Welcome to the InfoSci Platform
Reference Hub13
Machine Learning Approach for Brain Tumor Detection and Segmentation

Machine Learning Approach for Brain Tumor Detection and Segmentation

Adesh Kumar, Pavan Chauda, Aakanksha Devrari
Copyright: © 2021 |Volume: 11 |Issue: 3 |Pages: 17
ISSN: 1947-9344|EISSN: 1947-9352|EISBN13: 9781799861188|DOI: 10.4018/IJOCI.2021070105
Cite Article Cite Article

MLA

Kumar, Adesh, et al. "Machine Learning Approach for Brain Tumor Detection and Segmentation." IJOCI vol.11, no.3 2021: pp.68-84. http://doi.org/10.4018/IJOCI.2021070105

APA

Kumar, A., Chauda, P., & Devrari, A. (2021). Machine Learning Approach for Brain Tumor Detection and Segmentation. International Journal of Organizational and Collective Intelligence (IJOCI), 11(3), 68-84. http://doi.org/10.4018/IJOCI.2021070105

Chicago

Kumar, Adesh, Pavan Chauda, and Aakanksha Devrari. "Machine Learning Approach for Brain Tumor Detection and Segmentation," International Journal of Organizational and Collective Intelligence (IJOCI) 11, no.3: 68-84. http://doi.org/10.4018/IJOCI.2021070105

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Brain tumor is one type of disease that affects the brain directly. MRI is the finest imaging technique for a brain tumor and features information about tumor size, location, and type. MR images are most appropriate for brain studies because it has the best content in soft tissue. The segmentation, detection, and extraction of contaminated tumor area from magnetic resonance (MR) images are prime concerns, but very tedious tasks for radiologists or medical practitioners, and the accuracy depends on their experience. The automatic brain tumor detection and segmentation of MR images help the clinical experts to carry the treatment in a specific direction. The image segmentation methods play a very important role in automatic segmentation of MR images. The research article emphasises the comparative performance analysis of the different image segmentation algorithms such as Otsu's, watershed, level set, k-means, and DWT for brain tumor detection application. The MATLAB simulation is performed for all these algorithms on online images of brain tumor image segmentation benchmark (BRATS) dataset-2012. The performance of these methods is analysed based on response time and measures such as precision, recall, and accuracy. The predicted accuracy of Otsu's, watershed, level set, k-means and DWT algorithms using machine-learning model are 73.90%, 78.12%. 81.90%, 84.75%, and 88.12%, respectively. DWT has proven the good score for tumor detection applications.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.