Title CSO-based algorithm with support vector machine for brain tumor's disease diagnosis

Taie, Shereen A.; Ghonaim, Wafaa

doi:10.1109/percomw.2017.7917554

Cited by 24 publications

(22 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CSO is also applied for solving problems of other areas like diagnosis of brain tumor, feature selection, and 0-1 knapsack problem. Taie & Ghonaim (2017) concerned with maximization of profit and minimization of weight of the items present in the set. The authors solved ten varieties of 0-1 knapsack problem by BGCSO.…”

Section: Othersmentioning

confidence: 99%

Recent Studies on Chicken Swarm Optimization algorithm: a review (2014–2018)

et al. 2019

View full text Add to dashboard Cite

We would like to thank the reviewers and the Editor for their valuable time spent on reviewing our manuscript and for the constructive comments that have been given. The responses to the reviewer's comments are provided in the following sections in the order of the comments received. The reviewers' comments are cited in italics, while the answers are in regular font. Reviewer 1 Comment 1 Please rephrase: Table 5 Strength Weakness and Future works related to CSO to be Table 5. Strength, weakness, and future works of CSO.

show abstract

Section: Othersmentioning

confidence: 99%

Recent Studies on Chicken Swarm Optimization algorithm: a review (2014–2018)

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Sonar and Bhosle in year 2016 suggested many nature inspired algorithms such as Ant Colony Optimization (ACO) algorithm, Cuckoo Search (CS), Firefly Algorithm (FA) and Particle Swarm Optimization (PSO) for the classification of brain tumor from any MRI image [13]. In the similar work related to brain tumor classification, Taie and Ghonaim applied CS for the feature reduction [14]. Karnan and Logheshwari (2010) implemented ACO with Fuzzy Logic to segment brain tumor from MRI [15].…”

Section: Literature Reviewmentioning

confidence: 99%

A Hybrid Framework for Brain Tumor Classification using Grey Wolf Optimization and Multi-Class Support Vector Machine

Kumar*¹,

Ansari²,

Ashok³

2019

IJRTE

View full text Add to dashboard Cite

 Abstract: Medical image processing has a vital role in the detection of diseases in human beings. The accuracy for disease detection using any medical image is highly dependent on the image processing methods. Features extraction and reduction are the two key steps during the medical image processing for disease classification. To develop an effective and efficient mechanism with high accuracy for classification of malignant brain tumor from Magnetic Resonance Imaging (MRI) is the objective of the present research. To achieve this, a nature inspired algorithm; namely, Grey Wolf Optimization (GWO) along with a classification method, multiclass Support Vector Machine (MSVM) is used. Further, Results for the classification accuracy obtained from GWO are compared with other two well-known optimization algorithms such as Particle Swarm Optimization (PSO) and Firefly Algorithm (FA).

show abstract

“…An MSER feature is a steady connected component of some gray-level sets of the super-pixels [9]. E. Tumour Classification: It is a method to classify the types of tumour from extracted feature using MSER descriptor .MSER based SVM is used in the proposed BTDCS as a tumour classifier to classify the tumour as benign or malignant [10]. Motivation and contributions: Brain tumor segmentation and their classification is a standout amongst the most significant and troublesome assignments in numerous medicinal picture applications since it more often than not include an enormous measure of information.…”

Section: Figure 3: Framework Of Btdcsmentioning

confidence: 99%

“…Scarcely any cerebrum tumors are noncancerous (benevolent), and some brain tumor s are harmful (threatening). Brain tumor can start in your cerebrum (essential cerebrum tumors), or malignancy can start in different pieces of your body and spread to your mind (optional, or metastatic, cerebrum tumors) [5]. The locale of cerebrum tumor is given in the figure 1.…”

mentioning

confidence: 99%

An Automated Brain Tumour Boundary Detection using Region based Segmentation Technique along with SVM Classifier

Dharnia*,

Wasson

2019

IJEAT

View full text Add to dashboard Cite

We presents a fully automated method for an automated brain-tumour boundary detection using region based segmentation technique along with SVM Classifier of Magnetic Resonance Imaging (MRI).The procedure is based on artificial intelligence technique and classification of each super-pixel in MRI. A number of novel image features extraction approaches including intensity-based, texture based, fractal analysis and curvatures are calculated from each super-pixel within the entire brain area in MRI to ensure a robust classification. Brain tumor is the malignant types of cancer and their classification in earlier stage is biggest issue. While curable with early classification is useful, only extremely trained specialists are capable of accurately recognizing the cancer from skin MRI data. As expertise is in limited contribute, an automated systems capable of classifying cancer could save human lives, and also help to reduce unnecessary MRI, and reduce extra costs. On the way to achieve this goal, we proposed a Brain Tumour Detection and Classification System (BTDCS) that combines recent developments in machine learning with Support Vector Machine (SVM) structure, creating hybrid algorithm of threshold based segmentation with Maximally Stable External Regions (MSER) that are capable of segmenting accurate super-pixel region from MRI, as well as analyzing the detected area and surrounding tissue for malignant. Using threshold based segmentation technique, the foreground and background component is separated into two regions. To improve the segmentation results, MSER is used with the novel concept of region detection and feature extraction mechanism. The proposed system is evaluated using the largest publicly accessible standard BRATS 2015 dataset of MRI, containing benign and malignant images. When the evaluation parameters of proposed work is compared with a few other state-of-art methods, the proposed means attains the best performance of 98.2% concerning classification accuracy using only the MSER approach and SVM as classifier. The ultimate aim of this research is to devise an automated experimental approach that can segment the tumor boundary in a fast and efficient manner.

show abstract

Title CSO-based algorithm with support vector machine for brain tumor's disease diagnosis

Cited by 24 publications

References 10 publications

Recent Studies on Chicken Swarm Optimization algorithm: a review (2014–2018)

Recent Studies on Chicken Swarm Optimization algorithm: a review (2014–2018)

A Hybrid Framework for Brain Tumor Classification using Grey Wolf Optimization and Multi-Class Support Vector Machine

An Automated Brain Tumour Boundary Detection using Region based Segmentation Technique along with SVM Classifier

Contact Info

Product

Resources

About