MRI Brain Images Classification: A Multi-Level Threshold Based Region Optimization Technique

Abstract

Medical image processing is the most challenging and emerging field nowadays. Magnetic Resonance Images (MRI) act as the source for the development of classification system. The extraction, identification and segmentation of infected region from Magnetic Resonance (MR) brain image is significant concern but a dreary and time-consuming task performed by radiologists or clinical experts, and the final classification accuracy depends on their experience only. To overcome these limitations, it is necessary to use computer-aided techniques. To improve the efficiency of classification accuracy and reduce the recognition complexity involves in the medical image segmentation process, we have proposed Threshold Based Region Optimization (TBRO) based brain tumor segmentation. The experimental results of proposed technique have been evaluated and validated for classification performance on magnetic resonance brain images, based on accuracy, sensitivity, and specificity. The experimental results achieved 96.57% accuracy, 94.6% specificity, and 97.76% sensitivity, shows the improvement in classifying normal and abnormal tissues among given images. Detection, extraction and classification of tumor from MRI scan images of the brain is done by using MATLAB software.

Social-Group-Optimization based tumor evaluation tool for clinical brain MRI of Flair/diffusion-weighted modality

“…This study confirms that the image fusion approach facilitates superior image performance measures compared with the MRI with single modality. Kanmani and Marikkannu implemented a tumor mining and classification approach which obtained better statistical measures [5]. Nilesh et al proposed a detailed evaluation of brain tumor examination and classification procedure for brain MRI analysis [6].…”

“…Mapping of brain signal along with the brain image is also a flourishing research field [4]. To have superior perceptive on brain irregularity, it is essential to consider imaging procedures, such as Magnetic Resonance Imaging (MRI), Computed Tomography (CT) and Positron Emission Tomography (PET), which are widely adopted in clinics [5][6][7]. PET is a nuclear imaging procedure normally used along with CT. MRI is one of the widely used in medical domain to acquire images of internal body parts.…”

Analysis of the Curative Effect of Posterior Approach on Lumbar Brucellar Spondylitis with Abscess through Magnetic Resonance Imaging under Improved Watershed Algorithm

“…The use of medication alone for the treatment of BS is often unsatisfactory. At the same time, there are reports showing that for patients whose drug treatment is not effective, simply prolonging the treatment time will not improve the treatment effect, but will increase the damage to the liver and kidney function [ 6 ]. On the basis of medical treatment of lumbar brucellosis spondylitis, surgical operations can directly reach the diseased vertebral body and intervertebral space, remove infected lesions, inflammatory granulation tissues, and abscesses, scrape off the sclerotic bone, and create good conditions for bone healing in the bone graft area.…”

Machine Learning for Brain Images Classification of Two Language Speakers

“…e use of Magnetic Resonance Imaging (MRI) has reached a high degree of sophistication because it is useful for analysing the brain and detecting its diseases; however, the structure quantification and tissues has not yet been completely solved [1,2]. Several machine learning (ML) techniques have been implemented to classify brain activity, diseases, and behaviours and have achieved approximate solutions from this discipline [3][4][5][6].…”