Titre :

Segmentation and classification of benign and malignant breast tumors via texture characterization from ultrasound images

Auteur(s) :

Benaouali, Mohamed [Auteur]
Bentoumi, Mohamed [Auteur]
Touati, Menad [Auteur]
Tahleb Ahmed, Abdelmalik [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Mimi, Malika [Auteur]

Titre de la manifestation scientifique :

2022 7th International Conference on Image and Signal Processing and their Applications (ISPA)

Ville :

Mostaganem

Pays :

Algérie

Date de début de la manifestation scientifique :

2022-05-08

Titre de l’ouvrage :

2022 7th International Conference on Image and Signal Processing and their Applications (ISPA)

Titre de la revue :

Segmentation and classification of benign and malignant breast tumors via texture characterization from ultrasound images

Éditeur :

IEEE

Date de publication :

2022-06-03

Mot(s)-clé(s) en anglais :

Ultrasound images
Breast tumor
Segmentation
HOG features
LBP features
Classification

Discipline(s) HAL :

Sciences de l'ingénieur [physics]

Résumé en anglais : [en]

The present paper deals with breast tumors classification from ultrasound images. The proposed procedure consists of four steps, namely preprocessing, segmentation, feature extraction and classification. To improve the ...
Lire la suite >The present paper deals with breast tumors classification from ultrasound images. The proposed procedure consists of four steps, namely preprocessing, segmentation, feature extraction and classification. To improve the quality of ultrasound images, the preprocessing step consists of anisotropic filtering and histogram equalization that are performed on the original images. The segmentation is performed on the preprocessed images using the Level Set method that allows to extract the region of interest (ROI) and to reduce its size at the same time. Two feature extraction methods are used in this work namely, the local binary pattern (LBP) method and the histogram of oriented gradients (HOG) method. The two methods (LBP and HOG) are techniques of textures analysis and allow to characterize the ROI. The extracted feature sets constitute the inputs for three classifiers namely, support vector machines (SVM), k-nearest neighbors (KNN) and decision trees (DT). In this work, the best results are obtained by the concatenation of the two feature vectors namely LBP and HOG associated to the SVM classifier. This allows to achieve an accuracy of 96%, a sensitivity of 97% and a specificity of 94%.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Institut d'Électronique, de Microélectronique et de Nanotechnologie (IEMN) - UMR 8520

Source :

Harvested from HAL