Segmentation of osteosarcoma tumor using diffusion weighted MRI: a comparative study using nine segmentation algorithms
- 18 Downloads
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.
KeywordsMedical image segmentation Diffusion weight imaging Osteosarcoma Bone tumor segmentation Machine learning
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.
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 was obtained from all individual participants included in the study.
- 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
- 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.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.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
- 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.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
- 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
- 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
- 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
- 24.Sredhar, K., Panlal, B.: Enhancement of images using morphological transformations. Int. J. Comput. Sci. Inf. Technol. 4, 33–50 (2012)Google Scholar
- 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
- 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.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