Open Access
Subscription Access
Region Growing for MRI Brain Tumor Volume Analysis
The tumor volume is a significant prognostic factor in the treatment of malignant tumors. Manual segmentation of brain tumors from MR images is a challenging and time consuming task. A semi-automated region growing segmentation method is proposed to segment brain tumor from MR images. The proposed method can successfully segment a tumor provided that the parameters are set properly. This method is applied to 8-tumor contained MRI slices from 2 brain tumor patients' and satisfactory segmentation results are achieved.
Keywords
Brain Tumor, MRI, Imaging, Segmentation
User
Information
- Rafael C, Gonzalez and Richard Woods E (2003) Digital image processing. 2nd edition.
- Sonka M, Hlavac V and Boyle R (2003) Image processing, analysis and machine vision. 3rd edition.
- Edman M (2007) Segmentation using a region growing algorithm. Rensselaer Polytech. Instt.
- Haney SM, Thompson PM, Cloughesy TF, Alger JR and Toga AW (2001) Tracking tumor growth rates in patients with malignant gliomas: a test of two algorithms. AJNR Am. J. Neuroradiol. 22, 73-82.
- Mehnert and Jackway P (1997) An improved seeded region growing algorithm. Pattern Recog/ Letters. 18, 1065-1071.
- Basu S (1987) Image segmentation by semantic method. Pattern Recog. 20 (5) 497-511.
- Beaulieu JM and Goldberg M (1989) Hierarchy in picture segmentation: a stepwise optimisation approach. IEEE Trans. Pattern Analysis & Machine Intellig. 11 (2) 150-163.
- Gambotto JP (1993) A new approach to combining region growing and edge detection. Pattern Recog. Letters. 14, 869-875.
- Hojjatoleslami SA and Kittler J (2002) Region growing: a new approach. Dept. Electric. Electronics Engg., Univ. Surrey, Guildford, UK, GU25XH.
- Moonis et al. (2002) Estimation of tumor volume with fuzzy connectedness segmentation of MR images. ATRN Am. J. Neuroradiol. 23, 356-363.
- Liu J, Udupa JK, Odhner D, Hackney D and Moonis G (2005) A system for brain tumor volume estimation via MR imaging and fuzzy connectedness. Compu. Med. Imaging & Graphics. 29, 21-34.
- Lu Y, Jiang T and Zang Y (2003) Region growing method for the analysis of functional MRI data. NeuroImage. 20, 455-465.
- Salman YL, Assal MA, Badawi AM, Alian SM and MEI-EI Bayome (2005) Validation techniques for quantitative brain tumors measurements. IEEE Proc. Engg. Med. Biol. 7048-7051.
- Yang Y, Yan X, Zheng C and Lin P (2004) A novel statistical method for segmentation of brain MRI. IEEE, 946-949.
- Hwang J, Han Y and Park HW (2007) Segmentation of brain parenchyma using bilateral filtering and region growing. Intl. Conf. IEEE EMBS. 6263-6266.
- Vaidyanathan M, Clarke LP, Velthuizen RP, Phulphanich S, Bensaid AM, Hall LO, Bezdek JC, Greenberg H, Trotti A and Sibiger M (1995) Comparison of supervised MRI segmentation methods for volume determination during therapy. Magnetic Resonance Imaging. 13 (5), 719-728.
- Ma KL, Cohen MF and Painter JS (1991) Volume Seeds: A Volume exploration technique. J. Visual. Compu. Animation. 2, 135-140.
- Heath LM, Hall LO, Goldgof DB and Murtagh FR (2001) Automatic segmentation of non-enhancing brain tumors in magnetic resonace images. Artificial Intelligence in Med. 21, 43-63.
- Xie K, Yang J, Zau ZG and Zhu YM (2005) Semiautomatic brain tumor an edema segmentation using MRI. Eur. J. Radiol. 56 (1), 12-19.
- Khanpur RS (1999) Handbook of biomedical instrumentation. 2nd edition.
- Bu Lee, Soo-Min Song, Jae-Sung Lee and Myoung-Hee Kim (2005) Tumor segmentation from small animal PET using region growing based on gradient magnitude. Dept. of Computer Sci. Engg., Ewha Woman’s Univ.
Abstract Views: 460
PDF Views: 125