Advertisement

Segmentation of osteosarcoma tumor using diffusion weighted MRI: a comparative study using nine segmentation algorithms

  • Esha Baidya Kayal
  • Devasenathipathy Kandasamy
  • Raju Sharma
  • Sameer Bakhshi
  • Amit MehndirattaEmail author
Original Paper
  • 18 Downloads

Abstract

Osteosarcoma is a primary malignant bone tumor in children and adolescents with significant morbidity and poor prognosis. Diffusion weighted imaging (DWI) plays a crucial role in diagnosis and prognosis of this malignant disease by capturing cellular changes in tumor tissue early in the course of treatment without any contrast injection. Segmentation of tumor in DWI is challenging due to low signal-to-noise ratio, partial-volume effects, intensity inhomogeneities and irregular shape of osteosarcoma. The purpose of this study was to segment osteosarcoma solely utilizing DWI and identify effective and robust technique(s) for tumor segmentation. DWI dataset of fifty-five (N = 55; male:female = 41:14; Age = 17.8 ± 7.4 years) patients with osteosarcoma was acquired before treatment. Total nine automated and semi-automated segmentation algorithms based on (1) Otsu thresholding (OT), (2) Otsu threshold-based region growing (OT-RG), (3) Active contour (AC), (4) Simple linear iterative clustering Superpixels (SLIC-S), (5) Fuzzy c-means clustering (FCM), (6) Graph cut (GC), (7) Logistic regression (LR) (8) Linear support vector machines (L-SVM) and (9) Deep feed-forward neural network (DNN) were implemented. Segmentation accuracy was estimated by Dice coefficient (DC), Jaccard Index (JI), precision (P) and recall (R) using manually demarcated ground-truth tumor mask by a radiologist. Evaluated apparent diffusion coefficient (ADC) in segmented tumor mask and ground-truth tumor mask was compared using paired t test for statistical significance (p < 0.05) and Pearson correlation coefficient (PCC). Automated SLIC-S and FCM showed quantitatively and qualitatively superior segmentation with DC: ~ 79–82%; JI: ~ 67–71%; P: ~ 81–83%; R: ~ 80–86% and PCC = 0.89, 0.88 among all methods. Among semi-automated methods, AC was quantitatively more accurate (DC: ~ 77%; JI: ~ 65%; P: ~ 72%; R: ~ 88%; PCC = 0.85) than OT-RG and GC (DC: ~ 74–75%; JI: ~ 60–61%; P: ~ 67–72%; R: ~ 84–89%; PCC = 0.78, 0.73). Among machine learning algorithms, DNN showed the highest accuracy (DC: ~ 73%; JI: ~ 62%; P: ~ 77%; R: ~ 86%; PCC = 0.79) than LR and L-SVM (DC: ~ 70–71%; JI: ~ 58–63%; P: ~ 73%; R: ~ 74–85%; PCC = 0.69, 0.71). Execution times were instantaneous for SLIC-S, FCM and machine learning methods, while OT-RG, AC and GC took comparable ~ 1–6 s/slice image. Automated SLIC-S, FCM and semi-automated AC methods produced promising tumor segmentation results using DWI of the osteosarcoma dataset.

Keywords

Medical image segmentation Diffusion weight imaging Osteosarcoma Bone tumor segmentation Machine learning 

Notes

Acknowledgements

Authors would like to thank the Ministry of Human Resource Development, Government of India for providing the research fellowship funds to E.B.K. required for this study. Authors would also like to thank and acknowledge the valuable input of the intern team, Abhimanyu Sahai, Rishabh Gupta, Akshay Gupta, Kabir Chhbra and Sneha Patil in data processing and various stages of implementation of algorithms.

Compliance with ethical standards

Conflict of interest

The authors have no relevant conflicts of interest to disclose regarding this study.

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 Declaration of Helsinki and its later amendments or comparable ethical standards.

