Advertisement

An enhanced random walk algorithm for delineation of head and neck cancers in PET studies

  • Alessandro Stefano
  • Salvatore Vitabile
  • Giorgio Russo
  • Massimo Ippolito
  • Maria Gabriella Sabini
  • Daniele Sardina
  • Orazio Gambino
  • Roberto Pirrone
  • Edoardo Ardizzone
  • Maria Carla Gilardi
Original Article

Abstract

An algorithm for delineating complex head and neck cancers in positron emission tomography (PET) images is presented in this article. An enhanced random walk (RW) algorithm with automatic seed detection is proposed and used to make the segmentation process feasible in the event of inhomogeneous lesions with bifurcations. In addition, an adaptive probability threshold and a k-means based clustering technique have been integrated in the proposed enhanced RW algorithm. The new threshold is capable of following the intensity changes between adjacent slices along the whole cancer volume, leading to an operator-independent algorithm. Validation experiments were first conducted on phantom studies: High Dice similarity coefficients, high true positive volume fractions, and low Hausdorff distance confirm the accuracy of the proposed method. Subsequently, forty head and neck lesions were segmented in order to evaluate the clinical feasibility of the proposed approach against the most common segmentation algorithms. Experimental results show that the proposed algorithm is more accurate and robust than the most common algorithms in the literature. Finally, the proposed method also shows real-time performance, addressing the physician’s requirements in a radiotherapy environment.

Keywords

Head and neck cancer segmentation Random walks PET imaging Biological target volume 

Notes

Acknowledgments

This work was partially supported by CIPE1 (n. DM45602).

