Brain Tumor Segmentation with Skull Stripping and Modified Fuzzy C-Means
For medical image processing, brain tumor segmentation is one of the most researched topics. Diagnosis at an early stage plays a vital role in saving a patient’s life. It is troublesome to segment the tumor region from an MRI due to unavailability of a sharper edge and properly visible boundaries. In this paper, a combination of skull stripping methods and modified fuzzy c-means is presented to segment out the tumor region. After the acquired image is denoised, it is stripped of irrelevant tissues on the outer boundaries. It is further processed through the fuzzy c-means algorithm. The obtained results were proven to be better compared to the standard fuzzy c-means when applied on a sample of 100 MRIs.
KeywordsMRI Fuzzy c-means Skull stripping Image denoising
This research was supported by ABV-Indian Institute of Information Technology and Management. The dataset for testing our implementations was acquired from BRATS 2015, from which 100 MRI files (.mat format in T1 modality) were sampled out of 700 images.
- 2.Karnan, M., Logheshwari, T.: Improved implementation of brain MRI image segmentation using ant colony system. In: 2010 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), pp. 1–4. IEEE (2010)Google Scholar
- 3.A. Srivastava, A. Asati, and M. Bhattacharya, “A fast and noise-adaptive rough-fuzzy hybrid algorithm for medical image segmentation. In: 2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 416–421. IEEE (2010)Google Scholar
- 4.Ayoobkhan, M.U.A., Chikkannan, E., Ramakrishnan, K.: Feed-forward neural network-based predictive image coding for medical image compression. Arab. J. Sci. Eng. 1–9 (2017)Google Scholar
- 8.Bradley, P., Bennett, K., Demiriz, A.: Constrained k-means clustering. Microsoft Res. 1–8 (2000)Google Scholar
- 10.Pohle, R., Toennies, K.D.: Segmentation of medical images using adaptive region growing. In: Proceedings of SPIE Medical Imaging, vol. 4322, pp. 1337–1346 (2001)Google Scholar