Automated detection system for texture feature based classification on different image datasets using S-transform
- PDF / 1,047,087 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 96 Downloads / 209 Views
Automated detection system for texture feature based classification on different image datasets using S‑transform O. Homa Kesav1 · G. K. Rajini2 Received: 17 January 2020 / Accepted: 1 October 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The objective of this study is to present a computer-aided diagnosis (CAD) system for automatic detection of brain tumors in brain magnetic resonance (MR) image data sets as we consider the brain image dataset from the different datasets. The proposed system initially pre-processes the input images using Fuzzy C-means (FCM) for image segmentation. Subsequently, it utilizes variant of S-transform namely discrete orthonormal S-transform (DOST) to extract the texture features and its dimensionality is reduced using Principal component analysis (PCA) and linear discriminant analysis (LDA). The reduced features are then supplied to the proposed Adaboost algorithm with Random Forest (ADBRF) classifier where the random forest is used as the base classifier for classifying the abnormal brain tumors in MRI image datasets. The simulation results based on the five runs of k-fold stratified cross-validation indicate that the proposed method yields superior accuracy (98.26%) as compared to existing schemes. Keywords Discrete orthonormal S-transform (DOST) · Linear discriminant analysis (LDA) · Adaboost Random Forest (ADBRF)
1 Introduction Cancer has been a great threat to mankind since last few decades. Medical Fraternity, Scientists and Researchers have not only worked on curing this menace but are focusing on early detection so that the medical fraternity and patients have enough time to counter this and nip the disease in the bud. Brain is one of the most complex organs in the human body that works with billions of cells. A brain tumor arises when there is uncontrolled division of cells forming an abnormal group of cells around or inside the brain. That group of cells can affect the normal functionality of the brain activity and destroy the healthy cells (Kavitha et al. 2016; Christ and Parvathi 2012). Brain tumors classified to benign or low-grade (grade I and II) and malignant tumors or high-grade (grade * O. Homa Kesav [email protected] G. K. Rajini [email protected] 1
School of Electronics Engineering, VIT University, Vellore, India
School of Electrical Engineering, VIT University, Vellore, India
2
III and IV). Benign tumors are nonprogressive (non-cancerous) so considered to be less aggressive, they originated in the brain and grows slowly; also it cannot spread to anywhere else in the body. However, malignant tumors are cancerous and grow rapidly with undefined boundaries. They can be originated in the brain itself which called primary malignant tumor or to be originated elsewhere in the body and spread to the brain which called secondary malignant tumor (Khambhata and Panchal 2016; Kaur and Rani 2016; Das and Rajan 2016). Brain magnetic resonance imaging (MRI) is one of the best imaging techniques that researchers relied on for de
Data Loading...