References

  1. 1.
    Lauve A, Morris M, Schmidt-Ullrich R et al (2004) Simultaneous integrated boost intensity-modulated radiotherapy for locally advanced head-and-neck squamous cell carcinomas: II–clinical results. Int J Radiat Oncol Biol Phys. doi: 10.1016/j.ijrobp.2004.03.010 PubMedGoogle Scholar
  2. 2.
    Kim Y, Tomé WA (2007) On the radiobiological impact of metal artifacts in head-and-neck IMRT in terms of tumor control probability (TCP) and normal tissue complication probability (NTCP). Med Biol Eng Comput 45:1045–1051. doi: 10.1007/s11517-007-0196-8 CrossRefPubMedGoogle Scholar
  3. 3.
    Wahl RL, Jacene H, Kasamon Y, Lodge MA (2009) From RECIST to PERCIST: evolving Considerations for PET response criteria in solid tumors. J Nucl Med 50(Suppl 1):122S–150S. doi: 10.2967/jnumed.108.057307 CrossRefPubMedPubMedCentralGoogle Scholar
  4. 4.
    Stefano A, Russo G, Ippolito M et al (2016) Evaluation of erlotinib treatment response in non-small cell lung cancer using metabolic and anatomic criteria. Q J Nucl Med Mol Imaging 60(3):264–273PubMedGoogle Scholar
  5. 5.
    Newbold KL, Partridge M, Cook G et al (2008) Evaluation of the role of 18FDG-PET/CT in radiotherapy target definition in patients with head and neck cancer. Acta Oncol (Madr) 47:1229–1236CrossRefGoogle Scholar
  6. 6.
    Ciernik IF, Dizendorf E, Baumert BG et al (2003) Radiation treatment planning with an integrated positron emission and computer tomography (PET/CT): a feasibility study. Int J Radiat Oncol 57:853–863. doi: 10.1016/S0360-3016(03)00346-8 CrossRefGoogle Scholar
  7. 7.
    Belhassen S, Zaidi H (2010) A novel fuzzy C-means algorithm for unsupervised heterogeneous tumor quantification in PET. Med Phys 37:1309–1324. doi: 10.1118/1.3301610 CrossRefPubMedGoogle Scholar
  8. 8.
    Li H, Thorstad WL, Biehl KJ et al (2008) A novel PET tumor delineation method based on adaptive region-growing and dual-front active contours. Med Phys 35:3711–3721. doi: 10.1118/1.2956713 CrossRefPubMedPubMedCentralGoogle Scholar
  9. 9.
    Geets X, Lee JA, Bol A et al (2007) A gradient-based method for segmenting FDG-PET images: methodology and validation. Eur J Nucl Med Mol Imaging 34:1427–1438. doi: 10.1007/s00259-006-0363-4 CrossRefPubMedGoogle Scholar
  10. 10.
    Wanet M, Lee JA, Weynand B et al (2011) Gradient-based delineation of the primary GTV on FDG-PET in non-small cell lung cancer: a comparison with threshold-based approaches, CT and surgical specimens. Radiother Oncol 98:117–125. doi: 10.1016/j.radonc.2010.10.006 CrossRefPubMedGoogle Scholar
  11. 11.
    Namías R, D’Amato JP, Del Fresno M et al (2016) Multi-object segmentation framework using deformable models for medical imaging analysis. Med Biol Eng Comput. 54(8):1181–1192. doi: 10.1007/s11517-015-1387-3 CrossRefPubMedGoogle Scholar
  12. 12.
    Hatt M, Cheze Le Rest C, Albarghach N et al (2011) PET functional volume delineation: a robustness and repeatability study. Eur J Nucl Med Mol Imaging 38:663–672. doi: 10.1007/s00259-010-1688-6 CrossRefPubMedGoogle Scholar
  13. 13.
    Schinagl DAX, Vogel WV, Hoffmann AL et al (2007) Comparison of five segmentation tools for 18 F-FLUORO-DEOXYGLUCOSE-POSITRON emission tomography-based target volume definition in head and neck cancer. Int J Radiat Oncol Biol Phys 69:1282–1289. doi: 10.1016/j.ijrobp.2007.07.2333 CrossRefPubMedGoogle Scholar
  14. 14.
    Zaidi H, El Naqa I (2010) PET-guided delineation of radiation therapy treatment volumes: a survey of image segmentation techniques. Eur J Nucl Med Mol Imaging 37:2165–2187. doi: 10.1007/s00259-010-1423-3 CrossRefPubMedGoogle Scholar
  15. 15.
    Stefano A, Vitabile S, Russo G et al (2013) A Graph-Based Method for PET Image Segmentation in Radiotherapy Planning: a Pilot Study. Lect Notes Comput Sci 8157:711–720. doi: 10.1007/978-3-642-41184-7_72 CrossRefGoogle Scholar
  16. 16.
    Larson SM, Erdi Y, Akhurst T et al (1999) Tumor treatment response based on visual and quantitative changes in global tumor glycolysis using PET-FDG imaging. The visual response score and the change in total lesion glycolysis. Clin Positron Imaging 2:159–171. doi: 10.1016/S1095-0397(99)00016-3 CrossRefPubMedGoogle Scholar
  17. 17.
    Boykov Y, Veksler O, Zabih R (2001) Fast approximate energy minimization via graph cuts. Pattern Anal Mach Intell IEEE Trans 23:1222–1239. doi: 10.1109/34.969114 CrossRefGoogle Scholar
