Convolutional Neural Network and Adaptive Dictionary Learning for Brain Tumour Cell Detection
N. Poonguzhali1, B. Punitha2, J.Ashwini Mega3, G. Thamizamudhu4
1Dr. N. Poonguzhali, Assistant Professor, Department of Computer Science and Engineering, Manakula Vinayagar Institute of Technology, Puducherry (Tamil Nadu). India.
2B. Punitha, UG student, Department of Computer Science and Engineering, Manakula Vinayagar Institute of Technology, Puducherry (Tamil Nadu). India.
3J. Ashwini Mega, UG student, Department of Computer Science and Engineering, Manakula Vinayagar Institute of Technology, Puducherry (Tamil Nadu). India.
4G. Thamizamudhu, UG student, Department of Computer Science and Engineering, Manakula Vinayagar Institute of Technology, Puducherry (Tamil Nadu). India.
Manuscript received on April 10, 2017. | Revised Manuscript received on April 12, 2017. | Manuscript published on April 25, 2017. | PP: 13-18 | Volume-4 Issue-9, April 2017. | Retrieval Number: I1166044917
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper, we propose an efficient brain tumor detection method and an automatic segmentation method, which can detect tumor and locate it in the brain MRI images. Automatic and reliable segmentation methods are used in order to manage large spatial and structural variability among brain tumors. Also, some pre-processing steps are used for tumor detection purpose. The automatic segmentation method is based on convolution neural networks. We present an automatic cell detection framework using sparse reconstruction and adaptive dictionary learning. The automatic cell detection results are compared with manually annotated ground truth and other stateof-the-art cell detection algorithms.
Keywords: Cell detection, MRI images