Brain Tumor Segmentation and Classification using Multiple Feature Extraction and Convolutional Neural Networks
Tasmiya Tazeen1, Mrinal Sarvagya2
1Tasmiya Tazeen*, School of Electronics and Communication Engineering, Reva University, Bengaluru-560064, India.
2Mrinal Sarvagya, School of Electronics and Communication Engineering, Reva University, Bengaluru-560064, India.
Manuscript received on July 05, 2021. Revised Manuscript received on July 10, 2021. Manuscript published on August 30, 2021. | PP: 23-27 | Volume-10 Issue-6, August 2021 | Retrieval Number: 100.1/ijeat.F29480810621 | DOI: 10.35940/ijeat.F2948.0810621
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. 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: Intracranial tumors are a type of cancer that grows spontaneously inside the skull. Brain tumor is the cause for one in four deaths. Hence early detection of the tumor is important. For this aim, a variety of segmentation techniques are available. The fundamental disadvantage of present approaches is their low segmentation accuracy. With the help of magnetic resonance imaging (MRI), a preventive medical step of early detection and evaluation of brain tumor is done. Magnetic resonance imaging (MRI) offers detailed information on human delicate tissue, which aids in the diagnosis of a brain tumor. The proposed method in this paper is Brain Tumour Detection and Classification based on Ensembled Feature extraction and classification using CNN.
Keywords: Segmentation, Brain Tumor, Convolutional Neural Network, Deep Learning.
Scope of the Article: Classification