Advertisement

Unifying the seeds auto-generation (SAGE) with knee cartilage segmentation framework: data from the osteoarthritis initiative

  • Hong-Seng GanEmail author
  • Khairil Amir Sayuti
  • Muhammad Hanif Ramlee
  • Yeng-Seng Lee
  • Wan Mahani Hafizah Wan Mahmud
  • Ahmad Helmy Abdul Karim
Original Article
  • 34 Downloads

Abstract

Purpose

Manual segmentation is sensitive to operator bias, while semiautomatic random walks segmentation offers an intuitive approach to understand the user knowledge at the expense of large amount of user input. In this paper, we propose a novel random walks seed auto-generation (SAGE) hybrid model that is robust to interobserver error and intensive user intervention.

Methods

Knee image is first oversegmented to produce homogeneous superpixels. Then, a ranking model is developed to rank the superpixels according to their affinities to standard priors, wherein background superpixels would have lower ranking values. Finally, seed labels are generated on the background superpixel using Fuzzy C-Means method.

Results

SAGE has achieved better interobserver DSCs of 0.94 ± 0.029 and 0.93 ± 0.035 in healthy and OA knee segmentation, respectively. Good segmentation performance has been reported in femoral (Healthy: 0.94 ± 0.036 and OA: 0.93 ± 0.034), tibial (Healthy: 0.91 ± 0.079 and OA: 0.88 ± 0.095) and patellar (Healthy: 0.88 ± 0.10 and OA: 0.84 ± 0.094) cartilage segmentation. Besides, SAGE has demonstrated greater mean readers’ time of 80 ± 19 s and 80 ± 27 s in healthy and OA knee segmentation, respectively.

Conclusions

SAGE enhances the efficiency of segmentation process and attains satisfactory segmentation performance compared to manual and random walks segmentation. Future works should validate SAGE on progressive image data cohort using OA biomarkers.

Keywords

Seeds Automatic Random walks Knee cartilage segmentation 

Notes

Funding

The study is partially supported by the Fundamental Research Grant Scheme (FRGS) Grant No. FRGS/1/2018/ICT02/UNIKL/02/4 (Project title: Graph Transformed Deep ‘Interactive' Learning Framework in Medical Image Segmentation provided by the Malaysian Ministry of Education (MoE), Dana Penyelidikan Inovasi MARA (DPIM) Grant No. MARA/UNI/1/33/18/18(1) provided by Unit Penyelidikan & Inovasi MARA and Short Term Research Grant (STRG) Grant No. str17015 provided by Universiti Kuala Lumpur-British Malaysian Institute (UniKL-BMI).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

