Brain tumors detection and segmentation in MR images: Gabor wavelet vs. statistical features

Nabizadeh, Nooshin; Kubát, Miroslav

doi:10.1016/j.compeleceng.2015.02.007

Cited by 230 publications

(105 citation statements)

References 28 publications

Supporting

Mentioning

102

Contrasting

Unclassified

Order By: Relevance

“…In order to discuss the relation between lung adenocarcinoma CT images and EGFR mutation, we will focus on feature extraction and classification in this paper, and discuss the related literature. In 2015, the scholars, Nooshin Nabizadeh and Miroslav Kubat, published a paper about brain tumor detection and segmentation based on MR images [3]. They compared the capability and efficacy of two different feature sets -Gabor wavelets and statistical features -in automated segmentation of brain tumor lesions in MRI images.…”

Section: Related Workmentioning

confidence: 99%

“…Gabor Wavelet can capture the local structure of the image corresponding to spatial frequency, spatial localization and orientation selectivity, so it is usually applied to texture analysis and image segmentation [3]. In the spatial domain, a two-dimensional Gabor filter is a Gaussian kernel function modulated by a complex sinusoidal plane wave, defined as (6):…”

Section: ) the Texture Feature In Frequency Domainmentioning

confidence: 99%

See 1 more Smart Citation

The Identification of EGFR Mutation Based on the CT Image of Lung Adenocarcinoma

Tsan¹,

Tsai²,

Chin³

2016

IJIEE

View full text Add to dashboard Cite

Abstract-Lung adenocarcinoma is the most common cause of lung cancer in Taiwan. However, it is difficult to detect lung adenocarcinoma at early stage. Most radiologists usually decide the treatment strategies by screening whether the patients have the epidermal growth factor receptor (EGFR) gene mutations or not. However, the screen is expensive and time-consuming. Therefore, the aim of the present paper is to identify whether there are EGFR mutations in tumors with CT image. We segment the whole region of lung adenocarcinoma and extract the texture features in spatial domain and frequency domain using GLCM and Gabor Wavelet. Finally we use Neuro-fuzzy based AdaBoost to classify and identify the relationship between the texture features of lung adenocarcinoma CT images and EGFR mutations. The experimental result in this paper shows that our success rate was 92%, and we will improve our methods to increase the recognition rate in the future.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: ) the Texture Feature In Frequency Domainmentioning

confidence: 99%

The Identification of EGFR Mutation Based on the CT Image of Lung Adenocarcinoma

Tsan¹,

Tsai²,

Chin³

2016

IJIEE

View full text Add to dashboard Cite

show abstract

“…Right after carrying out this unfamiliar growth is going to be removed from the specific MR picture and special spot and also style tend to be determined as well as other factors just like exterior, eccentricity, entropy and also centroid are actually calculated. Nabizadeh, Nooshin, plus Miroslav Kubat [16] introduced a completely computerized method, which usually may identify slices that come with unknown growth plus, so that you can delineate the actual unknown growth area. The actual experimental final results upon single comparison system show the actual effectiveness with their planned procedure with productively segmenting mental faculties unknown growth tissue with high exactness plus lower computational complexity.. AbdelMaksoud et al [17] introduced a simple yet effective photo segmentation strategy making use of K-means clustering procedure included together with Fluffy C-means algorithm.…”

Section: Literature Surveymentioning

confidence: 99%

Improvement of Brain Tumor Feature based Segmentation using Decision based Alpha Trimmed Global Mean Filter

Sharma¹,

Singh²

2015

IJCA

View full text Add to dashboard Cite

Detection of the brain tumor is an important application of medical image processing. The literature survey in this paper has shown that the many of the existing methods has unobserved the deprived quality images like images with amount of noise or poor brightness. Moreover the much of the existing work on tumor detection has abandoned the use of object based segmentation. The overall goal of this research work is to propose an efficient brain tumor detection using the feature detection androundness metric. To enhance the tumor detection rate further we have integrated the proposed object based tumor detection with the Decision based alpha trimmed global mean. The proposed technique has the ability to produce effective results even in case of high density of the noise.

show abstract

“…The texture characteristics of extracted tumor which correspond to second-order statistics features such as the gray level co-occurrence matrix and gray level run length matrix [16,19]. The gray level co-occurrence matrix (GLCM) is a statistical method used to analyze the texture of the image.…”

Section: Second Order Statistic Featuresmentioning

confidence: 99%

“…Feature selection play important role in many classification problems [17][18][19]. There are several algorithms proposed for feature selection such as absolute value two-sample t-test with pooled variance estimate, principal component analysis (PCA), independent component analysis (ICA) and genetic algorithm.…”

Section: Introductionmentioning

confidence: 99%

Evaluating the Efficiency of different Feature Sets on Brain Tumor Classification in MR Images

Eltayeb¹,

Salem²,

Al-Atabany³

2018

IJCA

View full text Add to dashboard Cite

In this paper, a study for evaluating the efficacy of different feature sets that used brain tumor classification is presented. Different features sets are extracted as shape, 1 st order texture features (FOS), 2 nd order (GLCM, GLRLM), boundary features, and wavelet-based features. The brain tumors are extracted using the k-means clustering algorithm. Then different classifiers such as Artificial Neural Network (ANN), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM) were used in the classification process.A set of 65 real and simulated (Flair modality) MRI images from multimodal brain tumor image segmentation benchmark (BRATS) organized by MICCAI 2012 challenge is used for performance evaluation. The overall segmentation results for the 65 volumes are 90.15±0.12. For the Feature sets efficacy step, the highest accuracy of 94.74% is achieved by the SVM when using the wavelet-based features. The lowest accuracy achieved by the three classifiers obtained when using the second order texture features..

show abstract

Brain tumors detection and segmentation in MR images: Gabor wavelet vs. statistical features

Cited by 230 publications

References 28 publications

The Identification of EGFR Mutation Based on the CT Image of Lung Adenocarcinoma

The Identification of EGFR Mutation Based on the CT Image of Lung Adenocarcinoma

Improvement of Brain Tumor Feature based Segmentation using Decision based Alpha Trimmed Global Mean Filter

Evaluating the Efficiency of different Feature Sets on Brain Tumor Classification in MR Images

Contact Info

Product

Resources

About