Welcome to the InfoSci Platform
Reference Hub1
Cognitive Brain Tumour Segmentation Using Varying Window Architecture of Cascade Convolutional Neural Network

Cognitive Brain Tumour Segmentation Using Varying Window Architecture of Cascade Convolutional Neural Network

Mukesh Kumar Chandrakar, Anup Mishra
Copyright: © 2021 |Volume: 11 |Issue: 4 |Pages: 9
ISSN: 2155-6997|EISSN: 2155-6989|EISBN13: 9781799862055|DOI: 10.4018/IJCVIP.2021100102
Cite Article Cite Article

MLA

Chandrakar, Mukesh Kumar, and Anup Mishra. "Cognitive Brain Tumour Segmentation Using Varying Window Architecture of Cascade Convolutional Neural Network." IJCVIP vol.11, no.4 2021: pp.21-29. http://doi.org/10.4018/IJCVIP.2021100102

APA

Chandrakar, M. K. & Mishra, A. (2021). Cognitive Brain Tumour Segmentation Using Varying Window Architecture of Cascade Convolutional Neural Network. International Journal of Computer Vision and Image Processing (IJCVIP), 11(4), 21-29. http://doi.org/10.4018/IJCVIP.2021100102

Chicago

Chandrakar, Mukesh Kumar, and Anup Mishra. "Cognitive Brain Tumour Segmentation Using Varying Window Architecture of Cascade Convolutional Neural Network," International Journal of Computer Vision and Image Processing (IJCVIP) 11, no.4: 21-29. http://doi.org/10.4018/IJCVIP.2021100102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Brain tumour segmentation is a growing research area in cognitive science and brain computing that helps the clinicians to plan the treatment as per the severity of the tumour cells or region. Accurate brain tumor detection requires measuring the volume, shape, boundaries, and other features. Deep learning is used to measure the characteristics without human intervention. The proper parameter setting and evaluation play a major role. Keeping this in mind, this paper focuses on varying window cascade architecture of convolutional neural network for brain tumour segmentation. The cognitive brain tumour computing is associated with the model using cognition concept for training data. The mixing of training data of different types of tumour images is applied to the model that ensures effective training. The feature space and training model improve the performance. The proposed architecture results in improvement in dice similarity, specificity, and sensitivity. The approach with improved performance is also compared with the existing approaches on the same dataset.

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.