References

  1. 1.
    Schaefer LF, Sury M, Yin M, Jamieson S, Donnell I, Smith SE, Lynch JA, Nevitt MC, Duryea J (2017) Quantitative measurement of medial femoral knee cartilage volume: analysis of the OA Biomarkers Consortium FNIH Study cohort. Osteoarthr Cartil 25(7):1107–1113.  https://doi.org/10.1016/j.joca.2017.01.010 CrossRefGoogle Scholar
  2. 2.
    Hafezi-Nejad N, Guermazi A, Roemer FW, Hunter DJ, Dam EB, Zikria B, Kwoh CK, Demehri S (2017) Prediction of medial tibiofemoral compartment joint space loss progression using volumetric cartilage measurements: data from the FNIH OA biomarkers consortium. Eur Radiol 27(2):464–473.  https://doi.org/10.1007/s00330-016-4393-4 CrossRefGoogle Scholar
  3. 3.
    Liukkonen MK, Mononen ME, Tanska P, Saarakkala S, Nieminen MT, Korhonen RK (2017) Application of a semi-automatic cartilage segmentation method for biomechanical modeling of the knee joint. Comput Methods Biomech Biomed Eng 20(13):1453–1463.  https://doi.org/10.1080/10255842.2017.1375477 Google Scholar
  4. 4.
    Grady L (2006) Random walks for image segmentation. IEEE Trans Pattern Anal Mach Intell 28(11):1768–1783.  https://doi.org/10.1109/tpami.2006.233 CrossRefGoogle Scholar
  5. 5.
    Boykov YY, Jolly MP (2001) Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: IEEE international conference on computer vision, Vancouver, Canada, pp 105–112.  https://doi.org/10.1109/iccv.2001.937505
  6. 6.
    Mortensen EN, Barrett WA (1998) Interactive segmentation with intelligent scissors. Graph Models Image Process 60(5):349–384.  https://doi.org/10.1006/gmip.1998.0480 CrossRefGoogle Scholar
  7. 7.
    González G, Escalante-Ramírez B (2014) Knee cartilage segmentation using active shape models and local binary patterns. In: SPIE photonics Europe, SPIE, p 11Google Scholar
  8. 8.
    Folkesson J, Dam EB, Olsen OF, Pettersen PC, Christiansen C (2007) Segmenting articular cartilage automatically using a voxel classification approach. IEEE Trans Med Imaging 26(1):106–115.  https://doi.org/10.1109/tmi.2006.886808 CrossRefGoogle Scholar
  9. 9.
    Öztürk CN, Albayrak S (2016) Automatic segmentation of cartilage in high-field magnetic resonance images of the knee joint with an improved voxel-classification-driven region-growing algorithm using vicinity-correlated subsampling. Comput Biol Med 72:90–107.  https://doi.org/10.1016/j.compbiomed.2016.03.011 CrossRefGoogle Scholar
  10. 10.
    Lee HS, Kim HA, Kim H, Hong H, Young CY, Kim J (2016) Multi-atlas segmentation of the cartilage in knee MR images with sequential volume- and bone-mask-based registrations. In: SPIE medical imaging, San Diego, California, US, SPIE, pp 1–6Google Scholar
  11. 11.
    Cootes TF, Taylor CJ, Cooper DH, Graham J (1995) Active shape models-Their training and application. Comput Vis Image Underst 61(1):38–59.  https://doi.org/10.1006/cviu.1995.1004 CrossRefGoogle Scholar
  12. 12.
    Fripp J, Crozier S, Warfield SK, Ourselin S (2010) Automatic segmentation and quantitative analysis of the articular cartilages from magnetic resonance images of the knee. IEEE Trans Med Imaging 29(1):55–64.  https://doi.org/10.1109/tmi.2009.2024743 CrossRefGoogle Scholar
  13. 13.
    Hong Seng G, Khairil Amir S, Ahmad Helmy AK, Rasyiqah Annani MR, Aida Syafiqah AK (2017) Analysis on semi-automated knee cartilage segmentation model using inter-observer reproducibility: data from the osteoarthritis initiative. Paper presented at the proceedings of the 7th international conference on bioscience, biochemistry and bioinformatics, Bangkok, ThailandGoogle Scholar
  14. 14.
    Dam EB, Lillholm M, Marques J, Nielsen M (2015) Automatic segmentation of high- and low-field knee MRIs using knee image quantification with data from the osteoarthritis initiative. J Med Imaging 2(2):024001.  https://doi.org/10.1117/1.jmi.2.2.024001 CrossRefGoogle Scholar
  15. 15.
    Wang P, He X, Li Y, Zhu X, Chen W, Qiu M (2016) Automatic knee cartilage segmentation using multi-feature support vector machine and elastic region growing for magnetic resonance images. J Med Imaging Health Inform 6(4):948–956.  https://doi.org/10.1166/jmihi.2016.1748 CrossRefGoogle Scholar
  16. 16.