Informed consent

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

Supplementary material

11760_2019_1599_MOESM1_ESM.pdf (95 kb)
Supplementary material 1 (PDF 94 kb)

References

  1. 1.
    Geller, D.S., Gorlick, R.: Osteosarcoma: a review of diagnosis, management, and treatment strategies. Clin. Adv. Hematol. Oncol. 8, 705–718 (2010)Google Scholar
  2. 2.
    Wong, K.-P.: Medical image segmentation: methods and applications in functional imaging. In: Suri, J.S., Wilson, D.L., Laxminarayan, S. (eds.) Handbook of biomedical image analysis: volume II segmentation models part B, pp. 111–182. Springer, Boston (2005)CrossRefGoogle Scholar
  3. 3.
    Norouzi, A., Shafry, M., Rahim, M., et al.: Applications medical image segmentation methods, algorithms, and applications. IETE Tech. Rev. 3, 37–41 (2014).  https://doi.org/10.1080/02564602.2014.906861 CrossRefGoogle Scholar
  4. 4.
    Ashton, E.A., Takahashi, C., Berg, M.J., et al.: Accuracy and reproducibility of manual and semiautomated quantification of MS lesions by MRI. J. Magn. Reson. Imaging 17, 300–308 (2003).  https://doi.org/10.1002/jmri.10258 CrossRefGoogle Scholar
  5. 5.
    Costa, F.M., Ferreira, E.C., Vianna, E.M.: Diffusion-weighted magnetic resonance imaging for the evaluation of musculoskeletal tumors. Magn. Reson. Imaging Clin. NA 19, 159–180 (2011).  https://doi.org/10.1016/j.mric.2010.10.007 CrossRefGoogle Scholar
  6. 6.
    Raghavan, M.: Conventional modalities and novel, emerging imaging techniques for musculoskeletal tumors. Cancer Control 24, 161–171 (2017)CrossRefGoogle Scholar
  7. 7.
    Frangi, A.F., Egmont-petersen, M., Niessen, W.J., et al.: Bone tumor segmentation from MR perfusion images with neural networks using multi-scale pharmacokinetic features. Image Vis. Comput. 19, 679–690 (2001)CrossRefGoogle Scholar
  8. 8.
    Mandava, R., Wei, B.C., Yeow, L.S.: Spatial multiple criteria fuzzy clustering for image segmentation. In: Second International Conference on Computational Intelligence, pp. 305–310 (2010)Google Scholar
  9. 9.
    Mandava, R., Alia, O.M., Wei, B.C., et al.: Osteosarcoma segmentation in MRI using dynamic harmony search based clustering. In: International Conference of Soft Computing and Pattern Recognition, pp. 423–429 (2010)Google Scholar
  10. 10.
    Huang, W., Wen, D., Yan, Y., et al.: Multi-target osteosarcoma MRI recognition with texture context features based on CRF. In: International Joint Conference on Neural Networks (IJCNN), pp. 3978–3983 (2016)Google Scholar
  11. 11.
    Ma, J., Li, M., Zhao, Y.: Segmentation of multimodality osteosarcoma MRI with vectorial fuzzy-connectedness theory. In: International Conference on Fuzzy Systems and Knowledge Discovery, pp. 1027–1030 (2005)CrossRefGoogle Scholar
  12. 12.
    Zhao, Y., Hong, F., Li, M.: Multimodality MRI information fusion for osteosarcoma segmentation. In: IEEE EMBS Asian-Pacific Conference on Biomedical Engineering, pp. 166–167 (2003)Google Scholar
  13. 13.
    Chun-xiao, C., Dan, Z., Ning, L., et al.: Osteosarcoma segmentation in MRI based on zernike moment and SVM. Chinese J. Biomed. Eng. 22, 70–78 (2013)Google Scholar
  14. 14.
    Otsu, N.: A tlreshold selection method from gray-level histograms. IEEE Trans. Syst. MAN Cybern. SMC 9, 62–66 (1979)CrossRefGoogle Scholar
  15. 15.
    Mancas, M., Gosselin, B., Macq, B.: Segmentation using a region growing thresholding. In: Proceedings of SPIE 5672, Image Processing: Algorithms and Systems IV, pp. 388–398 (2006)Google Scholar
  16. 16.
    Chan, T.F., Vese, L.A.: Active Contours Without Edges. IEEE Trans. Image Process. 10, 266–277 (2001)CrossRefGoogle Scholar
  17. 17.
    Achanta, R., Shaji, A., Smith, K., et al.: SLIC Superpixels. IEEE Trans. Pattern Anal. Mach. Intell. 34, 2274–2282 (2012)CrossRefGoogle Scholar
  18. 18.
    Selvathi, D., Arulmurgan, A., Alagappan, S.: MRI image segmentation using unsupervised clustering techniques. In: IEEE Proceedings of the 6th International Conference on Computational Intelligence and Multimedia Applications (ICCIMA’05), pp. 5–10 (2005)Google Scholar
