Brain MRI classification using discrete wavelet transform and bag-of-words

Ayadi, Wadhah; Elhamzi, Wajdi; Charfi, Imen; Ouni, Bouraoui; Atri, Mohamed

doi:10.1109/aset.2018.8379832

Cited by 6 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence the need to find biometric features that are difficult to falsify, for example, magnetic resonance images (magnetic resonance brain print). The difference in rest or relaxation times led to tissue variability, which is the best option among all available imaging methods (Ayadi et al, 2018;Raja, 2019). Many studies and researches consider biometric features of brain fingerprints, the most common of them are discuss.…”

Section: Introductionmentioning

confidence: 99%

Human Identification Model Considering Biometrics Features

Radhi

2022

JLMA

View full text Add to dashboard Cite

In the medical field, brain classification is an effective technique for identifying a person through his brain print based on the hidden biometrics of high specificity included in the magnetic resonance images(MRI) of the brain, as this privacy strongly contributes to the issue of verification and identification of the person. In this paper, the brain print is extracted from the MRI obtained from 50 healthy people, which were passed through several pre-processing techniques in order to be used in the classification stage through convolutional neural network model, among those pre-classification stages, data collection after extracting the influential features for each image, which was based on linear discrimination analysis (LDA). The experimental results showed the importance of using LDA for feature extraction and adoption as input for K-NN and CNN classifiers. The classifiers proved successful in the classification if the features extracted with the help of LDA were adopted. Where CNN had the ability to classify with an accuracy of 99%, 82% for K-NN. The final stage in identifying a person through a brain fingerprint relied mainly on the model's success in classifying and predicting the remaining data in the testing stage.

show abstract

Section: Introductionmentioning

confidence: 99%

Human Identification Model Considering Biometrics Features

Radhi

2022

JLMA

View full text Add to dashboard Cite

show abstract

Pattern Descriptors Orientation and MAP Firefly Algorithm Based Brain Pathology Classification Using Hybridized Machine Learning Algorithm

Deepa¹,

Murugappan

Sumithra

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Magnetic Resonance Imaging (MRI) is a significant technique used to diagnose brain abnormalities at early stages. This paper proposes a novel method to classify brain abnormalities (tumor and stroke) in MRI images using a hybridized machine learning algorithm. The proposed methodology includes feature extraction (texture, intensity, and shape), feature selection, and classification. The texture features are extracted by intending a neoteric directional-based quantized extrema pattern. The intensity features are extracted by proposing the clustering-based wavelet transform. The shape-based extraction is preformed using conventional shape descriptors. Maximum A Priori (MAP) based firefly algorithm is proposed for feature selection. Finally, hybridized support vector-based random forest classifier is used for the classification. The MRI brain tumor and stroke images are detected and categorized into four classes which are a high-grade tumor, a low-grade tumor, an acute stroke, and a sub-acute stroke. Besides, three different regions are identified in tumor detection such as edema, and tumor (necrotic and non-enhancing) region. The accuracy of the proposed method is analyzed using various performance metrics in comparison with the few state-of-the-art classification methods. The proposed methodology successfully achieves a reliable accuracy of 88.3% for classifying brain tumor cases and 99.2% for brain stroke classification. The best F-score of 0.91 and the least FPR of 0.06 are attained while considering brain tumor classification against the proposed HSVFC. Likewise, HSVFC has 0.99 as the best F-score and a 0.0 FPR in the case of brain stroke classification. The experimental analysis offers a maximum mean accuracy of different classifiers for categorizing MRI brain tumor are 76.

show abstract