    Sinop AK, Grady L (2007) A seeded image segmentation framework unifying graph cuts and random walker which yields a new algorithm. In: IEEE 11th international conference on computer vision, Rio de Janeiro, Brazil, pp 1–8.  https://doi.org/10.1109/iccv.2007.4408927
  17. 17.
    Hong-Seng G, Tian-Swee T, Liang-Xuan W, Weng-Kit T, Sayuti KA, Karim AHA, Kadir MRBA (2014) Interactive knee cartilage extraction using efficient segmentation software: data from the osteoarthritis initiative. Bio-Med Mater Eng 24(6):3145–3157.  https://doi.org/10.3233/BME-141137 Google Scholar
  18. 18.
    Hong Seng G, Khairil Amir S, Ahmad Helmy AK (2017) Investigation of random walks knee cartilage segmentation model using inter-observer reproducibility: data from the osteoarthritis initiative. Bio-Med Mater Eng 28(2):75–85CrossRefGoogle Scholar
  19. 19.
    Achanta R (2012) SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282CrossRefGoogle Scholar
  20. 20.
    MacQueen J (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, vol 1: statistics. University of California Press, Berkeley, pp 281–297Google Scholar
  21. 21.
    Dengyong Z, Jason W, Arthur G, Olivier B, Bernhard S (2004) Ranking on data manifolds. In: Neural information processing systems. MIT Press, Cambridge, pp 169–176 Google Scholar
  22. 22.
    Bezdek J, Ehrlich R, Full W (1984) FCM: the fuzzy c-means clustering algorithm. Comput Geosci 10(2–3):191–203.  https://doi.org/10.1016/0098-3004(84)90020-7 CrossRefGoogle Scholar
  23. 23.
    Gan HS, Tan TS, Karim AHA, Sayuti KA, Kadir MRA (2014) Interactive medical image segmentation with seed precomputation system: data from the osteoarthritis initiative. In: 2014 IEEE conference on biomedical engineering and sciences (IECBES), pp 315–318.  https://doi.org/10.1109/iecbes.2014.7047510
  24. 24.
    Hong S, Sayuti KA, Harun NH, Karim AHA (2016) Flexible non cartilage seeds for osteoarthritic magnetic resonance image of knee: data from the osteoarthritis initiative. In: 2016 IEEE EMBS conference on biomedical engineering and sciences (IECBES), pp 748–751.  https://doi.org/10.1109/iecbes.2016.7843550
  25. 25.
    Shim H, Kwoh CK, Yun ID, Lee SU, Bae K (2009) Simultaneous 3D segmentation of three bone compartments on high resolution knee MR images from osteoarthritis initiative (OAI) using graph cuts. In: Proceedings of SPIE 7259, medical imaging 2009: image processing, vol 7259, pp 72593P–72593P.  https://doi.org/10.1117/12.812487
  26. 26.
    Chen H, Zhen X, Gu X, Yan H, Cervino L, Xiao Y, Zhou L (2015) SPARSE: seed point auto-generation for random walks segmentation enhancement in medical inhomogeneous targets delineation of morphological MR and CT images. J Appl Clin Med Phys 16(2):387–402CrossRefGoogle Scholar
  27. 27.
    Wang P, He Z (2017) Huang S An improved random walk algorithm for interactive image segmentation. In: ICONIP 2017: neural information processing Guangzhou, China, Springer, Cham, pp 151–159Google Scholar
  28. 28.
    Xie X, Yu ZL, Gu Z, Li Y (2018) An iterative boundary random walks algorithm for interactive image segmentation. In: Computer vision and pattern recognition, Salt Lake City, USA, IEEE, pp 1–9Google Scholar
  29. 29.
    Dong C, Chen Y-W, Lin L, Hu H, Jin C, Yu H, Han X-H, Tateyama T (2016) Simultaneous segmentation of multiple organs using random walks. J Inform Process 24(2):320–329.  https://doi.org/10.2197/ipsjjip.24.320 CrossRefGoogle Scholar

Copyright information

© CARS 2019

Authors and Affiliations

  1. 1.Medical Engineering Technology SectionUniversiti Kuala Lumpur, British Malaysian InstituteGombakMalaysia
  2. 2.Department of RadiologySchool of Medical Science, Universiti Sains MalaysiaKubang KerianMalaysia
  3. 3.Medical Devices and Technology Group (MEDITEG)Universiti Teknologi MalaysiaJohor BahruMalaysia
  4. 4.Department of Electronic Engineering Technology, Faculty of Engineering TechnologyUniversiti Malaysia PerlisArauMalaysia
  5. 5.Department of Electronic Engineering, Faculty of Electrical and Electronic EngineeringUniversiti Tun Hussein Onn MalaysiaBatu PahatMalaysia
  6. 6.Diagnostic Imaging ServicesKPJ Ipoh Specialist HospitalIpohMalaysia

Personalised recommendations