  19. 19.
    Boykov, Y., Funka-lea, G.: Graph cuts and efficient N-D image segmentation. Int. J. Comput. Vis. 70, 109–131 (2006).  https://doi.org/10.1007/s11263-006-7934-5 CrossRefGoogle Scholar
  20. 20.
    Cox, D.R.: The regression analysis of binary sequences. J. R. Stat. Soc. 20, 215–242 (2017)MathSciNetzbMATHGoogle Scholar
  21. 21.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Leaming 20, 273–297 (1995)zbMATHGoogle Scholar
  22. 22.
    Du, X., Li, Y., Yao, D.: A support vector machine based algorithm for magnetic resonance image segmentation. In: 4th International Conference on Natural Computation A, pp. 49–53 (2008)Google Scholar
  23. 23.
    Havaei, M., Davy, A., Warde-farley, D., et al.: Brain tumor segmentation with deep neural networks. Med. Image Anal. 35, 18–31 (2017).  https://doi.org/10.1016/j.media.2016.05.004 CrossRefGoogle Scholar
  24. 24.
    Sredhar, K., Panlal, B.: Enhancement of images using morphological transformations. Int. J. Comput. Sci. Inf. Technol. 4, 33–50 (2012)Google Scholar
  25. 25.
    Haralick, R.M.: Statistical and structural approaches to texture. Proc. IEEE 67, 786–804 (1979)CrossRefGoogle Scholar
  26. 26.
    Galloway, M.M.: Texture analysis using grey-level run lengths. Comput. Graph Image Process 4, 172–179 (1975)CrossRefGoogle Scholar
  27. 27.
    Mucciardi, A.N., Gose, E.E.: Comparison of seven techniques for choosing subsets of pattern recognition properties. IEEE Trans. Comput. C 20, 1023–1031 (1971)CrossRefGoogle Scholar
  28. 28.
    Ferlay, J., Soerjomataram, I., Dikshit, R., et al.: Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012. Int. J. Cancer 386, E359–E386 (2015).  https://doi.org/10.1002/ijc.29210 CrossRefGoogle Scholar
  29. 29.
    Chen, C., Ding, S., Li, N., Wu, S.: Osteosarcoma segmentation in CT images based on hybrid relative fuzzy connectedness. In: 5th International Conference on BioMedical Engineering and Informatics, pp: 324–328. IEEE (2012)Google Scholar
  30. 30.
    Zhang, R., Huang, L., Xia, W., et al.: Computerized medical imaging and graphics multiple supervised residual network for osteosarcoma segmentation in CT images. Comput. Med. Imaging Graph 63, 1–8 (2018).  https://doi.org/10.1016/j.compmedimag.2018.01.006 CrossRefGoogle Scholar
  31. 31.
    Liu, X., Haider, M.A., Yetik, I.S.: Unsupervised 3D prostate segmentation based on diffusion-weighted imaging MRI using active contour models with a shape prior. J. Electr. Comput. Eng. 2011, 1–2 (2011).  https://doi.org/10.1155/2011/410912 MathSciNetCrossRefzbMATHGoogle Scholar
  32. 32.
    Zhang, J., Baig, S., Wong, A., Haider, M.A.: Segmentation of prostate in diffusion MR images via clustering. Image Anal. Recognit. 10317, 471–478 (2017).  https://doi.org/10.1007/978-3-319-59876-5 CrossRefGoogle Scholar
  33. 33.
    Saad, N.M., Muda, S., Mokji, M.: Segmentation of brain lesions in diffusion- weighted MRI using thresholding technique. In: 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), pp. 249–254. IEEE (2011)Google Scholar
  34. 34.
    Schakel, T., Peltenburg, B., Dankbaar, J., et al.: Evaluation of diffusion weighted imaging for tumor delineation in head- and- neck radiotherapy by comparison with automatically segmented 18F- fluorodeoxyglucose positron emission tomography. Phys. Imaging Radiat. Oncol. 5, 13–18 (2018).  https://doi.org/10.1016/j.phro.2017.12.004 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Centre for Biomedical EngineeringIndian Institute of Technology DelhiHauz Khas, New DelhiIndia
  2. 2.Department of RadiologyAll India Institute of Medical SciencesNew DelhiIndia
  3. 3.Department of Medical Oncology, Dr. B. R. Ambedkar Institute-Rotary Cancer Hospital (IRCH)All India Institute of Medical SciencesNew DelhiIndia
  4. 4.Department of Biomedical EngineeringAll India Institute of Medical SciencesNew DelhiIndia

Personalised recommendations