Hershey, Pennsylvania
New York, New YorkBeijing, China
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 (Bhilai Institute of Technology, Durg, India) and Anup Mishra (Bhilai Institute of Technology, Durg, India)
Copyright: © 2021 |Pages: 9
DOI: 10.4018/IJCVIP.2021100102
OnDemand:
(Individual Articles)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

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.
Article Preview
Top

2. Methodology

2.1 Dataset

The experiment has been performed on BRATS 2013, 2015, 2017 dataset (Menze, 2014, Bakas, 2017; Sinha, 2014). The dataset consists of four modalities namely T1, T1C, T2, T2-Flair. Five ground truths are available, also known as labels which are necrosis, edema, non-enhancing tumor, enhancing tumor, everything else. Further details on dataset can be found in ((Menze, 2014, Bakas, 2017; Sinha, 2014).

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2025): Forthcoming, Available for Pre-Order
Volume 14: 1 Issue (2024)
Volume 13: 1 Issue (2023)
Volume 12: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 11: 4 Issues (2021)
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 2 Issues (2016)
Volume 5: 2 Issues (2015)
Volume 4: 2 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing