A Hybrid Feature Extraction Method With Regularized Extreme Learning Machine for Brain Tumor Classification

Abstract

Brain cancer classification is an important step that depends on the physician's knowledge and experience. An automated tumor classification system is very essential to support radiologists and physicians to identify brain tumors. However, the accuracy of current systems needs to be improved for suitable treatments. In this paper, we propose a hybrid feature extraction method with a regularized extreme learning machine (RELM) for developing an accurate brain tumor classification approach. The approach starts by preprocessing the brain images by using a min-max normalization rule to enhance the contrast of brain edges and regions. Then, the brain tumor features are extracted based on a hybrid method of feature extraction. Finally, a RELM is used for classifying the type of brain tumor. To evaluate and compare the proposed approach, a set of experiments is conducted on a new public dataset of brain images. The experimental results proved that the approach is more effective compared with the existing state-of-the-art approaches, and the performance in terms of classification accuracy improved from 91.51% to 94.233% for the experiment of the random holdout technique.INDEX TERMS Brain tumor classification, hybrid feature extraction, NGIST features, PCA, regularized extreme learning machine.

Neural memory plasticity for medical anomaly detection

“…In [13] the authors investigate the utility of capsule networks for exploiting the spatial relationships within the image. In [38] the authors propose the use of the GIST descriptor with PCA for feature extraction as opposed to using deep learned features. In addition, we utilise the baseline memory model of [1] in our comparisons.…”

“…Therefore, what is defined as normal for one subject can be abnormal for another, requiring learning of abnormal and normal scenarios in order to discriminate. Hence most approaches in the medical domain have used supervised learning [13,36,37,38]. With the recent spectacular success of deep learning methods for automatically learning task specific features, hand engineered features have been replaced by deep learned features for medical anomaly detection.…”

An optimized approach for extensive segmentation and classification of brain MRI

“…A work of Zhan et al [16] has discussed Glioma segmentation mechanisms by using multiple classifier based collaborative training. Literature has also witnessed usage of feature extraction along with learning approach method for assisting classification of brain as seen in the work of Gumaei et al [17].…”

Modelling and Forecasting of COVID-19 in India

“…Covid-19 has no specific treatment and it spreads quickly; it is crucial to make healthcare services for future cases [2]. Machine learning and approximation algorithms have been used to solve problems in areas such as healthcare [3], industry [4], cloud computing [5,6], human activity recognition [7], and brain tumor classification [8]. Machine learning models are certainly useful to forecast future cases to take control of this global pandemic [9][10][11].…”