lung nodules from follow-up chest CT scans based on non-rigid image registration. IEICE Technical Report 105(580):125–128Google Scholar
  24. 24.
    Itai Y, Kim H, Ishikawa S, Katsuragawa S, Doi K (2008) A method for reducing of subtraction artifacts in temporal subtraction image based on voxel matching method. IEICE Technical Report 107(461):281–284Google Scholar
  25. 25.
    Nagao M, Miyake N, Yoshino Y, Lu H, Tan J, Kim H, Murakami S, Aoki T, Hirano Y, Kido S (2017) Detection of abnormal candidate regions on temporal subtraction images based on DCNN. In: Proc. of 17th International Conference on Control, Automation and Systems, pp. 1444–1448Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Huimin Lu
    • 1
    Email author
  • Masashi Kondo
    • 1
  • Yujie Li
    • 2
  • JooKooi Tan
    • 1
  • Hyoungseop Kim
    • 1
  • Seiichi Murakami
    • 3
  • Takotoshi Aoki
    • 3
  • Shoji Kido
    • 4
  1. 1.Kyushu Institute of TechnologyKitakyushuJapan
  2. 2.Fukuoka UniversityFukuokaJapan
  3. 3.University of Occupational and Environmental Health JapanFukuokaJapan
  4. 4. Yamaguchi UniversityYamaguchiJapan

Personalised recommendations