A Biologically Inspired ELM-based Framework for Classification of Brain MRIs

Abstract

<span style="font-size: 11.0pt; line-height: 107%; font-family: 'Times New Roman',serif; mso-fareast-font-family: Calibri; mso-fareast-theme-font: minor-latin; mso-ansi-language: EN-IN; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;">Use of medical images for clinical analysis of various critical diseases have become increasingly predominant in modern health care systems. Application of machine learning technique in this context evolves as a potential solution in terms providing faster output with high diagnostic accuracy. In this work we propose an Extreme Learning Machine (ELM) based classifier SFLA-ELM for detection of normal and pathological brain condition from brain Magnetic Resonance Images (MRIs). ELM is known for its speed and accuracy whereas the proposed method uses a swarm based evolutionary technique Shuffled Frog Leaping Algorithm (SFLA) and 10-fold cross validation method to optimally determine the network parameter of the ELM for better classification performance.</span><span style="font-size: 11.0pt; line-height: 107%; font-family: 'Times New Roman',serif; mso-fareast-font-family: 'Droid Sans Fallback'; mso-ansi-language: EN-IN; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;"> The proposed model is experimented on three different brain MRI datasets of three different brain diseases. </span><span style="font-size: 11.0pt; line-height: 107%; font-family: 'Times New Roman',serif; mso-fareast-font-family: Calibri; mso-fareast-theme-font: minor-latin; mso-ansi-language: EN-IN; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;">To get better approximation accuracy and generalization ability for the base ELM classifier, the suitable activation function and the appropriate number of hidden layer nodes are chosen. The performance validation of the proposed framework is done under two different network conditions, i.e. fixed network structure and varying network structure, by comparing its performance with two standard hybridized ELM classifiers, namely, PSO-ELM and ABC-ELM. The comparative performance analysis suggests that the proposed SFLS-ELM gives better classification performance in diagnosing the diseases in terms of accuracy, sensitivity, specificity, F-score and Area under ROC curve (AUC).Furthermore, the SFLA-ELM also found to offer better generalization ability and better stability with more compact network structure.</span><span style="font-size: 22.0pt; mso-bidi-font-size: 16.0pt; line-height: 107%; font-family: 'Times New Roman',serif; mso-fareast-font-family: Calibri; mso-fareast-theme-font: minor-latin; mso-ansi-language: EN-IN; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;">A Biologically Inspired ELM-based Framework for Classification of Brain MRIs</span>

A Systematic Review on Metaheuristic Optimization Techniques for Feature Selections in Disease Diagnosis: Open Issues and Challenges

“…In [ 41 ], an algorithm was used to classify brain MRIs (magnetic resonance imaging) based on an Extreme Learning Machine using the Shuffled Frog Leaping algorithm. Likewise, the authors in [ 42 ] worked on an algorithm for brain disease detection.…”

A Novel MRI And CT Image Fusion Based on Discrete Wavelet Transform and Principal Component Analysis for Enhanced Clinical Diagnosis

“…One of its benefits is that MRI is safe for babies and women who are expecting a child because it does not utilize radiations but simply radio waves in the FM range. It also aids in the examination of non-bony or soft tissue structures such as the spine, brain, heart and eyes which is more accurate than the CT scans [3].…”

Analysis of Physicochemical Natures of Modern Artifacts in MRI

“…The research obtained 98% accuracy in detecting tumor or human brain's abnormality [13]. For classifying brain MRIs, a biologically inspired framework based on Extreme Learning Machine (ELM) is very effective [14].…”