  18. 18.
    Grady L (2006) Random Walks for Image Segmentation. IEEE Trans Pattern Anal Mach Intell 28:1768–1783CrossRefPubMedGoogle Scholar
  19. 19.
    Bagci U, Yao J, Caban J et al (2011) A Graph-Theoretic Approach for Segmentation of PET Images. Conf Proc IEEE Eng Med Biol Soc 2011:8479–8482. doi: 10.1109/IEMBS.2011.6092092 PubMedPubMedCentralGoogle Scholar
  20. 20.
    Onoma DP, Ruan S, Thureau S et al (2014) Segmentation of heterogeneous or small FDG PET positive tissue based on a 3D-locally adaptive random walk algorithm. Comput Med Imaging Graph 38:753–763. doi: 10.1016/j.compmedimag.2014.09.007 CrossRefPubMedGoogle Scholar
  21. 21.
    Bagci U, Udupa JK, Mendhiratta N et al (2013) Joint segmentation of anatomical and functional images: applications in quantification of lesions from PET, PET-CT, MRI-PET, and MRI-PET-CT images. Med Image Anal 17:929–945. doi: 10.1016/j.media.2013.05.004 CrossRefPubMedPubMedCentralGoogle Scholar
  22. 22.
    Udupa JK, Leblanc VR, Zhuge Y et al (2006) A framework for evaluating image segmentation algorithms. Comput Med Imaging Graph 30:75–87. doi: 10.1016/j.compmedimag.2005.12.001 CrossRefPubMedGoogle Scholar
  23. 23.
    Day E, Betler J, Parda D et al (2009) A region growing method for tumor volume segmentation on PET images for rectal and anal cancer patients. Med Phys 36:4349–4358. doi: 10.1118/1.3213099 CrossRefPubMedGoogle Scholar
  24. 24.
    Rundo L, Militello C, Vitabile S, Casarino C, Russo G, Midiri M, Gilardi MC (2016) Combining Split-and-Merge and Multi-Seed Region Growing Algorithms for Uterine Fibroid Segmentation in MRgFUS Treatments. Med Biol Eng Comput 54(7):1071–1084. doi: 10.1007/s11517-015-1404-6 CrossRefPubMedGoogle Scholar
  25. 25.
    Troost EGC, Schinagl DAX, Bussink J et al (2010) Clinical evidence on PET–CT for radiation therapy planning in head and neck tumours. Radiother Oncol 96:328–334. doi: 10.1016/j.radonc.2010.07.017 CrossRefPubMedGoogle Scholar
  26. 26.
    Paulino AC, Koshy M, Howell R et al (2005) Comparison of CT- and FDG-PET-defined gross tumor volume in intensity-modulated radiotherapy for head-and-neck cancer. Int J Radiat Oncol Biol Phys 61:1385–1392. doi: 10.1016/j.ijrobp.2004.08.037 CrossRefPubMedGoogle Scholar
  27. 27.
    Wang J, del Valle M, Goryawala M et al (2010) Computer-assisted quantification of lung tumors in respiratory gated PET/CT images: phantom study. Med Biol Eng Comput 48:49–58. doi: 10.1007/s11517-009-0549-6 CrossRefPubMedGoogle Scholar
  28. 28.
    Han D, Bayouth J, Song Q et al (2011) Globally optimal tumor segmentation in PET-CT images: a graph-based co-segmentation method. Inf Process Med Imaging. 22:245–256CrossRefPubMedPubMedCentralGoogle Scholar
  29. 29.
    Song Q, Bai J, Han D et al (2013) Optimal Co-segmentation of tumor in PET-CT images with context information. IEEE Trans Med Imaging 32:1685–1697. doi: 10.1109/TMI.2013.2263388 CrossRefPubMedPubMedCentralGoogle Scholar
  30. 30.
    Stefano A, Gallivanone F, Messa C et al (2014) Metabolic impact of partial volume correction of [18F]FDG PET-CT oncological studies on the assessment of tumor response to treatment. Q. J. Nucl. Med. Mol. Imaging 58(4):413–423PubMedGoogle Scholar
  31. 31.
    Soret M, Bacharach SL, Buvat II (2007) Partial-volume effect in PET tumor imaging. J Nucl Med 48:932–945. doi: 10.2967/jnumed.106.035774 CrossRefPubMedGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2016

Authors and Affiliations

  • Alessandro Stefano
    • 1
    • 2
  • Salvatore Vitabile
    • 3
  • Giorgio Russo
    • 1
    • 4
  • Massimo Ippolito
    • 5
  • Maria Gabriella Sabini
    • 4
  • Daniele Sardina
    • 4
  • Orazio Gambino
    • 2
  • Roberto Pirrone
    • 2
  • Edoardo Ardizzone
    • 2
  • Maria Carla Gilardi
    • 1
  1. 1.Institute of Molecular Bioimaging and PhysiologyNational Research Council (IBFM-CNR)CefalùItaly
  2. 2.Department of Chemical, Management, Information Technology and Mechanical EngineeringUniversity of PalermoPalermoItaly
  3. 3.Department of Biopathology and Medical Biotechnologies (DIBiMED)University of PalermoPalermoItaly
  4. 4.Medical Physics UnitCannizzaro HospitalCataniaItaly
  5. 5.Nuclear Medicine DepartmentCannizzaro HospitalCataniaItaly

Personalised recommendations